CN119010203A

CN119010203A - AC/DC micro-grid energy scheduling method and device

Info

Publication number: CN119010203A
Application number: CN202310558701.6A
Authority: CN
Inventors: 严帅; 李盈盈; 边卓伟; 张新; 罗雯予; 董虹妤
Original assignee: State Power Investment Group Science and Technology Research Institute Co Ltd
Current assignee: State Power Investment Group Science and Technology Research Institute Co Ltd
Priority date: 2023-05-17
Filing date: 2023-05-17
Publication date: 2024-11-22

Abstract

The invention provides an AC/DC micro-grid energy scheduling method and device, wherein the method is used for scheduling energy by evaluating whether the power supply of a renewable power supply in a micro-grid model meets the power demand of load equipment connected with the micro-grid model or not, and under the condition that the power supply meets the power demand, each renewable power supply in the renewable power supply topology information is called according to capacity prediction information and energy routing topology information; and under the condition of unsatisfied condition, generating demand deviation information according to the capacity prediction information and the power demand information, and calling each loss power supply in the loss power supply topology information to supplement energy based on the demand deviation information and the energy routing topology information. Therefore, the capacity of renewable energy sources in the micro-grid model can be predicted through real-time analysis, when the capacity of the renewable energy sources can not meet the demand information, loss power supply supplement is timely called, the power distribution proportion is dynamically adjusted according to the capacity prediction of the renewable energy sources, and the flexibility, the intelligence and the applicability of energy scheduling are improved.

Description

AC/DC micro-grid energy scheduling method and device

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to an alternating current/direct current micro-grid energy scheduling method and device.

Background

The rapid development of micro-grids provides a new trend for power development, renewable energy sources in various forms gradually permeate into the micro-grids in the form of distributed power sources, but the renewable energy sources are influenced by geographic conditions, environmental factors, time dimension, space dimension and the like, so that the distributed power sources have larger randomness, and the electric energy quality of grid connection points is easy to be poor. Therefore, the energy routing is provided for regulating and coordinating the electric energy of the distributed power supply and then is integrated into the power grid, so that the electric energy quality is ensured, and in the process, an energy scheduling strategy becomes a key for ensuring the electric energy quality.

The existing energy routing is mainly responsible for flexible access and intelligent management of micro power grids and large power grids, and the coordinated scheduling of distributed power supplies and traditional power grid power supplies is processed according to manual preset rules, so that the flexibility and the intelligence are low, and the technical problem that the applicability of energy scheduling strategies cannot be guaranteed exists.

Disclosure of Invention

The present invention aims to solve at least one of the technical problems in the related art to some extent.

Therefore, a first objective of the present invention is to provide an ac/dc micro-grid energy scheduling method, so as to predict the capacity of renewable energy sources in a micro-grid model through real-time analysis, and when the capacity of renewable energy sources can not meet the requirement information, timely retrieve the consumed power supply supplement, dynamically adjust the distribution ratio according to the capacity prediction of renewable energy sources, improve the flexibility, intelligence and applicability of energy scheduling, and solve the technical problems that the flexibility and intelligence of the processing mode relying on manual preset rules in the related art are lower and the applicability of energy scheduling strategies can not be guaranteed.

The second purpose of the invention is to provide an AC/DC micro-grid energy dispatching device.

A third object of the present invention is to propose an electronic device.

A fourth object of the present invention is to propose a computer readable storage medium.

A fifth object of the invention is to propose a computer programme product.

To achieve the above objective, an embodiment of a first aspect of the present invention provides a method for energy scheduling of an ac/dc micro-grid, including:

traversing the micro-grid model to generate grid topology information;

generating energy routing topology information, renewable power supply topology information and loss power supply topology information according to the power grid topology information;

generating power demand information of the micro-grid model according to at least one load device connected to the micro-grid model;

Carrying out capacity prediction on each renewable power supply in the renewable power supply topology information to obtain capacity prediction information of the micro-grid model;

under the condition that the capacity prediction information meets the power demand information, according to the capacity prediction information and the energy routing topology information, each renewable power supply in the renewable power supply topology information is called to carry out energy scheduling;

And under the condition that the capacity prediction information does not meet the power demand information, generating demand deviation information according to the capacity prediction information and the power demand information, and calling each power loss in the power loss topology information to carry out energy supplement based on the demand deviation information and the energy routing topology information.

To achieve the above object, an embodiment of a second aspect of the present invention provides an ac/dc micro-grid energy dispatching device, including:

the first generation module is used for traversing the micro-grid model and generating grid topology information;

the second generation module is used for generating energy routing topology information, renewable power supply topology information and loss power supply topology information according to the power grid topology information;

The third generation module is used for generating power demand information of the micro-grid model according to at least one load device connected to the micro-grid model;

the prediction module is used for predicting the productivity of each renewable power supply in the renewable power supply topology information so as to obtain the productivity prediction information of the micro-grid model;

The first processing module is used for calling each renewable power supply in the renewable power supply topology information to perform energy scheduling according to the capacity prediction information and the energy routing topology information under the condition that the capacity prediction information meets the power demand information;

And the second processing module is used for generating demand deviation information according to the capacity prediction information and the power demand information under the condition that the capacity prediction information does not meet the power demand information so as to call each power loss in the power loss topology information to carry out energy supplement based on the demand deviation information and the energy routing topology information.

