CN116128243B - Multi-dimensional safety intelligent control method for cascade hydropower station - Google Patents
Multi-dimensional safety intelligent control method for cascade hydropower station Download PDFInfo
- Publication number
- CN116128243B CN116128243B CN202310158607.1A CN202310158607A CN116128243B CN 116128243 B CN116128243 B CN 116128243B CN 202310158607 A CN202310158607 A CN 202310158607A CN 116128243 B CN116128243 B CN 116128243B
- Authority
- CN
- China
- Prior art keywords
- model
- hydropower station
- cascade hydropower
- target
- reservoir
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Feedback Control In General (AREA)
Abstract
本发明提供的一种梯级水电站多维安全智能管控方法，所述管控方法包括：收集目标梯级水电站的基础资料；采用人工智能模型从历史运行调度数据中提取带有管理者主观决策偏好的梯级水电站适应性调度规则；确定极端风险源模拟目标，梯级水电站安全管控目标和目标管控期；采用系统动力学方法构建梯级水电站系统动力学模型；根据模型主要控制方程和目标梯级水电站的相关数据确定模型变量函数表达式；根据安全管控目标划定多维安全约束条件；运行所述梯级水电站系统动力学模型。能够为复杂风险源综合作用下的梯级水电站系统多维安全调度方案制定提供技术支撑，提升梯级水电站风险智能化管控水平。
The invention provides a multi-dimensional safe intelligent management and control method for cascade hydropower stations. The management and control method includes: collecting basic data of the target cascade hydropower station; using an artificial intelligence model to extract the cascade hydropower station adaptation with the manager's subjective decision-making preferences from the historical operation scheduling data. Scheduling rules; determine extreme risk source simulation targets, cascade hydropower station safety control targets and target control periods; use system dynamics methods to construct a cascade hydropower station system dynamics model; determine model variable functions based on the main control equations of the model and relevant data of the target cascade hydropower station Expression; delimit multi-dimensional safety constraints according to safety management and control objectives; run the cascade hydropower station system dynamics model. It can provide technical support for the formulation of multi-dimensional safety dispatch plans for cascade hydropower station systems under the comprehensive influence of complex risk sources, and improve the level of intelligent risk management and control of cascade hydropower stations.
Description
Technical Field
The invention relates to the field of hydraulic and hydroelectric engineering, in particular to a multi-dimensional safe intelligent management and control method for a cascade hydropower station.
Background
The cascade hydropower station joint scheduling enables the hydropower resources to be utilized efficiently, and comprehensive benefits of flood control, power generation, ecology, shipping, water supply and the like of the hydropower facilities are brought into full play to the maximum extent. However, in the operation process of the cascade hydropower station, individual operation targets cannot reach the expected requirements due to the influence of various factors such as natural inflow conditions, engineering facility conditions and operation scheduling modes, and a multidimensional safety event exists. With the increasing scale of river basin cascade development, the source of system risk leading to multidimensional security events is also significantly increased. The corresponding safety scheduling scheme is formulated under the comprehensive action of complex risk sources, and the multi-dimensional safety events of the cascade hydropower station system are effectively managed and controlled, so that the safety and stable operation of the engineering can be ensured, the safety of life and property of downstream residents can be ensured, the sustainable development of socioeconomic performance is promoted, and the cascade hydropower station system has important social significance.
The existing cascade hydropower station safety control method mostly adopts an optimized solution safety scheduling scheme taking the probability of risk as a target under a specific inflow situation, and the method assumes normal operation of engineering facilities, only takes natural inflow as a system risk source, and fails to consider the influence of the comprehensive effect of multiple risk sources on the system operation. In addition, the scheduling scheme set obtained by optimizing and solving still needs a manager to further make an artificial decision, so that the timeliness of safety control is reduced.
Disclosure of Invention
In view of the above, the present invention has been made in order to provide a multi-dimensional safe and intelligent management and control method for a cascade hydropower station, which overcomes or at least partially solves the above-mentioned problems.
