CN119051084B

CN119051084B - Dynamic load balancing optimization method and system for micro-grid based on historical electricity consumption data

Info

Publication number: CN119051084B
Application number: CN202411165493.4A
Authority: CN
Inventors: 孙靖博; 赵旭东
Original assignee: Northeast Dianli University
Current assignee: Northeast Electric Power University
Priority date: 2024-08-23
Filing date: 2024-08-23
Publication date: 2025-09-19
Anticipated expiration: 2044-08-23
Also published as: CN119051084A

Abstract

The invention discloses a micro-grid dynamic load balancing optimization method and system based on historical electricity consumption data, and relates to the field of power system correlation, wherein the method comprises the following steps: and sensing the micro grid nodes according to the historical electricity utilization period to obtain historical electricity utilization data, constructing a historical electricity change graph based on the historical electricity utilization data, constructing a load prediction model according to the graph to generate electricity load prediction data, performing load balancing optimization to obtain a load distribution scheme, and performing intelligent power optimization scheduling on the micro grid nodes by the scheme. The technical problems of inaccurate prediction of the electric load of the micro-grid, unbalanced load distribution and imperfect coping with abnormal conditions and electric power dispatching strategies in the prior art are solved, and the technical effects of improving the overall efficiency, stability and reliability of the operation of the micro-grid are achieved.

Description

Dynamic load balancing optimization method and system for micro-grid based on historical electricity consumption data

Technical Field

The application relates to the field of power systems, in particular to a micro-grid dynamic load balancing optimization method and system based on historical power consumption data.

Background

In the micro-grid operation management scene, the stable supply problem in the power load peak period is particularly prominent, and the contradiction between the power resource allocation requirements is relatively more remarkable. How to efficiently distribute power resources better meets the power requirements of different nodes becomes a vital link for solving the stable operation of the micro-grid. Traditional micro-grid management is single and localized, only depends on fixed monitoring equipment or limited scheduling strategies, is insufficient in overall operation situation of the micro-grid, lacks deep analysis and utilization of historical electricity utilization data, is difficult to comprehensively and accurately evaluate power supply and demand conditions of all nodes, has unreasonable conditions in resource allocation, causes insufficient resources of some key nodes, and has idle resources of some nodes, and formulation of a power scheduling scheme is simple and fixed, so that the continuous changing actual operation situation of the micro-grid can not be well dealt with.

In the related technology of the present stage, the micro-grid power load has the technical problems of inaccurate prediction, unbalanced load distribution and imperfect power dispatching strategy for coping with abnormal conditions.

Disclosure of Invention

According to the method and the system for optimizing the dynamic load of the micro-grid based on the historical electricity consumption data, the historical electricity consumption data are acquired through sensing the micro-grid nodes according to the historical electricity consumption period, a historical electricity change diagram is constructed based on the historical electricity consumption data, a load prediction model is constructed according to the diagram to generate power load prediction data, accordingly, load balancing optimization is conducted to obtain a load distribution scheme, the scheme is executed to conduct intelligent power optimization scheduling on the micro-grid nodes, optimal configuration and efficient utilization of power resources are achieved, and the technical effects of improving the overall efficiency, stability and reliability of operation of the micro-grid are achieved.

The application provides a micro-grid dynamic load balancing optimization method and system based on historical electricity consumption data, comprising the following steps:

The method comprises the steps of carrying out data sensing on a plurality of nodes of a micro-grid according to a historical electricity utilization period to obtain a plurality of historical electricity utilization data, constructing a historical electricity change diagram based on the plurality of historical electricity utilization data, constructing a load prediction model according to the historical electricity change diagram to predict the micro-grid to generate a plurality of electric load prediction data, carrying out load balancing optimization based on the plurality of electric load prediction data to generate a load distribution scheme, and carrying out intelligent power optimization scheduling on the plurality of nodes of the micro-grid by executing the load distribution scheme.

The application also provides a micro-grid dynamic load balancing and optimizing system based on historical electricity consumption data, which comprises the following steps:

The system comprises a historical electricity consumption data acquisition module, a historical electricity consumption pattern generation module, a micro-grid load prediction module, a load distribution scheme generation module and an intelligent power dispatching module, wherein the historical electricity consumption data acquisition module is used for carrying out data sensing on a plurality of nodes of a micro-grid according to a historical electricity consumption period to obtain a plurality of historical electricity consumption data, the historical electricity consumption pattern generation module is used for constructing a historical electricity consumption pattern based on the plurality of historical electricity consumption data, the micro-grid load prediction module is used for constructing a load prediction model according to the historical electricity consumption pattern to predict the micro-grid to generate a plurality of power load prediction data, the load distribution scheme generation module is used for carrying out load balance optimization based on the plurality of power load prediction data to generate a load distribution scheme, and the intelligent power dispatching module is used for executing intelligent power optimization dispatching on the plurality of nodes of the micro-grid by the load distribution scheme.

According to the micro-grid dynamic load balancing optimization method and system based on the historical electricity consumption data, firstly, data sensing is carried out on a plurality of nodes of the micro-grid according to the historical electricity consumption period to obtain a plurality of historical electricity consumption data, a historical electricity change diagram is built based on the historical electricity consumption data, a load prediction model is built according to the historical electricity change diagram to predict the micro-grid, a plurality of electric load prediction data are generated, load balancing optimization is carried out based on the plurality of electric load prediction data, a load distribution scheme is generated, and the load distribution scheme is executed to carry out intelligent power optimization scheduling on the plurality of nodes of the micro-grid, so that the technical effects of improving the overall efficiency, stability and reliability of operation of the micro-grid are achieved.

Drawings

In order to more clearly illustrate the technical solution of the embodiments of the present application, the following will briefly describe the drawings of the embodiments of the present application, in which flowcharts are used to illustrate operations performed by a system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.