To achieve the above object, an embodiment of a third aspect of the present invention provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the ac/dc microgrid energy scheduling method of the first aspect described above.

To achieve the above object, an embodiment of a fourth aspect of the present invention proposes a computer-readable storage medium storing computer instructions for causing the computer to execute the ac/dc micro grid energy scheduling method of the first aspect.

In order to achieve the above object, an embodiment of a fifth aspect of the present invention proposes a computer program product comprising a computer program which, when executed by a processor, implements the ac/dc microgrid energy scheduling method of the first aspect described above.

The technical scheme provided by the embodiment of the invention comprises the following beneficial effects:

Generating power grid topology information by traversing the micro-grid model, generating energy routing topology information, renewable power source topology information and loss power source topology information according to the power grid topology information, generating power demand information of the micro-grid model according to at least one load device connected to the micro-grid model, carrying out capacity prediction on each renewable power source in the renewable power source topology information to obtain capacity prediction information of the micro-grid model, calling each renewable power source in the renewable power source topology information to carry out energy scheduling according to the capacity prediction information and the energy routing topology information when the capacity prediction information meets the power demand information, and generating demand deviation information according to the capacity prediction information and the power demand information when the capacity prediction information does not meet the power demand information so as to call each loss power source in the loss power source topology information to carry out energy supplement based on the demand deviation information and the energy routing topology information. Therefore, the capacity of renewable energy sources in the micro-grid model can be analyzed and predicted in real time, when the capacity of the renewable energy sources can not meet the demand information, the loss power supply supplement is timely called, the power distribution proportion is dynamically adjusted according to the capacity prediction of the renewable energy sources, the flexibility, the intelligence and the applicability of energy scheduling are improved, and the technical problems that the mode flexibility and the intelligence of processing by relying on manual preset rules in the related technology are low and the applicability of energy scheduling strategies can not be guaranteed are solved.

Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.

Drawings

The foregoing and/or additional aspects and advantages of the invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:

Fig. 1 is a schematic flow chart of an ac/dc micro grid energy scheduling method according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of generating energy routing topology information, renewable power source topology information and lossy power source topology information according to an embodiment of the present invention;

Fig. 3 is a schematic flow chart of generating power demand information of a micro-grid model according to an embodiment of the present invention;

FIG. 4 is a schematic flow chart of obtaining capacity prediction information of a micro-grid model according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of an ac/dc micro-grid energy dispatching device according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.

The distributed power sources in the micro-grid, such as a wind power generation system, a hydroelectric power generation system, a photovoltaic power generation system and a large power grid, can input stable electric energy information only through energy routing adjustment when being connected with the grid, and a coordination control strategy between a traditional power source and the distributed power source is the main working content in the process, and the coordination control strategy in the prior art mainly depends on manual setting rules to process, such as the distribution proportion of the distributed energy source and the traditional power source, and the like.

In order to solve the problem, the embodiment of the invention provides an AC/DC micro-grid energy scheduling method, which is used for predicting the capacity of renewable energy sources in a micro-grid model through real-time analysis, and timely retrieving loss power supply supplement when the capacity of the renewable energy sources can not meet the demand information, and dynamically adjusting the power distribution proportion aiming at the capacity prediction of the renewable energy sources, so that the flexibility, the intelligence and the applicability of energy scheduling are improved, and the technical problems that the flexibility and the intelligence of a mode relying on manual preset rules for processing in the related technology are lower and the applicability of an energy scheduling strategy can not be ensured are solved.

The following describes an ac/dc micro grid energy scheduling method and apparatus according to an embodiment of the present invention with reference to the accompanying drawings.

It should be noted that, all actions of acquiring signals, information or data in the present invention are performed under the condition of conforming to the corresponding data protection rule policy of the country of the location and obtaining the authorization given by the owner of the corresponding device.

Fig. 1 is a flow chart of an ac/dc micro-grid energy scheduling method according to an embodiment of the present invention, where it is to be noted that, in the embodiment, the ac/dc micro-grid energy scheduling method is performed by an ac/dc micro-grid energy scheduling device, and the ac/dc micro-grid energy scheduling device may be implemented by software and/or hardware, and the ac/dc micro-grid energy scheduling device may be configured in an electronic device, and an execution body is described below as an example of the electronic device.

As shown in fig. 1, the ac/dc micro-grid energy scheduling method includes the following steps:

step S101, traversing the micro-grid model to generate grid topology information.

The micro-grid model is a virtual or semi-virtual model which is constructed based on a simulation technology and simulates the operation of an actual power system by modeling and mathematic of the power system, and various operation conditions of the actual power system can be analyzed by computer means, so that the stability and safety of micro-grid operation control are improved. The micro-grid model comprises all types of power information in an actual micro-grid and power information of the actual micro-grid which is added in advance; the method comprises the steps of including all types of loads and load devices in an actual micro-grid and adding the loads and the load devices of the actual micro-grid in advance; including grid line connection information between the various nodes, etc.