According to one aspect of the invention, there is provided a multi-dimensional safety intelligent control method for a cascade hydropower station, the control method comprising:
collecting basic data of a target cascade hydropower station;
extracting adaptive scheduling rules of the cascade hydropower station with subjective decision preference of a manager from historical operation scheduling data by adopting an artificial intelligent model;
determining an extreme risk source simulation target, a cascade hydropower station safety control target and a target control period;
constructing a cascade hydropower station system dynamics model by adopting a system dynamics method;
coupling the artificial intelligence model with related variables of the system dynamics model by means of a Python programming language;
determining a model variable function expression according to a model main control equation and related data of a target cascade hydropower station, and determining a simulation time length and a time length by combining a safety control target;
defining a multi-dimensional safety constraint condition according to a safety control target, and controlling related variables of the model through Boolean logic operation and extremum function;
and operating the cascade hydropower station system dynamics model to obtain an intelligent cascade hydropower station scheduling scheme in a multidimensional safety target management and control period under an extreme risk scene.
Optionally, the collecting basic data of the target cascade hydropower station specifically includes:
collecting a target cascade hydropower station water level reservoir capacity relation curve, a drainage tail water relation curve, drainage capacity curves of all drainage facilities and historical operation scheduling data;
the historical operation scheduling data comprises a database water level, a warehouse-in flow and a warehouse-out flow.
Optionally, the step hydropower station adaptive scheduling rule extracting the subjective decision preference of the manager from the historical operation scheduling data by adopting the artificial intelligence model specifically comprises the following steps:
the method comprises the steps of extracting cascade hydropower station adaptive scheduling rules with manager subjective decision preference from historical operation scheduling data by adopting an artificial intelligent model, taking an LSTM model in the artificial intelligent model as an example, defining a library water level and a library flow as model input data, defining a library outlet flow as output data, setting parameters required by the LSTM model, and setting core components of each unit in the LSTM model including a forgetting gate, an input gate, a cell state and an output gate.
Optionally, the parameters required for setting the LSTM model specifically include: maximum iteration number, hidden layer number, node number.
Optionally, the step hydropower station system dynamics model construction method specifically includes:
determining a main structural variable of a model according to an actual engineering structure of the target cascade hydropower station, and determining a related auxiliary variable of the model according to an extreme risk source simulation target;
the method comprises the steps of taking the reservoir capacity and the total power generation amount of a hydropower station as model stock, taking the inflow, outflow and daily power generation amount of the hydropower station as model flow, and connecting different variables through a directed causal link so as to construct a system dynamics model describing the operation foundation of the hydropower station;
adding variables for describing system structural details into a basic system dynamics model according to the actual structure of the hydropower station, wherein the variables comprise the steps of reducing the outlet flow into the flow discharged through different water discharge facilities, establishing the drainage capacity relation between the reservoir water level and the different facilities, and constructing a hydropower station operation refined system dynamics model by adopting directed causal link connection;
and adding corresponding auxiliary variables in combination with a risk source simulation target, and constructing a hydropower station operation multidimensional risk system dynamics model by adopting directed causal link connection.
Optionally, the outflow includes outflow through various drainage facilities, overflow volume, water loss due to evaporation and infiltration in the reservoir.
Optionally, the coupling the artificial intelligence model with the related variables of the system dynamics model by means of the Python programming language specifically includes:
the artificial intelligent model is coupled with related variables of a system dynamics model by means of a Python programming language, the water level and the warehousing flow of a database at each moment in system dynamics are used as LSTM model input, and the output flow of the LSTM model is used as the system warehousing flow at the current moment and is fed back to the system dynamics model.