Fig. 1 is a schematic flow chart of a dynamic load balancing optimization method for a micro-grid based on historical electricity consumption data according to an embodiment of the application;

fig. 2 is a schematic structural diagram of a dynamic load balancing and optimizing system for a micro-grid based on historical electricity consumption data according to an embodiment of the present application.

Reference numerals illustrate the historical electricity consumption data acquisition module 10, the historical electricity change map generation module 20, the micro-grid load prediction module 30, the load distribution scheme generation module 40 and the electricity intelligent scheduling module 50.

Detailed Description

The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail with reference to the accompanying drawings, and the described embodiments should not be construed as limiting the present application, and all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present application.

In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, the term "first\second" being referred to merely as distinguishing between similar objects and not representing a particular ordering for the objects. The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules that may not be expressly listed or inherent to such process, method, article, or apparatus, and unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used herein is for the purpose of describing embodiments of the application only.

The embodiment of the application provides a micro-grid dynamic load balancing optimization method based on historical electricity consumption data, which comprises the following steps of:

And step S100, data sensing is carried out on a plurality of nodes of the micro-grid according to the historical electricity utilization period, and a plurality of historical electricity utilization data are obtained.

Specifically, the historical electricity consumption period is accurately determined based on historical electricity consumption ladder information, the mode and rule of electricity consumption in different time periods are reflected by the historical electricity consumption ladder information, key period stages such as electricity consumption peak period, valley period and stationary period can be clarified through deep analysis, a plurality of nodes are set according to historical electricity supply and demand information of a micro-grid, clear knowledge on the whole framework and an electricity transmission path of the micro-grid is needed, the set nodes can comprehensively and effectively reflect the flowing and using conditions of electricity in the micro-grid, the electricity consumption collection work is conducted on the micro-grid according to the determined historical electricity consumption period by combining the set supply and demand relation of the plurality of nodes, the electricity consumption and electricity load conditions of the plurality of nodes in different time periods are accurately measured and recorded in the collection process, the obtained data comprises a plurality of historical electricity consumption data and a plurality of historical electricity load data, the electricity consumption data directly reflect the total amount of electricity consumed by each node in a specific time period, the electricity load data reflect the electricity load born by each node in the same time period, the electricity consumption data is integrated into a plurality of accurate data, the accurate data are provided for the history data and the accurate data are added to the historical data, and the accurate data are fully analyzed, and the data are provided for the accurate data are fully analyzing and the data.

In one possible implementation, the step S100 further includes a step S110 of sensing data of a plurality of nodes of the micro grid according to the historical electricity consumption period to obtain a plurality of historical electricity consumption data, and determining the historical electricity consumption period based on the historical electricity consumption ladder information. Specifically, the historical electricity consumption period is determined based on historical electricity consumption ladder information, the historical electricity consumption ladder information comprises the electricity price division and corresponding electricity consumption distribution conditions in different time periods, through deep analysis of the information, peak time, valley time and relatively stable time periods of electricity consumption are found, for example, in certain areas, working hours in daytime can be electricity consumption peaks, working hours at night can be electricity consumption valleys, and electricity consumption modes of weekends and working days can be different, and representative time periods can be clearly identified through identifying the rules and modes, so that the historical electricity consumption period is determined.

Step S120, setting a plurality of nodes according to the historical power supply and demand information of the micro grid. Specifically, the nodes are set according to historical power supply and demand information of the micro-grid, so that comprehensive understanding of the architecture of the micro-grid, power transmission lines and power utilization characteristics of each area is required, for example, in industrial centralized areas, commercial areas and residential areas, the power demand and supply characteristics are different, and the nodes are set at key positions, such as power input points, main power utilization equipment access points, key branch points of power transmission and the like, according to different supply and demand characteristics, so that comprehensive and accurate monitoring and analysis of the flow and the use condition of power can be ensured.

And step S130, carrying out power consumption collection on the micro-grid according to the historical power consumption period and combining the supply and demand relation of the plurality of nodes to obtain a plurality of historical power consumption data and a plurality of historical power load data. Specifically, according to the determined historical electricity utilization period, electricity utilization is carried out on the micro-grid by combining with supply and demand relations of a plurality of nodes, in each historical electricity utilization period, for a plurality of set nodes, professional power monitoring equipment and sensors are utilized to measure and record relevant data of electric power in real time, because the supply and demand relations of different nodes in different periods are different, some nodes can bear larger electric loads in peak periods, and some nodes have smaller electric quantities in valley periods, and a plurality of historical electricity utilization data, namely the total amount of electric energy actually consumed by each node in different periods and a plurality of historical electric load data, namely the instant electric load magnitude born by each node in corresponding time periods, are obtained through accurate measurement and acquisition.

And step S140, adding the plurality of historical electricity consumption data and the plurality of historical electrical load data to the plurality of historical electricity consumption data. Specifically, the collected historical electricity consumption data and the historical electricity load data are added into the historical electricity consumption data to construct a comprehensive and systematic historical electricity consumption database, and the newly collected data and the existing historical data are combined to more completely present the electricity consumption history of the micro-grid, so that a rich and reliable data basis is provided for subsequent analysis, modeling and optimization.

Step S200, constructing a historical power variation graph based on the plurality of historical power consumption data.

Specifically, the acquired historical electricity utilization data are sorted and classified, the data comprise information such as electricity utilization amount and electric load of different time periods and different nodes, in the sorting process, accuracy and integrity of the data need to be ensured, existing error or missing values are processed, a first coordinate axis and a second coordinate axis are determined based on the historical electricity utilization amount data, and the first coordinate axis represents time, such as specific year, month, date or hour; the fourth coordinate axis is used for representing the value of the electric load, such as kilowatt or megawatt, after the coordinate axes are determined, a historical electric consumption coordinate system is constructed based on the first coordinate axis and the second coordinate axis, in the coordinate system, the electric consumption data corresponding to different time points are marked and drawn, so as to form a curve of the change of the electric consumption along with time, the change trend of the historical electric consumption is shown, the historical electric load coordinate system is constructed based on the third coordinate axis and the fourth coordinate axis, the electric load data of different time points are marked in the coordinate system, the curve of the change of the electric load along with time is formed, the change trend of the historical electric load is clearly shown, the change trend of the historical electric load and the change trend of the historical electric load are comprehensively considered, a complete historical electric power change graph is constructed, the change graph can intuitively reflect the dynamic change condition of the electric consumption and the load of the electric network in a period of time, providing an important visual basis for subsequent analysis and prediction.