The power grid topology information refers to determined power grid topology information after analyzing the topological structure characteristics of each node of the power grid and the power grid line connection information in the micro-power grid model. The preferred analysis method is: and traversing the micro-grid model by taking different types of power supplies as starting points and multiple starting points in parallel according to current flow directions. Wherein the power supply is preferably identified as: a, b, c, etc. For example, traversing to a subsequent node may alternatively be identified in turn as: a1, a2; b1, b2; c1, c2, etc., if the third node of the two lines a and b has an intersection point, the optional label is ab3, and if the 4 th node of a and the 3 rd node of c have an intersection point, the optional label is a4c3. Based on the method, the micro-grid model is traversed, namely, grid topology information is generated, in the process, nodes in the topology structure can be identified according to different identification information, and further deployment positions of the nodes, parameter information of the nodes and the like can be scheduled based on the micro-grid model.

Step S102, generating energy routing topology information, renewable power supply topology information and loss power supply topology information according to the power grid topology information.

The energy routing topology information refers to topology information extracted from the power grid topology information and used for indicating energy routing relations.

The renewable power source topology information is power source topology information which is extracted from the power grid topology information and is used for indicating power source relation and the power source type is renewable energy. Exemplary are as follows: renewable power sources such as wind power, fan power, hydraulic power, and the like.

The power consumption topology information refers to power topology information extracted from power grid topology information, wherein the power topology information is used for indicating a power relation and the power type is nonrenewable energy, and is exemplified as follows: non-renewable resources such as grid power, i.e., non-renewable resource sources such as fuel, diesel, flint, etc.

Optionally, the energy routing topology information for indicating the energy routing relationship and the power supply topology information for indicating the power supply relationship can be extracted from the power grid topology information first, and then the power supply topology information is set to be in a state to be responded, so that the power supply topology information is used as an information basis for performing energy scheduling analysis later, and higher response speed can be ensured. And then, the regenerated power supply topology information and the lost power supply topology information are subjected to classification analysis so as to be convenient for differential scheduling by using energy routes according to power consumption requirements in the subsequent steps. As an example without limitation: the renewable power source is scheduled preferentially, the non-renewable power source is scheduled secondarily, and the aim of improving the environmental protection performance of energy scheduling is achieved.

Step S103, generating power demand information of the micro-grid model according to at least one load device connected to the micro-grid model.

Wherein, the load device refers to an electric power device with electricity consumption requirement connected to the micro-grid, including but not limited to: energy storage equipment and equipment to be charged.

Wherein the power demand information corresponds to the device type of the load device one by one. Alternatively, the power demand information of the micro-grid model may be generated by performing a power profile analysis on each load device accessing the micro-grid model, and generating a power demand type and a power parameter set of each load device based on the power demand type and the power parameter set. Wherein the power demand type is used to characterize the power type demanded by the load device, such as, for example: electric car-alternating current; charging a livestock battery-alternating current; energy storage-alternating current data and the like; the power parameter set is used to characterize specific information of the power demand, including but not limited to, demand current, demand voltage, and demand duration.

Step S104, carrying out capacity prediction on each renewable power source in the renewable power source topology information to obtain capacity prediction information of the micro-grid model.

The capacity prediction information may be determined by traversing each renewable power source in the renewable power source topology information to perform power yield prediction. Alternatively, the capacity prediction information may be capacity prediction information within a preset time period in the future. Wherein the optional preset time period is longer than or equal to the demand time period.

As an example, multiple types of distributed power sources can be called according to the topology information of the regenerated power sources, and then time sequence change information of the environment elements in a future preset time period can be extracted according to the types of the distributed power sources, so that capacity prediction information of the distributed power sources in the future preset time period can be estimated based on the time sequence change information of the environment elements, whether the capacity in the required time period meets the required electric energy of the electric power parameter set can be determined according to the capacity prediction information in a subsequent step, and flexible power transmission proportioning can be performed according to a judging result.

The preferable mode of capacity prediction is as follows: the capacity of the distributed power supply is predicted by the intelligent model, and the capacity is predicted by the machine learning models such as a decision tree model, an expert system, a neural network model and the like, so that the influence relationship of complex environmental elements on the capacity of different distributed power supplies can be fitted based on historical data, a more stable and accurate capacity prediction result is further determined, and a data feedback basis is provided for realizing energy scheduling with higher adaptability.

Step S105, when the capacity prediction information meets the power demand information, each renewable power source in the renewable power source topology information is called to perform energy scheduling according to the capacity prediction information and the energy routing topology information.

Specifically, the capacity prediction information and the power demand information may be compared, and whether the capacity prediction amount in the demand period satisfies the required power of the power parameter set may be determined, preferably, by determining whether the capacity prediction amount in the demand period satisfies the total power corresponding to the required current.

If the capacity prediction information meets the power demand information, the renewable power sources can meet the power demand of the power parameter set, and each renewable power source in the renewable power source topology information can be called to carry out energy scheduling according to the capacity prediction information and the energy routing topology information. For example, the energy route topology information corresponding to the distributed renewable power source can be traversed, the corresponding energy route is called to schedule and supply power to the renewable power source, and the converted voltage meets the required voltage.

Step S106, when the capacity prediction information does not meet the power demand information, the demand deviation information is generated according to the capacity prediction information and the power demand information, so that each power loss in the power loss topology information is invoked to supplement energy based on the demand deviation information and the energy routing topology information.

If the capacity prediction information does not meet the power demand information, it is indicated that the renewable power source is only dependent on the power demand information, and at this time, the demand deviation information for representing the difference between the power demand information and the capacity prediction information may be generated based on the capacity prediction information and the power demand information, so that each power loss in the power loss topology information is invoked to perform energy replenishment based on the demand deviation information and the energy routing topology information.