Optionally, the determining the model variable function expression according to the model main control equation and the related data of the target cascade hydropower station specifically includes:
and determining the simulation time length and the time step length by combining the safety control target, wherein the model main control equation comprises a water quantity balance equation and a generating capacity calculation equation, and the simulation time length and the time step length are as follows:
equation V for water balance i,t+1 ＝V i,t +I i,t +LI i,t -Q P i,t -Q F i,t -Q OV i,t -Q L i,t (6)
Wherein V is i,t+1 Representing the storage capacity of the ith reservoir at the end of the t period; v (V) i,t Representing the initial reservoir capacity of the ith reservoir in the period t; i i,t Representing the inflow of the ith reservoir generated by the release of the upstream reservoir in the t period; LI (LI) i,t Representing the interval inflow generated in the period t between the upstream reservoir and the downstream reservoir; q (Q) P i,t Representing the power generation flow released by the ith reservoir through the unit in the t period; q (Q) F i,t Representing the flow rate released by the ith reservoir in the t period through other water discharge facilities except the unit; q (Q) OV i,t Representing overflow quantity generated by the flood peak of the ith reservoir in the period t; q (Q) L i,t Indicating the loss of other water quantity of the ith reservoir in the period t caused by evaporation, infiltration and the like;
calculation equation of electric power generation amount, P i,t ＝9.81×η×H i,t ×Q P i,t ×t (7)
Wherein P is i,t Representing the generated energy of the ith reservoir in the t period; η represents a unit efficiency coefficient of the ith reservoir; h i,t Representing the average water of the ith reservoir in period tA head.
The invention provides a multi-dimensional safe intelligent control method for a cascade hydropower station, which comprises the following steps: collecting basic data of a target cascade hydropower station; extracting adaptive scheduling rules of the cascade hydropower station with subjective decision preference of a manager from historical operation scheduling data by adopting an artificial intelligent model; determining an extreme risk source simulation target, a cascade hydropower station safety control target and a target control period; constructing a cascade hydropower station system dynamics model by adopting a system dynamics method; coupling the artificial intelligence model with related variables of the system dynamics model by means of a Python programming language; determining a model variable function expression according to a model main control equation and related data of a target cascade hydropower station, and determining a simulation time length and a time length by combining a safety control target; defining a multi-dimensional safety constraint condition according to a safety control target, and controlling related variables of the model through Boolean logic operation and extremum function; and operating the cascade hydropower station system dynamics model to obtain an intelligent cascade hydropower station scheduling scheme in a multidimensional safety target management and control period under an extreme risk scene. The technical support can be provided for the establishment of a multi-dimensional safety scheduling scheme of the cascade hydropower station system under the comprehensive action of complex risk sources, and the intelligent management and control level of the cascade hydropower station risk is improved.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of an LSTM module according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a dynamics model of a hydropower station basic system provided by an embodiment of the invention;
FIG. 3 is a dynamic model of a hydropower station refinement system provided by an embodiment of the invention;
FIG. 4 is a dynamic model of a multidimensional risk system of a hydropower station provided by an embodiment of the invention;
FIG. 5 is a model coupling calculation method according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of an LSTM model adaptive scheduling rule extraction effect according to an embodiment of the present invention;
FIG. 7 is a dynamic model of a cascade hydropower station system provided by an embodiment of the invention;
fig. 8 is a schematic diagram of an intelligent scheduling scheme in a multi-dimensional safety target management and control period of a cascade hydropower station according to an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The terms "comprising" and "having" and any variations thereof in the description embodiments of the invention and in the claims and drawings are intended to cover a non-exclusive inclusion, such as a series of steps or elements.
The technical scheme of the invention is further described in detail below with reference to the accompanying drawings and the examples.
The invention provides a multi-dimensional safe intelligent management and control method for a cascade hydropower station, which can provide technical support for establishing a multi-dimensional safe scheduling scheme of a cascade hydropower station system under the comprehensive action of complex risk sources and improve the risk intelligent management and control level of the cascade hydropower station.
Example 1
A multi-dimensional safe intelligent control method for a cascade hydropower station comprises the following specific steps:
and collecting basic data of historical operation scheduling data (library water level, warehouse flow and warehouse outlet flow) of a target cascade hydropower station water level and reservoir capacity relation curve, a drainage tail water relation curve, drainage capacity curves of all drainage facilities.
The method comprises the steps of extracting cascade hydropower station adaptive scheduling rules with manager subjective decision preference from historical operation scheduling data by adopting an artificial intelligent model, taking an LSTM model in the artificial intelligent model as an example, defining a library water level and a library flow as model input data, defining a library outlet flow as output data, setting parameters (maximum iteration times, hidden layer numbers, node numbers and the like) required by the LSTM model, wherein the core composition of each unit in the LSTM comprises a forgetting gate, an input gate, a cell state and an output gate.