In one possible implementation, the step S200 further includes a step S210 of constructing a historical power variation graph based on the plurality of historical power consumption data, and determining a first coordinate axis and a second coordinate axis based on the plurality of historical power consumption data. Specifically, when determining the first coordinate axis and the second coordinate axis based on the plurality of historical electricity consumption data, the characteristics of the historical electricity consumption data are analyzed, the first coordinate axis selects a time dimension, for example, the time dimension is in units of days, weeks, months or years, so that the change of electricity consumption along with time is clearly displayed, the second coordinate axis is used for representing the value of electricity consumption, the units of the second coordinate axis can be kilowatt-hours, megawatt-hours and the like, and a foundation can be laid for the subsequent construction of visual electricity consumption change display through selection.

And step S220, determining a third coordinate axis and a fourth coordinate axis based on the historical electrical load data. Specifically, for determining a third coordinate axis and a fourth coordinate axis based on a plurality of historical electric load data, from the aspect of data characteristics, the third coordinate axis is time and is consistent with the time scale of the first coordinate axis, so as to ensure that the electric consumption and the change of the electric load are compared under the same time frame, and the fourth coordinate axis is used for representing the numerical value of the electric load, wherein the unit of the fourth coordinate axis can be kilowatt, megawatt and the like, and the magnitude of the electric load can be accurately reflected.

And step S230, constructing a historical power consumption coordinate system based on the first coordinate axis and the second coordinate axis. Specifically, a historical electricity consumption coordinate system is built based on a determined first coordinate axis and a determined second coordinate axis, scale marking is carried out on the first coordinate axis according to a selected time interval, and reasonable scale division is carried out on the second coordinate axis according to a numerical range of electricity consumption, so that a clear frame is provided for drawing electricity consumption data.

And step S240, constructing a historical electrical load coordinate system based on the third coordinate axis and the fourth coordinate axis. Specifically, a historical electric load coordinate system is constructed based on a third coordinate axis and a fourth coordinate axis, similar to the historical electric consumption coordinate system, time scales are marked on the third coordinate axis, and scales are divided on the fourth coordinate axis according to an electric load numerical range, so that a space special for displaying electric load data is formed.

Step S250, synchronizing the plurality of historical power consumption data to the historical power consumption coordinate system to obtain a historical power consumption variation trend. Specifically, a plurality of historical electricity consumption data are synchronized into a historical electricity consumption coordinate system, the electricity consumption value corresponding to each time point is accurately marked in the coordinate system according to time sequence, and the points are connected in a connecting mode, so that a change curve of the historical electricity consumption along with time is intuitively presented, and change trends such as increase and decrease, fluctuation and the like of the historical electricity consumption are clearly presented.

And step S260, synchronizing the plurality of historical electric load data to the historical electric load coordinate system to obtain a historical electric load change trend. Specifically, a plurality of historical electric load data are synchronized to a historical electric load coordinate system, electric load values are marked at corresponding time points, and the historical electric load data are connected to form a curve, so that the change trend of the historical electric load is obtained, and the change trend comprises the characteristics of peaks, valleys, stable stages and the like of the electric load.

And step S270, constructing the historical power change diagram according to the historical power consumption change trend and the historical power load change trend. Specifically, a historical power change graph is constructed according to the obtained historical power consumption change trend and the historical power load change trend, in the graph, the change curves of the historical power consumption and the power load are drawn in the same graph, or are compared and displayed in a split graph mode, the two trends are comprehensively analyzed, the power use condition and the load change rule of the micro-grid in the past can be more comprehensively known, and a powerful reference basis is provided for subsequent power management and optimization.

And step S300, a load prediction model is constructed according to the historical power change diagram to predict the micro-grid, and a plurality of power load prediction data are generated.

Specifically, the obtained historical power change graph is subjected to deep analysis and feature extraction, including observation of periodic change rules of historical power consumption and power load, seasonal fluctuation, difference between working days and non-working days, influence of sudden events or special conditions on power change and the like, a proper load prediction model is selected according to the extracted features and rules, common models such as a time sequence model, a regression model, a neural network model and the like are taken as examples, a complex nonlinear relation is processed by taking the neural network model as an example, the method is suitable for the condition that the power load is influenced by various factors and the change rule is complex, after the model is determined, a plurality of power consumption time scales are set according to the historical power consumption period, the time scales can be hours, days, weeks, months and even seasons and the like so as to capture the change mode of the power load from different time dimensions, extracting a plurality of power change data based on a set power utilization time scale in combination with a historical power change map, wherein the data is used as an input of a model and is used for training and optimizing the model, the extracted plurality of power change data is divided into a training data set, a supervision data set and a test data set, the training data set is used for learning and parameter adjustment of the model, the supervision data set is used for monitoring and guiding the model in a training process, the test data set is used for evaluating the performance and accuracy of the model, based on a selected BP neural network model, the training data set and the supervision data set are combined for supervised iterative training, the model continuously adjusts internal weights and biases in the training process to minimize errors between predicted values and actual values until the test data set passes the test of training results, the prediction error of the model on the test data reaches an acceptable range, or the performance index (such as mean square error, average absolute error and the like) of the model meets the preset requirement, the model is trained, the current relevant data of the micro-grid is input into the model through the test to predict the power load, the model can generate power load prediction data of a plurality of future time periods according to the input data and the learned rule, the prediction data covers different time points and nodes, and important decision basis is provided for operation planning, resource allocation and load balance optimization of the micro-grid.