As a possible implementation manner, the energy supplementing of the demand deviation information by retrieving the power loss in the power loss topology information based on the energy routing topology information can be achieved by traversing the power loss topology information and the energy routing topology information. In particular, conventional power sources in large power grids may be scheduled for power scheduling.

Therefore, whether the power supply of the renewable power supply meets the power consumption requirement of the load is evaluated, if yes, the renewable power supply is fully called through the energy route, and if not, the renewable power supply is supplemented through the traditional power supply. The technical effects of energy conservation and environmental protection are achieved while sufficient power dispatching is ensured. Meanwhile, based on different capacity prediction information, the traditional power distribution and micro-grid power distribution proportion is dynamically adjusted, so that the method is more suitable for dynamically-changed power distribution scenes, and the intelligence of energy scheduling is improved.

According to the AC/DC micro-grid energy scheduling method, grid topology information is generated by traversing a micro-grid model, energy routing topology information, renewable power source topology information and loss power source topology information are generated according to the grid topology information, so that power demand information of the micro-grid model is generated according to at least one load device connected to the micro-grid model, capacity prediction is conducted on renewable power sources in the renewable power source topology information to obtain capacity prediction information of the micro-grid model, energy scheduling is conducted on renewable power sources in the renewable power source topology information according to the capacity prediction information and the energy routing topology information when the capacity prediction information meets the power demand information, demand deviation information is generated according to the capacity prediction information and the power demand information when the capacity prediction information does not meet the power demand information, and energy supplement is conducted on the loss power sources in the loss power source topology information based on the demand deviation information and the energy routing topology information. Therefore, the capacity of renewable energy sources in the micro-grid model can be analyzed and predicted in real time, when the capacity of the renewable energy sources can not meet the demand information, the loss power supply supplement is timely called, the power distribution proportion is dynamically adjusted according to the capacity prediction of the renewable energy sources, the flexibility, the intelligence and the applicability of energy scheduling are improved, and the technical problems that the mode flexibility and the intelligence of processing by relying on manual preset rules in the related technology are low and the applicability of energy scheduling strategies can not be guaranteed are solved.

According to the analysis, the energy routing topology information, the renewable power source topology information and the loss power source topology information can be generated according to the power grid topology information. The specific process of the electronic device executing step S102 is shown in fig. 2, and may include the following steps:

Step S201 extracts energy routing topology information for indicating an energy routing relationship and power supply topology information for indicating a power supply relationship from the grid topology information.

Wherein the power topology information is only used for indicating the power relation, and each power in the power topology information comprises a renewable power source and a non-renewable power source.

Step S202, traversing the power topology information to extract the power types so as to determine the power types of all the power sources in the power topology information.

Because each power supply in the power supply topology information comprises a renewable power supply and a non-renewable power supply, the power supply type of each power supply in the power supply topology information can be determined by traversing the power supply topology information to extract the power supply type. Exemplary are as follows: the determined power source type can be any one of a photovoltaic power source, a fan power source, a hydraulic power source and a power grid power source.

Step S203, generating regenerated power topology information and lost power topology information based on the power topology information according to the power type of each power in the power topology information.

After determining the power supply type of each power supply in the power supply topology information, the regenerated power supply topology information and the lost power supply topology information may be generated based on the power supply topology information according to the power supply type of each power supply in the power supply topology information. The regenerated power topology information refers to power topology information of which the power type is that renewable energy supplies power, and the regenerated power topology information is exemplified as follows: such as wind power, fan power, hydraulic power, and other renewable power types. The lossy power topology information refers to power topology information in which the power type supplies power to a non-renewable energy source, such as: non-renewable resources such as grid power, i.e., non-renewable resource sources such as fuel, diesel, flint, etc.

In summary, by classifying and analyzing the regenerated power topology information and the lost power topology information, differentiated scheduling by using energy routes according to power consumption requirements in subsequent steps is facilitated. As an example without limitation: the renewable power source is scheduled preferentially, the non-renewable power source is scheduled secondarily, and the aim of improving the environmental protection performance of energy scheduling is achieved.

From the above analysis, in the present invention, the power demand information of the micro-grid model can be generated according to at least one load device connected to the micro-grid model. The specific process of the electronic device executing step S103 is shown in fig. 3, and may include the following steps:

step S301, performing power characteristic analysis on the load device according to any load device accessed to the micro-grid model, so as to obtain a power demand type and a power parameter set of the load device.

Wherein the power demand type is used to characterize the power type demanded by the load device, such as, for example: electric car-alternating current; charging a livestock battery-alternating current; energy storage-alternating current data and the like.

Wherein the set of power parameters includes, but is not limited to, a demand current, a demand voltage, and a demand time period.

Optionally, the power parameter set is preferably determined in the following manner: the model can be searched through the type of the power equipment, and then the power parameter set is matched according to the type of the power equipment, alternatively, a power equipment type-power parameter set database can be constructed based on big data and updated periodically, so that the type of the power equipment can be input into the power equipment type-power parameter set database, and the power parameter set can be quickly searched. The accuracy of the demand information can be guaranteed through the power parameter set determined by the big data, and further the accuracy of power dispatching is guaranteed.

Step S302, generating power demand information corresponding to the load device according to the power demand type and the power parameter set of the load device.