As shown in fig. 1. First, the forget gate screens and discards the output information from the previous unit and the current input information, and transfers the result to the input gate (formula 1). The input gate then determines which information received needs to be updated and added to the cell state (equations 2 and 3). Finally, it is decided by the output gate which information in the current cell is output to the next cell (equations 4 and 5). The LSTM network established in this study comprises an input layer, an LSTM hidden layer and an output layer, and is trained by continuously adjusting weights and thresholds using a time back propagation algorithm.
Forgetting the door: f (f) t ＝σ(W f X t +U f h t-1 +b f ) (1)
An input door: i.e t ＝σ(W i X t +U i h t-1 +b i ) (2)
Cell state: c (C) t ＝f t ·C t-1 +i t ·tanh(W c X t +U c h t-1 +b c ) (3)
Output door: o (O) t ＝σ(W o X t +U o h t-1 +b o ) (4)
Hidden door: h is a t ＝O t ·tanh(C t ) (5)
Wherein f t i t C t O t Respectively representing a forgetting door, an input door, a unit state and an output door.
X t Represents the current input information, h t Representing the hidden layer output.
[W f ,W i ,W c ,W o ]，[U f ,U i ,U c ,U o ]，[b f ,b i ,b c ,b o ]The input information weight matrix, the hidden information weight matrix and the deviation vector of each part are represented respectively. σ () and tanh () represent a sigmoid activation function and a hyperbolic tangent function, respectively.
Determining 80% of the collected historical scheduling data sequences as training sequences and 20% as test sequences, and enabling an LSTM model to learn scheduling rules in historical operation by using the running model;
determining an extreme risk source simulation target, a cascade hydropower station safety control target and a target control period;
and constructing a cascade hydropower station system dynamics model by adopting a system dynamics method, determining a main structural variable of the model according to an actual engineering structure of a target cascade hydropower station, and determining a model-related auxiliary variable according to an extreme risk source simulation target. The hydropower station storage capacity and total power generation are taken as model stock, the hydropower station inflow, outflow (including outflow through various drainage facilities, overflow, water loss caused by evaporation and infiltration in a storage area) and daily power generation are taken as model flow, and different variables are connected through a directed causal link to construct a system dynamics model describing the operation foundation of the hydropower station, as shown in fig. 2.
According to the actual structure of the hydropower station, variables for describing system structural details are added into a basic system dynamics model, the method comprises the steps of reducing the outlet flow into the amount of water discharged through different water discharging facilities, establishing the water discharging capacity relation between the reservoir water level and the different facilities, and constructing a hydropower station operation refined system dynamics model by adopting directed causal link connection, wherein as shown in fig. 3, the target hydropower station is assumed to comprise two forms of unit overcurrent and gate overcurrent.
And finally, adding corresponding auxiliary variables in combination with a risk source simulation target, and constructing a multi-dimensional risk system dynamics model for hydropower station operation by adopting directed causal link connection, wherein the explanation is given by taking gate overcurrent capacity damage and unit generator damage stall as examples, and the explanation is shown in fig. 4.
The artificial intelligent model is coupled with related variables of a system dynamics model by means of a Python programming language, the water level and the flow of the warehouse-in flow at each moment in the system dynamics are used as LSTM model input, the output flow of the LSTM model is used as the flow of the system warehouse-out flow at the current moment and fed back to the system dynamics model, as shown in figure 5, so that the whole operation process of the model is controlled by an adaptive scheduling rule.