In one possible implementation manner, a load prediction model is constructed according to the historical power change diagram to predict the micro-grid, so as to generate a plurality of power load prediction data, and step S300 further includes step S310, where a plurality of power consumption time scales are set according to the historical power consumption period. Specifically, a plurality of electricity time scales are set according to the historical electricity utilization period, and the periodicity and regularity of the historical electricity utilization data need to be deeply analyzed, for example, if the historical electricity utilization data show that there is a significant difference between the weekdays and the weekends of each week, the time scales in days are set to distinguish the weekdays from the weekends, or if there are seasonal electricity utilization peaks and valleys, the time scales in months or quarters are set, and by such careful division, the characteristics of the power change can be captured more accurately.

Step S320, extracting a plurality of power variation data based on the plurality of power utilization time scales in combination with the historical power variation graph. Specifically, based on a plurality of set power utilization time scales, a plurality of power change data are extracted by combining a historical power change graph, corresponding data points or data segments are screened and extracted from the historical power change graph according to different time scales, and the data reflect the change conditions of power utilization amount and power load under a specific time scale, including various trends of ascending, descending, stabilizing and the like.

Step S330, the plurality of power variation data is divided into a training data set, a supervision data set, and a test data set. Specifically, the extracted multiple power change data are divided into a training data set, a supervision data set and a test data set, wherein the training data set is generally divided randomly or according to a certain proportion, the training data set is generally large in scale and is used for a main learning process of a model, the model learns the power change mode and rule, the supervision data set plays a role in monitoring and adjusting in the training process, the model is helped to better optimize parameters, and the test data set is independent of the training and supervision processes and is used for finally evaluating the performance and accuracy of the model.

Step S340, based on BP neural network, combining the training data set and the supervision data set to perform supervised iterative training until the test result of the test data set passes, and outputting the load prediction model. Specifically, based on a BP neural network, the BP neural network is a powerful machine learning model, can process complex nonlinear relations, during training, a training data set is input into the network, the network calculates output according to input data and preset initial parameters and compares the output with an actual target value, the error is calculated, the weight and bias in the network are adjusted according to the error through a back propagation algorithm, so that the error is reduced, in the training process, the supervision data set is combined at the same time, additional information and constraint are provided for the supervision data set, the model is helped to learn and adjust more accurately, the situation of overfitting or underfitting is avoided, the training process is repeated continuously, repeated for a plurality of iterations, the model is gradually optimized and converged, a test data set is used for testing the training result periodically, if the test result does not meet the preset precision requirement, training and adjustment are continued until the test data set passes the test of the training result, namely, the prediction error of the model on the test data set reaches an acceptable range or meets a specific performance index, the final load prediction model is output at the moment, the load prediction model can provide important reference management basis for future power grid according to the input new data, and predicted power load conditions.

And step S400, carrying out load balancing optimization based on the plurality of power load prediction data to generate a load distribution scheme.

Specifically, the plurality of acquired power load prediction data are comprehensively collated and analyzed. The method comprises the steps of recording and classifying predicted load values of different nodes in detail in different time periods, collecting a real-time power operation information set of a micro-grid, acquiring key elements such as power operation efficiency information, power transmission loss information, power demand fluctuation information and the like from the real-time power operation information set, wherein the information can reflect the current operation state and potential problems of the micro-grid, and constructing a preset optimization target based on the acquired information, wherein the preset optimization target comprises a preset power operation efficiency target, a preset power transmission loss target and a preset power demand fluctuation target, and for example, the preset power operation efficiency target can be used for improving the overall operation efficiency to a certain percentage; the preset power demand fluctuation target may be to control demand fluctuation within a certain range to ensure stability of power supply, generate first load distribution data in combination with a plurality of power load prediction data according to a preset power operation efficiency target, preferentially ensure that the operation efficiency of power can reach a preset target when considering how to distribute the load, calculate a load distribution scheme capable of realizing the highest operation efficiency by analyzing factors such as the load prediction data and the equipment performance of each node, generate second load distribution data in combination with a plurality of power load prediction data according to the preset power transmission loss target, focus on the loss condition of power in the transmission process, generate third load distribution data in combination with a plurality of power load prediction data according to the preset power demand fluctuation target to aim at balancing the power demand in different time periods by optimizing the modes such as line selection, load distribution adjustment and the like, the method has the advantages that the occurrence of large fluctuation of demands is avoided, the stable operation of the power system is ensured, the first load distribution data, the second load distribution data and the third load distribution data are comprehensively considered, the integration and the balance are carried out, the distribution scheme under each target is analyzed, an optimal balance point is found, a final load distribution scheme is constructed, the requirements of operation efficiency can be met, the transmission loss can be reduced, the fluctuation of the electric power demands can be stabilized, and the load balance optimization of the micro-grid is realized.

In one possible implementation manner, load balancing optimization is performed based on the plurality of power load prediction data, a load distribution scheme is generated, and step S400 further includes step S410 of collecting a real-time power operation information set of the micro-grid, and obtaining power operation efficiency information, power transmission loss information and power demand fluctuation information. Specifically, by deploying sensors and monitoring devices at key positions of the micro-grid, power operation information of the micro-grid is collected in real time, the devices continuously collect data such as current, voltage and power and gather the data into a real-time power operation information set, and the information is subjected to deep analysis and calculation to obtain power operation efficiency information such as actual operation efficiency, energy conversion efficiency and the like of the devices, power transmission loss information including energy loss caused by line resistance, transformer loss and the like, and power demand fluctuation information, namely the change amplitude and frequency of power demand in different time periods.