Optionally, the required current, the required voltage and the required time period may be generated according to a power parameter set of the load device; adding the demand type of the load device into the primary power demand information; adding the required current, the required voltage and the required time period into the secondary power demand information; and storing the primary power demand information and the secondary power demand information in one-to-one correspondence to generate power demand information corresponding to the load equipment.

Specifically, the demand type of the load device is added to the primary power demand information, whereby the primary power demand information can be used as identification information of the power scheduling process to determine the type and direction of the power scheduling. And adding the power parameter sets of load equipment such as the required current, the required voltage, the required time length and the like into the secondary power demand information storage, and taking the power parameter sets as reference data for carrying out power scheduling subsequently.

Step S303, generating power demand information of the micro-grid model according to the power demand information corresponding to each load device.

After determining the power demand information corresponding to each load device accessing the micro-grid, the power demand information of the micro-grid model can be directly generated based on the power demand information corresponding to each load device.

According to the analysis, the capacity prediction of each renewable power source in the renewable power source topology information can be performed to obtain the capacity prediction information of the micro-grid model. The specific process of the electronic device executing step S104 is shown in fig. 4, and may include the following steps:

Step S401, traversing the renewable power source topology information to extract the power source type so as to determine the power source type of each renewable power source in the renewable power source topology information.

Exemplary are as follows: the power type of each renewable power source in the determined renewable power source topology information includes, but is not limited to: photovoltaic power, fan power, hydraulic power, etc.

Step S402, based on the power type of each renewable power source in the renewable power source topology information, obtaining a power generation scenario element corresponding to each renewable power source.

The power generation scene elements are environment element information corresponding to the power supply types one by one. Exemplary are as follows: when the power type of each renewable power source in the renewable power source topology information is a photovoltaic power source, the renewable power source is photovoltaic power generation and is related to environmental factors such as irradiation amount, duration time and the like, so that corresponding power generation scene elements include but are not limited to irradiation amount, duration time and the like; when the power type of each renewable power source in the renewable power source topology information is a fan power source, the wind power generation is related to environmental factors such as wind speed, wind power level, duration time and the like, so that corresponding power generation scene factors include, but are not limited to, wind speed, wind power level, duration time and the like.

It should be noted that different power types may correspond to different geographic locations in the regenerated power topology information, the same power type may also correspond to different geographic locations in the regenerated power topology information, and different power types may correspond to the same geographic location in the regenerated power topology information, but the power generation scenario elements are different.

Optionally, the power generation scene elements corresponding to each renewable power source can be obtained through various public, legal and compliance modes, for example, the ac/dc micro-grid energy scheduling device collects environmental element information corresponding to the power source types one by one in a preset time period based on the power source types of each renewable power source in the renewable power source topology information, wherein the optional preset time period is longer than or equal to the required time period, or the ac/dc micro-grid energy scheduling device obtains the power generation scene elements corresponding to each renewable power source collected by other devices.

Step S403, acquiring energy routing parameters of the energy routing device corresponding to each renewable power source.

The energy routing parameters comprise parameter information of energy routing equipment for energy scheduling and line parameter information between the energy routing equipment and a power supply access point for electric energy to be scheduled.

Alternatively, the energy routing parameters of the energy routing device corresponding to each renewable power source may be determined in various public, legal, and compliant ways.

Step S404, adopting a capacity prediction model, and performing capacity prediction on each renewable power source in the renewable power source topology information based on the power source type of each renewable power source, the power generation scene element corresponding to each renewable power source and the energy routing parameter of the energy routing equipment corresponding to each renewable power source so as to obtain capacity prediction information of the micro-grid model.

The capacity prediction model can be based on deep neural network training and is used for predicting based on power supply types, power generation scene elements and energy routing parameters and determining an intelligent model of electric energy output prediction information in a preset time period. The deep neural network is a neuron structure simulating the human brain, experience learning is carried out based on historical data, and then an artificial intelligent model with a large amount of complex data is fitted, because a large amount of historical data is fitted, the converged productivity prediction model can be trained based on a deep neural network and is used for making accurate prediction results of electric energy output based on power supply types, power generation scene elements and energy routing parameters and providing reference data for dynamic power distribution ratio.

As one possible implementation, the capacity prediction model includes a first process layer and a second process layer. The process for carrying out capacity prediction by adopting the capacity prediction model comprises the following steps: inputting the power type of each renewable power source and the power generation scene element corresponding to each renewable power source into a first processing layer of a capacity prediction model to obtain initial capacity prediction information; inputting the power type of each renewable power source and the energy routing parameters of the energy routing equipment corresponding to each renewable power source into a second processing layer of the capacity prediction model to obtain capacity utilization rate prediction information; and generating capacity prediction information of the micro-grid model based on the initial capacity prediction information and the capacity utilization prediction information.

It should be noted that, since the energy that can be produced by renewable energy sources may be difficult to be fully utilized by the energy routing schedule, it is necessary to evaluate the productivity utilization rate of the energy routing to improve the refinement of the energy routing power schedule.

The capacity prediction model comprises two main processing layers, a first processing layer and a second processing layer.

The first processing layer is used for carrying out initial productivity prediction. The initial capacity prediction information is a capacity prediction result obtained by inputting the power type of each renewable power source and the power generation scene element corresponding to each renewable power source into the first processing layer of the capacity prediction model for prediction. The first treatment layer is preferably formed by a plurality of groups: and performing supervised training learning on the power supply type, the power generation scene element and the capacity identification information, and inputting the power supply type and the power generation scene element which are acquired in real time after the first processing layer is converged so as to generate capacity prediction information representing the power generation before dispatching.