Determining a model variable function expression according to a model main control equation and related data of a target cascade hydropower station, determining a simulation time length and a time step length by combining a safety control target, wherein the model main control equation comprises a water quantity balance equation (formula 6) and a generating capacity calculation equation (formula 7), and the model variable function expression is as follows:
V i,t+1 ＝V i,t +I i,t +LI i,t -Q P i,t -Q F i,t -Q OV i,t -Q L i,t (6)
wherein V is i,t+1 Representing the storage capacity of the ith reservoir at the end of the t period; v (V) i,t Representing the initial reservoir capacity of the ith reservoir in the period t; i i,t Representing the inflow of the ith reservoir generated by the release of the upstream reservoir in the t period; LI (LI) i,t Representing the interval inflow generated in the period t between the upstream reservoir and the downstream reservoir; q (Q) P i,t Representing the power generation flow released by the ith reservoir through the unit in the t period; q (Q) F i,t Representing the flow released by the ith reservoir in the period t through other water discharge facilities (including deep holes, surface holes, spillways and the like) except the unit; q (Q) OV i,t Representing overflow quantity generated by the flood peak of the ith reservoir in the period t; q (Q) L i,t Indicating the loss of other water quantity of the ith reservoir in the period t caused by evaporation, infiltration and the like;
P i,t ＝9.81×η×H i,t ×Q P i,t ×t (7)
wherein P is i,t Representing the generated energy of the ith reservoir in the t period; η represents a unit efficiency coefficient of the ith reservoir; h i,t The average head of the ith reservoir over period t is indicated.
Assuming that the safety management and control period is one year, and the extreme risk sources are half damaged in the overflow capacity of the reservoir gate and half damaged in the generator set of the reservoir gate at the beginning of the flood period (on the 180 th day), and stopping running, the expression of each variable function in the multi-dimensional risk system dynamics model of the hydropower station is shown in table 1:
TABLE 1 model structural variable expression
Defining a multidimensional safety constraint condition according to a safety control target, controlling related variables of a model through Boolean logic operation and an extremum function, and assuming that the multidimensional safety control target comprises flood control and power generation, the flood control safety requirement water level is lower than the check flood level of a hydropower station, the power generation safety requirement minimum daily power generation amount of the hydropower station meets the minimum daily power generation amount under the guaranteed power output, and the functional expression of the related variables of the model under the multidimensional safety constraint condition is shown in table 2:
table 2 model dependent variable expressions under multidimensional safety constraints
And (3) operating the model to obtain the intelligent scheduling scheme of the cascade hydropower station in the multidimensional safety target management and control period under the extreme risk scene.
Example 2
Collecting basic data of a hydropower station with a step A-B of a certain river basin, wherein the normal water storage level of the hydropower station A is 600m, the dead water level of the hydropower station A is 540m, and the normal water storage level of the hydropower station B is 380m, and the dead water level of the hydropower station B is 370m;
extracting adaptive scheduling rules of the cascade hydropower station with subjective decision preference of a manager from historical operation scheduling data by adopting an artificial intelligent model; in the example, a long-term memory network LSTM model is selected, the history scheduling data comprises date data from 1 month at 2015 to 1 month at 2020, and data from 1 month at 2015 to 31 days at 2018 to 1 month at 2019 are used as training sets and data from 1 month at 2019 to 1 month at 2020 are used as test sets according to the 'two-eight principle'. Taking the warehouse-in flow and the warehouse-out water level as model inputs, taking the warehouse-in flow as model outputs, training the LSTM model and testing the accuracy of the LSTM model, wherein the test effect is shown in figure 6;
in the example, the hydropower station A and the hydropower station B are both provided with two drainage facilities of an adjustable gate and a generator set, and the two hydropower stations preferentially adopt the unit overcurrent in daily operation. The extreme risk event of this example is that under the condition of high water years, two hydropower station units fail due to earthquake or engineering aging and the like, half of the units are stopped, and nine months of maintenance are carried out. The safety control target is the power generation safety and flood control safety of the cascade hydropower station, and the target control period is one year after the self-assembly unit fails;
and constructing a dynamic model of the cascade hydropower station system, wherein the overall structure of the model is shown in figure 7. To achieve the simulation of the unit faults, a "unit availability factor" is added in the model as a model auxiliary variable.
And (3) coupling the LSTM model trained in the second step with a dynamic model of the cascade reservoir system to control the whole operation process of the model by adopting the adaptive dispatching rules.
The model variable expression is determined, the simulation time length and the time step length are determined, the simulation time length is 365d in total from 1 month, 1 day to 12 months and 31 days in this example, the time step length is 1d, and the main variable expression is shown in table 3.