Step S420, constructing a preset optimization target based on the power operation efficiency information, the power transmission loss information and the power demand fluctuation information, where the preset optimization target includes a preset power operation efficiency target, a preset power transmission loss target and a preset power demand fluctuation target. Specifically, a preset optimization target is constructed based on the acquired power operation efficiency information, power transmission loss information and power demand fluctuation information, an expected operation efficiency value is set as a preset power operation efficiency target according to actual conditions and expected performances of the micro-grid for power operation efficiency, an acceptable maximum loss value is determined for power transmission loss to form a preset power transmission loss target, and an allowable fluctuation range is set as a preset power demand fluctuation target for power demand fluctuation.

Step S430, generating first load distribution data according to the preset power operation efficiency target in combination with the plurality of power load prediction data. Specifically, first load distribution data are generated by combining a plurality of power load prediction data according to a preset power operation efficiency target, performance characteristics of each device and nodes, current load prediction and the preset efficiency target are comprehensively considered, and an optimal load distribution scheme of each node and each device on the premise that the preset power operation efficiency target is met is calculated through an optimization algorithm and a model, so that the first load distribution data are obtained.

Step S440, generating second load distribution data according to the preset power transmission loss target and combining the plurality of power load prediction data. Specifically, the second load distribution data is generated by combining a plurality of power load prediction data according to a preset power transmission loss target, the loss condition in the power transmission process is focused, the transmission loss is minimized by adjusting line loads, optimizing the layout of power sources and loads and the like, and the corresponding load distribution scheme, namely the second load distribution data, is calculated by combining the load prediction data.

Step S450, generating third load distribution data according to the preset power demand fluctuation target in combination with the plurality of power load prediction data. Specifically, third load distribution data are generated by combining a plurality of power load prediction data according to a preset power demand fluctuation target, power demand predictions in different time periods and supply capacity and response characteristics of a micro-grid are analyzed, and the demand fluctuation is controlled within a preset range while meeting the demand by reasonably allocating the load, so that the third load distribution data are obtained.

Step S460, constructing the load distribution scheme based on the first load distribution data, the second load distribution data, and the third load distribution data. Specifically, the first load distribution data, the second load distribution data and the third load distribution data are comprehensively considered, the three groups of data are compared, integrated and weighted average, a multi-objective optimization algorithm is adopted or different priorities are given according to actual conditions, so that an optimal solution which can simultaneously consider the power operation efficiency, the transmission loss and the demand fluctuation is found, and a final load distribution scheme is constructed.

And S500, executing the load distribution scheme to perform intelligent power optimization scheduling on a plurality of nodes of the micro-grid.

Specifically, after the load distribution scheme is determined, the control system of the micro-grid starts to start an execution flow, the system acquires specific power distribution instructions for each node in the load distribution scheme, performs real-time power distribution and scheduling operation on a plurality of nodes of the micro-grid according to the instructions, closely monitors electric load data of each node, judges whether the plurality of electric load data of the plurality of nodes are greater than or equal to a preset threshold value, if the plurality of electric load data are smaller than the preset threshold value, indicates that the electric load of the nodes is in a relatively safe and normal range, performs real-time operation monitoring on the plurality of nodes of the micro-grid, continuously collects operation data of the nodes, including voltage, current, power factor and the like, generates operation feedback information based on the real-time operation monitoring data, wherein the feedback information comprises real-time operation states of the nodes, change trend of the electric parameters and the like, load balancing evaluation is carried out on the micro-grid based on operation feedback information, the power distribution condition, the load change condition, the deviation from a preset target and other factors of each node are comprehensively considered in the evaluation process, so that a load balancing score is generated, an emergency response scheduling strategy is generated according to the load balancing score, for example, if the score is lower, the power distribution of some nodes may need to be regulated, the supply is increased or reduced, so that more optimized load balancing is realized, if a plurality of electric load data are greater than or equal to a preset threshold value, the condition that the nodes may face overload or abnormal conditions is explained, the abnormal positioning is carried out on a plurality of nodes of the micro-grid, the abnormal nodes are accurately determined through data analysis and comparison, the weight distribution is carried out on a plurality of abnormal nodes, a plurality of weight factors are generated according to the importance of the nodes, the load degree and other factors, the weight factors are arranged in a descending order to generate a weight sequence, deviation correction is carried out according to the weight sequence based on a plurality of abnormal nodes, important nodes with larger deviation are preferentially processed according to the height of the weight, a plurality of deviation correction results are generated by adjusting modes such as power supply and switching lines, the abnormal nodes are corrected according to the deviation correction results, the power load of the nodes is ensured to be restored to be in a normal range, intelligent power optimization scheduling is carried out on the micro-grid based on the corrected nodes, and stable and efficient operation of the micro-grid is ensured.

In a possible implementation manner, the executing the load distribution scheme performs power intelligent optimization scheduling on a plurality of nodes of the micro-grid, and step S500 further includes step S510, executing the load distribution scheme, and determining whether a plurality of electrical load data of the plurality of nodes is greater than or equal to a preset threshold. Specifically, the system starts to execute a preset load distribution scheme, and in the executing process, electric load data of a plurality of nodes of the micro-grid are monitored and collected in real time at the same time, and the collected electric load data of the plurality of nodes are compared with a preset threshold value to judge whether the electric load data is larger than or equal to the preset threshold value.

And step S520, if the plurality of electrical load data is smaller than the preset threshold, performing real-time operation monitoring on the plurality of nodes of the micro-grid, and generating operation feedback information. Specifically, if the plurality of electrical load data is smaller than the preset threshold value, which means that the electrical load of the current node is in a relatively safe and acceptable range, at this time, the system starts a real-time operation monitoring mechanism for the plurality of nodes of the micro-grid, continuously collects a series of key operation parameters and data including voltage, current, power and the like through sensors and monitoring devices installed on the respective nodes, and generates operation feedback information capable of reflecting the real-time operation conditions of the nodes after the data are summarized and collated.