The second processing layer is used for evaluating the productivity utilization rate. The capacity utilization information is a result of inputting the power type of each renewable power source and the energy routing parameters of the energy routing device corresponding to each renewable power source into the second processing layer of the capacity prediction model for capacity utilization statistical analysis. The second processing layer preferably collects the power supply type, the energy routing parameter and the energy production utilization rate identification information of the current type, is based on a neural network, is supervised and trained, and inputs the power supply type and the energy routing parameter collected in real time when the second processing layer converges so as to generate the energy production utilization rate prediction information corresponding to the energy production prediction information before dispatching one by one.

Generating actually utilized capacity information according to the initial capacity prediction information and the capacity utilization information, preferably traversing all renewable power supply types through the capacity prediction information = capacity utilization information. By evaluating the productivity utilization rate, the refinement of the energy routing power dispatching control strategy is improved.

As a possible implementation manner, the first processing layer includes at least one neuron node, and the output result of the first processing layer is a weighted average of the output results of the node model corresponding to the at least one neuron node. A process for obtaining a first handle layer comprising the steps of: obtaining first historical data, wherein the first historical data comprises at least one group of power supply type, power generation scene elements and capacity identification information; for each neuron node, determining training data and verification data corresponding to the neuron node from the first historical data; and training a node model corresponding to the neuron node based on the training data and the verification data corresponding to the neuron node.

Specifically, the first processing layer is used for fitting the environmental time sequence elements and the power supply type information to perform productivity prediction, and the fitting process of the multi-dimensional environmental time sequence elements is complex, so that the training fitting process of data is performed by constructing a deep neural network frame, and the training is performed by adopting the neural network frame of the node nested network architecture preferably, wherein the process is as follows:

acquiring first historical data, wherein the first historical data is a data set for performing first processing layer training based on big data acquisition, and comprises a plurality of groups of data sets: the power supply type, the power generation scene elements and the capacity identification information, wherein the capacity identification information can be determined by collecting the capacity in the historical data, manual calculation of identification is not needed, and the data processing efficiency is improved.

Dividing the first historical data into k groups, extracting k times with the first historical data being put back, setting extracted data as first training data, setting the number not extracted as first verification data, and training a first node model through the first training data and the first verification data; repeating M times, constructing a second node model according to the second training data and the second verification data, and stopping until an Mth node model is constructed according to the Mth training data and the Mth verification data. Wherein M is a natural number which is greater than or equal to 1, and the value is determined according to the group number of the first historical data, and is specifically determined by looking at the permutation and combination of the extraction which is put back. The training data is used for training the node model, the verification data is used for verifying the generalization capability of the node model, and when the generalization capability meets the preset requirement, namely the output accuracy of the verification data reaches the preset accuracy, the node model converges. The preset accuracy can be preset.

And then the first node model, the second node model, … … and the Mth node model are nested on M parallel neuron nodes of an implicit network layer in the first processing layer, a network-in-network architecture is constructed, weight distribution is carried out at an output end according to the output error degree (node weight = node output error degree/sum of all node output error degrees), and the generated final output result is a weighted average of a plurality of node output results.

By constructing the network-in-network architecture based on the integration idea, fitting of multi-dimensional environment time sequence elements and power supply types can be achieved, an intelligent model capable of evaluating productivity prediction information is generated, and accuracy and stability of output results of the first processing layer are improved.

As a possible implementation manner, the second processing layer is a feedforward neural network, and the process of obtaining the second processing layer includes the following steps: obtaining second historical data, wherein the second historical data comprises a plurality of groups of power supply types, energy routing parameters and capacity utilization rate identification information; determining a training data set, an iteration data set and a verification data set from the second historical data; the second processing layer is trained based on the training dataset, the iteration dataset, and the validation dataset.

Specifically, the second history data refers to history data used to construct the second processing layer, and includes a plurality of groups: the second processing layer is preferably constructed based on a feedforward neural network, wherein the feedforward neural network is a simpler neural network architecture and is suitable for estimating the productivity utilization rate with low complexity. The construction process is preferably as follows:

Multiple groups were combined: the power supply type, the energy routing parameters and the capacity utilization identification information are divided into 7:1.5:1.5 proportion of three data, 7 proportion of historical data is used as a training data set, 1.5 proportion of historical data is used as an iteration data set, 1.5 proportion of historical data is used as a verification data set, supervised learning is carried out on the basis of a feedforward neural network through the training data set, a second processing layer is constructed, iteration training is carried out on the second processing layer through cooperation of the iteration data set and the feedforward neural network, output stability of the second processing layer is improved, and generalization capability of the second processing layer is verified through the verification data set. And the productivity utilization rate is evaluated through the power supply type and the energy routing parameters with lower complexity of feedforward neural network fitting, so that the convergence speed and the data processing efficiency are improved.

In order to achieve the above embodiment, the invention further provides an ac/dc micro-grid energy dispatching device.

Fig. 5 is a schematic structural diagram of an ac/dc micro-grid energy dispatching device according to an embodiment of the present invention.

As shown in fig. 5, the ac/dc micro grid energy scheduling apparatus includes: the first generation module 51, the second generation module 52, the third generation module 53, the prediction module 54, the first processing module 55, and the second processing module 56.