TABLE 3 model structural variable expression
According to the safety control target, defining a multi-dimensional safety constraint condition, in the example, the minimum output of the power generation safety control hydropower station is ensured to be output, the highest water level of the flood control safety control hydropower station does not exceed the check flood level, and the calculation expression of the related variables of the model is adjusted through Boolean logic operation and extremum function, as shown in table 4.
Table 4 model dependent variable expressions under multidimensional safety constraints
And (3) operating the model to obtain an intelligent scheduling scheme in a multi-dimensional safety target management and control period of the cascade hydropower station under an extreme risk scene, as shown in fig. 8.
The beneficial effects are that: the invention provides a multi-dimensional safe intelligent management and control method for a cascade hydropower station, which can provide technical support for establishing a multi-dimensional safe scheduling scheme of a cascade hydropower station system under the comprehensive action of complex risk sources and improve the risk intelligent management and control level of the cascade hydropower station.
The foregoing detailed description of the invention has been presented for purposes of illustration and description, and it should be understood that the invention is not limited to the particular embodiments disclosed, but is intended to cover all modifications, equivalents, alternatives, and improvements within the spirit and principles of the invention.
Claims (5)
1. The multidimensional safety intelligent control method for the cascade hydropower station is characterized by comprising the following steps of:
collecting basic data of a target cascade hydropower station;
extracting adaptive scheduling rules of the cascade hydropower station with subjective decision preference of a manager from historical operation scheduling data by adopting an artificial intelligent model;
determining an extreme risk source simulation target, a cascade hydropower station safety control target and a target control period;
constructing a cascade hydropower station system dynamics model by adopting a system dynamics method;
coupling the artificial intelligence model with related variables of the system dynamics model by means of a Python programming language;
determining a model variable function expression according to a model main control equation and related data of a target cascade hydropower station, and determining a simulation time length and a time length by combining a safety control target;
defining a multi-dimensional safety constraint condition according to a safety control target, and controlling related variables of the model through Boolean logic operation and extremum function;
operating the cascade hydropower station system dynamics model to obtain a cascade hydropower station intelligent scheduling scheme in a multidimensional safety target management and control period under an extreme risk scene;
the step hydropower station system dynamics model construction method adopting the system dynamics method specifically comprises the following steps:
determining a main structural variable of a model according to an actual engineering structure of the target cascade hydropower station, and determining a related auxiliary variable of the model according to an extreme risk source simulation target;
the method comprises the steps of taking the reservoir capacity and the total power generation amount of a hydropower station as model stock, taking the inflow, outflow and daily power generation amount of the hydropower station as model flow, and connecting different variables through a directed causal link so as to construct a system dynamics model describing the operation foundation of the hydropower station;
adding variables for describing system structural details into a basic system dynamics model according to the actual structure of the hydropower station, wherein the variables comprise the steps of reducing the outlet flow into the flow discharged through different water discharge facilities, establishing the drainage capacity relation between the reservoir water level and the different facilities, and constructing a hydropower station operation refined system dynamics model by adopting directed causal link connection;
adding corresponding auxiliary variables in combination with a risk source simulation target, and constructing a hydropower station operation multidimensional risk system dynamics model by adopting directed causal link connection;
the coupling of the artificial intelligence model with the related variables of the system dynamics model by means of the Python programming language specifically comprises:
coupling the artificial intelligent model with related variables of a system dynamics model by means of a Python programming language, taking the water level and the warehousing flow of a database at each moment in system dynamics as LSTM model input, and feeding back the output flow of the LSTM model as the system warehousing flow at the current moment to the system dynamics model;
the determining the model variable function expression according to the model main control equation and the related data of the target cascade hydropower station specifically comprises the following steps:
and determining the simulation time length and the time step length by combining the safety control target, wherein the model main control equation comprises a water quantity balance equation and a generating capacity calculation equation, and the simulation time length and the time step length are as follows:
equation V for water balance i,t+1 ＝V i,t +I i,t +LI i,t -Q P i,t -Q F i,t -Q OV i,t -Q L i,t (6)
Wherein V is i,t+1 Representing the storage capacity of the ith reservoir at the end of the t period; v (V) i,t Representing the initial reservoir capacity of the ith reservoir in the period t; i i,t Representing the inflow of the ith reservoir generated by the release of the upstream reservoir in the t period; LI (LI) i,t Representing the interval inflow generated in the period t between the upstream reservoir and the downstream reservoir; q (Q) P i,t Representing the power generation flow released by the ith reservoir through the unit in the t period; q (Q) F i,t Representing the flow rate released by the ith reservoir in the t period through other water discharge facilities except the unit; q (Q) OV i,t Representing overflow quantity generated by the flood peak of the ith reservoir in the period t; q (Q) L i,t Indicating the loss of other water quantity of the ith reservoir in the period t caused by evaporation and infiltration;
calculation equation of electric power generation amount, P i,t ＝9.81×η×H i,t ×Q P i,t ×t(7)
Wherein P is i,t Representing the generated energy of the ith reservoir in the t period; η represents a unit efficiency coefficient of the ith reservoir; h i,t The average head of the ith reservoir over period t is indicated.