And step S530, carrying out load balance evaluation on the micro-grid based on the operation feedback information, and generating a load balance score. Specifically, load balancing evaluation is performed on the micro-grid based on the acquired operation feedback information, multiple aspects such as power distribution conditions of all nodes, variation trend of loads, deviation degree from ideal balancing state and the like are comprehensively considered in the evaluation process, and a quantized evaluation result is given for the load balancing condition of the micro-grid through calculation and analysis, namely load balancing scores are generated.

And S540, generating an emergency response scheduling strategy according to the load balancing scores, and performing intelligent power optimization scheduling on the nodes. The method comprises the steps of determining an emergency response scheduling strategy according to a generated load balance score, if the score is high, indicating that the load balance state of the micro-grid is good, and possibly not needing to be greatly adjusted, if the score is low, indicating that an unbalanced condition exists, generating a corresponding scheduling strategy, wherein the strategy comprises the steps of reallocating power resources, adjusting the power supply priority of certain nodes or starting a standby power supply, and the like, and performing intelligent power optimal scheduling on a plurality of nodes according to the strategy so as to continuously optimize the running state of the micro-grid and ensure stable and efficient power supply.

In a possible implementation manner, an emergency response scheduling policy is generated according to the load balancing score, power intelligent optimization scheduling is performed on the plurality of nodes, step S540 further includes step S541, if the plurality of electrical load data is greater than or equal to the preset threshold, performing abnormal positioning on the plurality of nodes of the micro-grid, and determining a plurality of abnormal nodes. Specifically, when the plurality of electrical load data is greater than or equal to a preset threshold value, which indicates that abnormal conditions may occur in the operation of the micro-grid, the system may perform abnormal positioning on a plurality of nodes of the micro-grid, and accurately determine the plurality of abnormal nodes by analyzing the electrical load data of each node in detail and comparing the electrical load data with the differences between the electrical load data and the normal range or the expected value.

Step S542, performing weight distribution on the plurality of abnormal nodes to generate a plurality of weight factors, and performing descending order arrangement on the plurality of weight factors to generate a weight sequence. Specifically, after the abnormal nodes are determined, weight distribution is carried out on the abnormal nodes, the weight distribution is carried out according to factors which possibly include importance of the nodes, carried key load degree, influence on stability of the whole micro-grid and the like, a plurality of weight factors are generated according to the generated weight factors, the relative importance degree of each abnormal node is reflected, the generated weight factors are arranged in a descending order to form a weight sequence, and the weight sequence clearly shows importance priority of the abnormal nodes.

In step S543, offset correction is performed according to the weight sequence based on the plurality of abnormal nodes, and a plurality of offset correction results are generated. Specifically, based on a plurality of abnormal nodes, performing deviation correction according to the sequence of the weight sequence, and for the abnormal nodes with higher weights, performing treatment and correction preferentially, wherein the correction mode comprises the steps of adjusting distribution of power supply, changing line connection, starting standby power supply or limiting part of non-critical load, and the like, so that the electric load of the abnormal nodes returns to a normal range or is close to a preset ideal state, and generating a plurality of deviation correction results through correction operation.

And step S544, correcting the plurality of abnormal nodes according to the plurality of deviation correction results, and performing intelligent power optimization scheduling on the micro-grid based on the plurality of correction nodes. Specifically, the plurality of abnormal nodes are corrected according to the plurality of deviation correction results, the electric load of the abnormal nodes is confirmed to be effectively regulated and improved, so that the abnormal nodes meet the normal operation requirement of the micro-grid, the micro-grid is subjected to integral intelligent power optimization scheduling based on the corrected nodes, the power distribution and the operation state of the micro-grid are re-evaluated, the whole micro-grid can continue to stably and efficiently operate after being subjected to abnormal condition processing, the power requirement of a user is met, and the reliability and the economy of the micro-grid are improved.

According to the embodiment of the application, the historical electricity consumption data is acquired by sensing the micro-grid nodes according to the historical electricity consumption period, the historical electricity change graph is constructed based on the historical electricity consumption data, the load prediction model is constructed according to the graph to generate the power load prediction data, the load distribution scheme is obtained by carrying out load balancing optimization according to the power load prediction data, the intelligent power optimization scheduling is carried out on the micro-grid nodes by executing the scheme, the optimal configuration and the efficient utilization of power resources are realized, and the technical effects of improving the overall efficiency, the stability and the reliability of the operation of the micro-grid are achieved.

Hereinabove, a dynamic load balancing optimization method for a micro-grid based on historical electricity consumption data according to an embodiment of the present invention is described in detail with reference to fig. 1. Next, a micro grid dynamic load balancing optimization system based on historical electricity usage data according to an embodiment of the present invention will be described with reference to fig. 2.

The micro-grid dynamic load balancing and optimizing system based on historical electricity consumption data is used for solving the technical problems of inaccurate power load prediction, unbalanced load distribution and imperfect power dispatching strategy of the micro-grid in the prior art, and achieves the technical effects of improving the overall efficiency, stability and reliability of micro-grid operation. The micro-grid dynamic load balancing optimization system based on the historical electricity consumption data comprises a historical electricity consumption data acquisition module 10, a historical electricity change diagram generation module 20, a micro-grid load prediction module 30, a load distribution scheme generation module 40 and an electricity intelligent scheduling module 50.

The historical electricity consumption data acquisition module 10 is used for carrying out data sensing on a plurality of nodes of the micro-grid according to the historical electricity consumption period to obtain a plurality of historical electricity consumption data;

The historical power change map generation module 20 is configured to construct a historical power change map based on the plurality of historical power usage data;

The micro-grid load prediction module 30 is configured to construct a load prediction model according to the historical power change map to predict the micro-grid, so as to generate a plurality of power load prediction data;

The load distribution scheme generating module 40 is configured to perform load balancing optimization based on the plurality of power load prediction data, and generate a load distribution scheme;

the intelligent power dispatching module 50 is used for executing the load distribution scheme to conduct intelligent power optimization dispatching on the nodes of the micro-grid.