The first generation module 51 is configured to traverse the micro-grid model and generate grid topology information;

A second generating module 52, configured to generate energy routing topology information, renewable power source topology information, and lossy power source topology information according to the grid topology information;

A third generating module 53, configured to generate power demand information of the micro-grid model according to at least one load device connected to the micro-grid model;

The prediction module 54 is configured to predict the capacity of each renewable power source in the topology information of the renewable power source, so as to obtain capacity prediction information of the micro-grid model;

The first processing module 55 is configured to invoke each renewable power source in the renewable power source topology information to perform energy scheduling according to the capacity prediction information and the energy routing topology information when the capacity prediction information meets the power demand information;

the second processing module 56 is configured to generate demand deviation information according to the capacity prediction information and the power demand information, so as to invoke each power loss in the power loss topology information to perform energy replenishment based on the demand deviation information and the energy routing topology information, when the capacity prediction information does not satisfy the power demand information.

Further, in a possible implementation manner of the embodiment of the present invention, the third generating module 53 is configured to:

Aiming at any load device accessed to the micro-grid model, carrying out power characteristic analysis on the load device to obtain a power demand type and a power parameter set of the load device; wherein the power demand type is used to characterize the power type demanded by the load device, the power parameter set includes, but is not limited to, demand current, demand voltage, and demand duration;

Generating power demand information corresponding to the load equipment according to the power demand type and the power parameter set of the load equipment;

and generating the power demand information of the micro-grid model according to the power demand information corresponding to each load device.

Further, in one possible implementation of an embodiment of the present invention, the prediction module 54 is configured to:

Traversing the renewable power source topology information to extract the power source type so as to determine the power source type of each renewable power source in the renewable power source topology information;

Acquiring power generation scene elements corresponding to each renewable power source based on the power source type of each renewable power source in the renewable power source topology information; the power generation scene elements are environment element information corresponding to the power supply types one by one;

acquiring energy routing parameters of energy routing equipment corresponding to each renewable power source;

And carrying out capacity prediction on each renewable power source in the renewable power source topology information based on the power source type of each renewable power source, the power generation scene element corresponding to each renewable power source and the energy routing parameter of the energy routing equipment corresponding to each renewable power source by adopting a capacity prediction model so as to obtain capacity prediction information of the micro-grid model.

Further, in one possible implementation of the embodiment of the present invention, the capacity prediction model includes a first processing layer and a second processing layer; the prediction module 54 is further configured to:

inputting the power type of each renewable power source and the power generation scene element corresponding to each renewable power source into a first processing layer of a capacity prediction model to obtain initial capacity prediction information;

Inputting the power type of each renewable power source and the energy routing parameters of the energy routing equipment corresponding to each renewable power source into a second processing layer of the capacity prediction model to obtain capacity utilization rate prediction information;

and generating capacity prediction information of the micro-grid model based on the initial capacity prediction information and the capacity utilization prediction information.

Further, in one possible implementation manner of the embodiment of the present invention, the first processing layer includes at least one neuron node, and an output result of the first processing layer is a weighted average of output results of a node model corresponding to the at least one neuron node;

A process for obtaining a first handle layer comprising the steps of:

obtaining first historical data, wherein the first historical data comprises at least one group of power supply type, power generation scene elements and capacity identification information;

for each neuron node, determining training data and verification data corresponding to the neuron node from the first historical data;

And training a node model corresponding to the neuron node based on the training data and the verification data corresponding to the neuron node.

Further, in a possible implementation manner of the embodiment of the present invention, the second processing layer is a feedforward neural network, and the process of obtaining the second processing layer includes the following steps:

obtaining second historical data, wherein the second historical data comprises a plurality of groups of power supply types, energy routing parameters and capacity utilization rate identification information;

Determining a training data set, an iteration data set and a verification data set from the second historical data;

The second processing layer is trained based on the training dataset, the iteration dataset, and the validation dataset.

Further, in a possible implementation manner of the embodiment of the present invention, the second generating module 52 is configured to:

Extracting energy routing topology information for indicating an energy routing relationship and power supply topology information for indicating a power supply relationship from the power grid topology information;

traversing the power topology information to extract the power types so as to determine the power types of all power sources in the power topology information;

generating regenerated power topology information and lost power topology information based on the power topology information according to the power type of each power in the power topology information.

It should be noted that the foregoing explanation of the embodiment of the method for dispatching ac/dc micro-grid energy is also applicable to the apparatus for dispatching ac/dc micro-grid energy of this embodiment, and will not be repeated here.

According to the AC/DC micro-grid energy scheduling device, grid topology information is generated by traversing a micro-grid model, energy routing topology information, renewable power source topology information and loss power source topology information are generated according to the grid topology information, so that power demand information of the micro-grid model is generated according to at least one load device connected to the micro-grid model, capacity prediction is conducted on renewable power sources in the renewable power source topology information to obtain capacity prediction information of the micro-grid model, energy scheduling is conducted on renewable power sources in the renewable power source topology information according to the capacity prediction information and the energy routing topology information when the capacity prediction information meets the power demand information, demand deviation information is generated according to the capacity prediction information and the power demand information when the capacity prediction information does not meet the power demand information, and energy supplement is conducted on the loss power sources in the loss power source topology information based on the demand deviation information and the energy routing topology information. Therefore, the capacity of renewable energy sources in the micro-grid model can be analyzed and predicted in real time, when the capacity of the renewable energy sources can not meet the demand information, the loss power supply supplement is timely called, the power distribution proportion is dynamically adjusted according to the capacity prediction of the renewable energy sources, the flexibility, the intelligence and the applicability of energy scheduling are improved, and the technical problems that the mode flexibility and the intelligence of processing by relying on manual preset rules in the related technology are low and the applicability of energy scheduling strategies can not be guaranteed are solved.

In order to achieve the above embodiment, the present invention further proposes an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor, where the instructions are executable by the at least one processor, so that the at least one processor can execute the ac/dc micro grid energy scheduling method according to any one of the embodiments of the present invention.

It should be noted that the electronic device shown in fig. 6 is only an example, and should not impose any limitation on the functions and application scope of the embodiments of the present invention.

As shown in fig. 6, the electronic device includes:

A memory 601, a processor 602, and a computer program stored on the memory 601 and executable on the processor 602.

The processor 602 implements the ac/dc microgrid energy scheduling method provided in any of the above embodiments when executing the program.

Further, the electronic device further includes:

a communication interface 603 for communication between the memory 601 and the processor 602.

A memory 601 for storing a computer program executable on the processor 602.

The memory 601 may comprise a high-speed RAM memory or may further comprise a non-volatile memory (non-volatile memory), such as at least one disk memory.

The processor 602 is configured to implement the ac/dc micro grid energy scheduling method according to any one of the foregoing embodiments when executing the program.

If the memory 601, the processor 602, and the communication interface 603 are implemented independently, the communication interface 603, the memory 601, and the processor 602 may be connected to each other through a bus and perform communication with each other. The bus may be an industry standard architecture (Industry Standard Architecture, abbreviated ISA) bus, an external device interconnect (PERIPHERAL COMPONENT, abbreviated PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated EISA) bus, among others. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 6, but not only one bus or one type of bus.

Alternatively, in a specific implementation, if the memory 601, the processor 602, and the communication interface 603 are integrated on a chip, the memory 601, the processor 602, and the communication interface 603 may perform communication with each other through internal interfaces.

The processor 602 may be a central processing unit (Central Processing Unit, abbreviated as CPU), or an Application SPECIFIC INTEGRATED Circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the invention.

In order to implement the above embodiments, the present invention further proposes a computer readable storage medium storing computer instructions, where the computer instructions are configured to cause a computer to execute the ac/dc micro grid energy scheduling method according to any one of the above embodiments of the present invention.

In order to implement the above embodiments, the present invention further proposes a computer program product comprising a computer program which, when executed by a processor, implements the ac/dc micro grid energy scheduling method according to any of the above embodiments of the present invention.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present invention.

Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.

It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.

Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.

In addition, each functional unit in the embodiments of the present invention may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.

The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.

Claims

1. The AC/DC micro-grid energy scheduling method is characterized by comprising the following steps of:

traversing the micro-grid model to generate grid topology information;

2. The method of claim 1, wherein generating power demand information for the microgrid model from at least one load device accessing the microgrid model comprises:

Aiming at any load equipment connected to the micro-grid model, carrying out power characteristic analysis on the load equipment to obtain a power demand type and a power parameter set of the load equipment; wherein the power demand type is used to characterize a power type demanded by the load device, the set of power parameters including, but not limited to, a demand current, a demand voltage, and a demand duration;

3. The method according to claim 1, wherein the predicting the capacity of each renewable power source in the renewable power source topology information to obtain the capacity prediction information of the micro-grid model includes:

Performing power type extraction by traversing the renewable power source topology information to determine the power type of each renewable power source in the renewable power source topology information;

4. The method of claim 3, wherein the capacity prediction model comprises a first process layer and a second process layer; the capacity prediction model, based on the power type of each renewable power source, the power generation scene element corresponding to each renewable power source, and the energy routing parameter of the energy routing device corresponding to each renewable power source, performs capacity prediction on each renewable power source in the renewable power source topology information to obtain capacity prediction information of the micro-grid model, includes:

Inputting the power type of each renewable power source and the power generation scene element corresponding to each renewable power source into a first processing layer of the productivity prediction model to obtain initial productivity prediction information;

Inputting the power type of each renewable power source and the energy routing parameters of the energy routing equipment corresponding to each renewable power source into a second processing layer of the productivity prediction model to obtain productivity utilization prediction information;

5. The method of claim 4, wherein the first processing layer comprises at least one neuron node, and wherein the output result of the first processing layer is a weighted average of the output results of the node model corresponding to the at least one neuron node;

the process for obtaining the first treatment layer comprises the following steps:

6. The method of claim 4, wherein the second processing layer is a feed-forward neural network, and the process of obtaining the second processing layer comprises the steps of:

Determining a training dataset, an iterative dataset and a validation dataset from the second historical data;

the second processing layer is trained based on the training dataset, the iterative dataset, and the validation dataset.

7. The method of any of claims 1-6, wherein generating energy routing topology information, renewable power topology information, and lossy power topology information from the grid topology information comprises:

Traversing the power topology information to extract power types so as to determine the power types of all power supplies in the power topology information;

8. An ac/dc micro-grid energy dispatching device, comprising:

9. An electronic device, comprising:

At least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

10. A computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-8.

11. A computer program product comprising a computer program which, when executed by a processor, implements the method of any of claims 1-8.