2. The multidimensional safety intelligent control method for the cascade hydropower station according to claim 1, wherein the collecting basic data of the target cascade hydropower station specifically comprises:
collecting a target cascade hydropower station water level reservoir capacity relation curve, a drainage tail water relation curve, drainage capacity curves of all drainage facilities and historical operation scheduling data;
the historical operation scheduling data comprises a database water level, a warehouse-in flow and a warehouse-out flow.
3. The multi-dimensional safe intelligent control method for the cascade hydropower station according to claim 1, wherein the step hydropower station adaptive scheduling rule with subjective decision preference of a manager extracted from historical operation scheduling data by adopting an artificial intelligent model specifically comprises the following steps:
the method comprises the steps of extracting cascade hydropower station adaptive scheduling rules with manager subjective decision preference from historical operation scheduling data by adopting an artificial intelligent model, wherein the artificial intelligent model is an LSTM model, a library water level and a library flow are defined as model input data, a library outlet flow is defined as output data, parameters required by the LSTM model are set, and the core composition of each unit in the LSTM comprises a forgetting gate, an input gate, a cell state and an output gate.
4. The multi-dimensional safety intelligent control method for the cascade hydropower station according to claim 3, wherein the setting of parameters required by the LSTM model specifically comprises: maximum iteration number, hidden layer number, node number.
5. The multi-dimensional safe and intelligent control method for the cascade hydropower station according to claim 1, wherein the outflow comprises outflow through various drainage facilities, overflow volume, water loss caused by evaporation and infiltration in a reservoir area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310158607.1A CN116128243B (en) | 2023-02-20 | 2023-02-20 | Multi-dimensional safety intelligent control method for cascade hydropower station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310158607.1A CN116128243B (en) | 2023-02-20 | 2023-02-20 | Multi-dimensional safety intelligent control method for cascade hydropower station |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116128243A CN116128243A (en) | 2023-05-16 |
| CN116128243B true CN116128243B (en) | 2023-12-01 |
Family
ID=86302792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310158607.1A Active CN116128243B (en) | 2023-02-20 | 2023-02-20 | Multi-dimensional safety intelligent control method for cascade hydropower station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116128243B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116976760A (en) * | 2023-07-28 | 2023-10-31 | 中国长江三峡集团有限公司 | Hydropower engineering intelligent model construction method and device and electronic equipment |
| CN118378870B (en) * | 2024-06-26 | 2024-08-27 | 华中科技大学 | A method and system for evaluating scheduling scheme of cascade hydropower stations |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105676890A (en) * | 2016-01-22 | 2016-06-15 | 长江水利委员会长江科学院 | Dynamic operation water level control method for 3D or higher cascaded reservoirs in flood season |
| CN112785454A (en) * | 2020-12-25 | 2021-05-11 | 国电大渡河流域水电开发有限公司 | Intelligent scheduling method for flood season of cascade hydropower station and decision support system |
| CN113052378A (en) * | 2021-03-24 | 2021-06-29 | 水利部海河水利委员会水资源保护科学研究所 | Watershed multi-reservoir combined dispatching method based on water delivery efficiency and ecological benefits |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019174040A1 (en) * | 2018-03-16 | 2019-09-19 | 大连理工大学 | Coupling and clustering analysis and decision-making tree based short-term power generation scheduling method for cascaded hydroelectric station group |
-
2023
- 2023-02-20 CN CN202310158607.1A patent/CN116128243B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105676890A (en) * | 2016-01-22 | 2016-06-15 | 长江水利委员会长江科学院 | Dynamic operation water level control method for 3D or higher cascaded reservoirs in flood season |