Next, the specific configuration of the historical electricity usage data acquisition module 10 will be described in detail. As described above, the historical electricity consumption data obtaining module 10 may further include a period determining unit configured to determine the historical electricity consumption period based on the historical electricity consumption ladder information, a node setting unit configured to set the plurality of nodes according to the historical electricity supply and demand information of the micro grid, an electricity collection unit configured to collect electricity consumption of the micro grid according to the historical electricity consumption period in combination with a supply and demand relationship of the plurality of nodes to obtain a plurality of historical electricity consumption data and a plurality of historical electricity load data, and a data adding unit configured to add the plurality of historical electricity consumption data and the plurality of historical electricity load data to the plurality of historical electricity consumption data.

Next, the specific configuration of the history power variation map generation module 20 will be described in detail. As described above, the historical power change map generation module 20 may further include a first coordinate axis and a second coordinate axis determining unit configured to determine a first coordinate axis and a second coordinate axis based on the plurality of historical power consumption data, a third coordinate axis and a fourth coordinate axis determining unit configured to determine a third coordinate axis and a fourth coordinate axis based on the plurality of historical power load data, a historical power consumption coordinate system constructing unit configured to construct a historical power consumption coordinate system based on the first coordinate axis and the second coordinate axis, a historical power load coordinate system constructing unit configured to construct a historical power load coordinate system based on the third coordinate axis and the fourth coordinate axis, a historical power consumption change trend acquiring unit configured to synchronize the plurality of historical power consumption data to the historical power consumption coordinate system to obtain a historical power consumption change trend, a historical power load change trend acquiring unit configured to synchronize the plurality of historical power load data to the historical power load coordinate system to obtain a historical power load change trend, and a historical power change map constructing unit configured to construct the power load change map based on the historical power consumption change trend.

Next, the specific configuration of the micro grid load prediction module 30 will be described in detail. As described above, the micro-grid load prediction module 30 may further include a time scale setting unit configured to set a plurality of electricity time scales according to the historical electricity period, an electricity change data extraction unit configured to extract a plurality of electricity change data based on the plurality of electricity time scales in combination with the historical electricity change map, a data division unit configured to divide the plurality of electricity change data into a training data set, a supervision data set, and a test data set, and a load prediction model output unit configured to perform supervised iterative training in combination with the training data set and the supervision data set based on a BP neural network until the test data set passes a test of a training result, and output the load prediction model.

Next, the specific configuration of the load distribution scheme generation module 40 will be described in detail. As described above, the load distribution scheme generating module 40 may further include a power operation efficiency information acquiring unit configured to acquire a real-time power operation information set of the micro grid, obtain power operation efficiency information, power transmission loss information, and power demand fluctuation information, a preset target unit configured to construct a preset optimization target based on the power operation efficiency information, the power transmission loss information, and the power demand fluctuation information, the preset optimization target including a preset power operation efficiency target, a preset power transmission loss target, and a preset power demand fluctuation target, a first load distribution data generating unit configured to generate first load distribution data in combination with the plurality of power load prediction data according to the preset power operation efficiency target, a second load distribution data generating unit configured to generate second load distribution data in combination with the plurality of power load prediction data according to the preset power transmission loss target, and a third load distribution data generating unit configured to generate third load distribution data in combination with the plurality of power load prediction data according to the preset power demand fluctuation target, and a load distribution scheme constructing unit configured to construct the load distribution scheme based on the first load distribution data and the third load distribution data.

Next, the specific configuration of the power intelligent scheduling module 50 will be described in detail. As described above, executing the load distribution scheme to perform power intelligent optimization scheduling on a plurality of nodes of the micro grid, the power intelligent scheduling module 50 may further include an electrical load data determining unit configured to execute the load distribution scheme, determine whether a plurality of electrical load data of the plurality of nodes is greater than or equal to a preset threshold, an operation feedback information generating unit configured to perform real-time operation monitoring on the plurality of nodes of the micro grid if the plurality of electrical load data is less than the preset threshold, generate operation feedback information, and a load balance score generating unit configured to perform load balance evaluation on the micro grid based on the operation feedback information, generate a load balance score, and an emergency response scheduling policy generating unit configured to generate an emergency response scheduling policy according to the load balance score, and perform power intelligent optimization scheduling on the plurality of nodes.

The emergency response scheduling strategy generating unit can further comprise an abnormal node determining subunit, a weight sequence generating subunit and an intelligent optimizing scheduling subunit, wherein the abnormal node determining subunit is used for performing abnormal positioning on the plurality of nodes of the micro-grid and determining a plurality of abnormal nodes if the plurality of electric load data are larger than or equal to the preset threshold value, the weight sequence generating subunit is used for performing weight distribution on the plurality of abnormal nodes to generate a plurality of weight factors, the plurality of weight factors are arranged in a descending order to generate a weight sequence, the deviation correcting result generating subunit is used for performing deviation correction according to the weight sequence based on the plurality of abnormal nodes to generate a plurality of deviation correcting results, and the intelligent optimizing scheduling subunit is used for performing intelligent power optimizing scheduling on the micro-grid based on the plurality of correcting nodes.

The micro-grid dynamic load balancing and optimizing system based on the historical electricity consumption data provided by the embodiment of the invention can execute the micro-grid dynamic load balancing and optimizing method based on the historical electricity consumption data provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.

Although the present application makes various references to certain modules in a system according to an embodiment of the present application, any number of different modules may be used and run on a user terminal and/or a server, and each unit and module included are merely divided according to functional logic, but are not limited to the above-described division, so long as the corresponding functions can be implemented, and in addition, specific names of each functional unit are only for convenience of distinguishing from each other, and are not intended to limit the scope of protection of the present application.

The above embodiments do not limit the scope of the present application. It will be apparent to those skilled in the art that various modifications, combinations, and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of the present application. In some cases, the acts or steps recited in the present application may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. The micro-grid dynamic load balancing optimization method based on historical electricity consumption data is characterized by comprising the following steps of:

sensing data of a plurality of nodes of the micro-grid according to the historical electricity utilization period to obtain a plurality of historical electricity utilization data;

Constructing a historical power change map based on the plurality of historical power usage data;

Constructing a load prediction model according to the historical power change diagram to predict the micro-grid, and generating a plurality of power load prediction data;

Load balancing optimization is carried out based on the plurality of power load prediction data, and a load distribution scheme is generated;

executing the load distribution scheme to perform intelligent power optimization scheduling on a plurality of nodes of the micro-grid;

The method for sensing the data of the nodes of the micro-grid according to the historical electricity utilization period to obtain a plurality of historical electricity utilization data comprises the following steps:

Determining the historical electricity utilization period based on historical electricity utilization ladder information;

Setting a plurality of nodes according to historical power supply and demand information of the micro-grid;

According to the historical electricity utilization period, the electricity utilization collection is carried out on the micro-grid by combining the supply-demand relation of the plurality of nodes, and a plurality of historical electricity consumption data and a plurality of historical electricity load data are obtained;

Adding the plurality of historical electricity usage data, the plurality of historical electrical load data to the plurality of historical electricity usage data;

the load balancing optimization is performed based on the plurality of power load prediction data, and a load distribution scheme is generated, and the method comprises the following steps:

acquiring a real-time power operation information set of a micro-grid to obtain power operation efficiency information, power transmission loss information and power demand fluctuation information;

Constructing a preset optimization target based on the power operation efficiency information, the power transmission loss information and the power demand fluctuation information, wherein the preset optimization target comprises a preset power operation efficiency target, a preset power transmission loss target and a preset power demand fluctuation target;

generating first load distribution data according to the preset power operation efficiency target and combining the plurality of power load prediction data;

generating second load distribution data according to the preset power transmission loss target and combining the plurality of power load prediction data;

generating third load distribution data according to the preset power demand fluctuation target and combining the plurality of power load prediction data;

constructing the load distribution scheme based on the first load distribution data, the second load distribution data and the third load distribution data;

the method for performing the load distribution scheme to perform intelligent power optimization scheduling on a plurality of nodes of the micro-grid comprises the following steps:

Executing the load distribution scheme, and judging whether a plurality of pieces of electric load data of the plurality of nodes are larger than or equal to a preset threshold value;

if the plurality of electrical load data are smaller than the preset threshold, performing real-time operation monitoring on the plurality of nodes of the micro-grid to generate operation feedback information;

Carrying out load balance evaluation on the micro-grid based on the operation feedback information to generate a load balance score;

Generating an emergency response scheduling strategy according to the load balancing scores, and performing intelligent power optimization scheduling on the nodes;

If the plurality of electrical load data is larger than or equal to the preset threshold value, carrying out abnormal positioning on the plurality of nodes of the micro-grid, and determining a plurality of abnormal nodes;

Performing weight distribution on the plurality of abnormal nodes to generate a plurality of weight factors, and performing descending arrangement on the plurality of weight factors to generate a weight sequence;

performing deviation correction according to the weight sequence based on the plurality of abnormal nodes to generate a plurality of deviation correction results;

And correcting the plurality of abnormal nodes according to the plurality of deviation correction results, and performing intelligent power optimization scheduling on the micro-grid based on the plurality of correction nodes.

2. The method for dynamic load balancing optimization of a micro-grid based on historical electricity usage data according to claim 1, wherein the method comprises the steps of:

determining a first coordinate axis and a second coordinate axis based on the plurality of historical electricity consumption data;

determining a third coordinate axis and a fourth coordinate axis based on the plurality of historical electrical load data;

Constructing a historical electricity consumption coordinate system based on the first coordinate axis and the second coordinate axis;

constructing a historical electrical load coordinate system based on the third coordinate axis and the fourth coordinate axis;

Synchronizing the plurality of historical electricity consumption data to the historical electricity consumption coordinate system to obtain a historical electricity consumption change trend;

Synchronizing the plurality of historical electrical load data to the historical electrical load coordinate system to obtain a historical electrical load change trend;

and constructing the historical power change graph according to the historical power consumption change trend and the historical power load change trend.

3. The method for dynamic load balancing optimization of a micro-grid based on historical electricity consumption data according to claim 1, wherein the load prediction model comprises the following steps:

setting a plurality of electricity utilization time scales according to the historical electricity utilization period;

extracting a plurality of power change data based on the plurality of power utilization time scales in combination with the historical power change map;

dividing the plurality of power variation data into a training data set, a supervisory data set, and a test data set;

And based on the BP neural network, performing supervised iterative training by combining the training data set and the supervision data set until the test result of the test data set passes, and outputting the load prediction model.

4. A microgrid dynamic load balancing optimization system based on historical electricity usage data, characterized in that the system is used for implementing the microgrid dynamic load balancing optimization method based on historical electricity usage data according to any one of claims 1-3, the system comprising:

The historical electricity consumption data acquisition module is used for carrying out data sensing on a plurality of nodes of the micro-grid according to the historical electricity consumption period to obtain a plurality of historical electricity consumption data;

A historical power change map generation module for constructing a historical power change map based on the plurality of historical power usage data;

The micro-grid load prediction module is used for constructing a load prediction model according to the historical power change diagram to predict the micro-grid and generating a plurality of power load prediction data;

the load distribution scheme generation module is used for carrying out load balancing optimization based on the plurality of power load prediction data to generate a load distribution scheme;

and the power intelligent scheduling module is used for executing the load distribution scheme to perform power intelligent optimal scheduling on a plurality of nodes of the micro-grid.