| CN112785454A (en) * | 2020-12-25 | 2021-05-11 | 国电大渡河流域水电开发有限公司 | Intelligent scheduling method for flood season of cascade hydropower station and decision support system |
| CN113052378A (en) * | 2021-03-24 | 2021-06-29 | 水利部海河水利委员会水资源保护科学研究所 | Watershed multi-reservoir combined dispatching method based on water delivery efficiency and ecological benefits |
Non-Patent Citations (1)
| Title |
|---|
| 纪昌明 ; 李克飞 ; 张验科 ; 谢维 ; .梯级水电站群联合调度多目标风险决策模型.水力发电.2013,(第04期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116128243A (en) | 2023-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116128243B (en) | Multi-dimensional safety intelligent control method for cascade hydropower station | |
| CN112036611B (en) | A Grid Optimal Planning Method Considering Risks | |
| CN114648176B (en) | Wind-solar power supply consumption optimization method based on data driving | |
| CN109615146B (en) | Ultra-short-term wind power prediction method based on deep learning | |
| CN111555355A (en) | Scheduling strategy and optimization method of water-photovoltaic combined power generation | |
| CN107240932A (en) | Photovoltaic plant capacity optimization method in a kind of water light complementary system | |
| CN110071530B (en) | Coordinated scheduling method for wind power ramping in power system with energy storage based on LSTM | |
| CN116683530A (en) | Wind-light-containing hybrid type pumping and storing station cascade reservoir random optimization scheduling method | |
| CN118656668A (en) | A new power system power and electricity balance analysis method based on multi-cascade multi-process panoramic timing operation simulation | |
| CN106446383A (en) | A Method for Solving Uncertain Unit Combination Problems with Safety Constraints Based on Improved Constrained Order Optimization | |
| Xu et al. | Optimal dispatching rules of hydropower reservoir in flood season considering flood resources utilization: A case study of Three Gorges Reservoir in China | |
| CN104810863A (en) | Generator set active power real-time dispatching method considering wind power prediction error | |
| CN116418001A (en) | Reservoir group multi-energy complementary dispatching method and system to deal with uncertainty of new energy sources | |
| CN114330113B (en) | New energy power system elasticity optimization method based on deep reinforcement learning | |
| CN114169679A (en) | A day-ahead risk scheduling method for wind-solar-water multi-energy complementarity considering output stability | |
| Yu et al. | Research on reverse order impoundment mode of cascade reservoir flood control system: Case study on upper reaches of Yangtze River | |
| CN116865358A (en) | Multi-time long-scale power system wind power waste and load fluctuation tracking method and equipment | |
| CN117293894A (en) | Cascade hydropower-photovoltaic complementary planning method | |
| CN115967128A (en) | A Robust Day-ahead Scheduling Method for Cascaded Water-light Complementary Systems Considering the Vibration Region | |
| CN116415708A (en) | Power grid robust planning method considering confidence level | |
| CN114528771A (en) | New energy consumption measuring and calculating method and system based on hybrid particle swarm optimization | |
| Li et al. | MILP model for peak shaving in hydro-wind-solar-storage systems with uncertainty and unit commitment | |
| CN116187165A (en) | Power grid elasticity improving method based on improved particle swarm optimization | |
| CN114971039A (en) | A mid- and long-term scheduling method for water-light complementarity based on improved particle swarm optimization algorithm | |
| CN113128768A (en) | Water-wind-fire short-term optimization scheduling method considering wind-electricity uncertainty |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20231108 Address after: 100038, Fuxing Road, Beijing, Haidian District Applicant after: China Institute of Water Resources and Hydropower Research Applicant after: CHINA YANGTZE POWER Co.,Ltd. Address before: 100038, Fuxing Road, Beijing, Haidian District Applicant before: China Institute of Water Resources and Hydropower Research |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |