Hydropower station cascade joint dynamic scheduling method and system based on multi-objective optimization

Abstract

The invention relates to the technical field of hydropower station dispatching, in particular to a cascade joint dynamic dispatching method and system for a hydropower station based on multi-objective optimization. The method comprises the following steps: deploying global acquisition nodes, defining multi-source acquisition contents, acquiring node real-time data, and preprocessing the node real-time data to obtain cascade hydropower station real-time operation and working condition data; determining decision variables and boundary conditions, constructing a multi-objective optimization model, setting population scale and iteration number parameters, and generating an optimal solution in a non-dominated solution set as an initial scheduling scheme; the working condition is monitored in real time, parameter deviation is judged, an adjusted scheduling scheme matched with the actual working condition is obtained, and feedback is executed; the system comprises a dynamic data real-time acquisition module, a multi-target preliminary optimization module and a scheduling scheme dynamic adjustment and execution module. By means of the mode, working condition changes are monitored in real time, parameter deviation judgment is conducted, and the adaptability of a scheduling scheme is improved.

Description

Technical Field

[0001] This invention relates to the field of hydropower station dispatching technology, and in particular to a method and system for joint dynamic dispatching of hydropower station cascades based on multi-objective optimization. Background Technology

[0002] With the rapid development of the social economy, the demand for electricity continues to rise, and hydropower, as a clean and renewable energy source, is playing an increasingly prominent strategic role in the energy structure. Cascade joint dispatching of hydropower stations is a core technical means to achieve efficient utilization of water resources in a river basin, balanced power generation, flood control, ecological benefits, and other diverse needs. The scientific nature and real-time performance of its dispatching scheme directly affect the operational efficiency and safety stability of the cascade hydropower stations.

[0003] However, the existing cascade joint dispatching technology for hydropower stations still has the following defects: the dispatching scheme lacks a dynamic adjustment mechanism; most existing technologies are static dispatching modes, which cannot monitor changes in operating conditions in real time and make parameter deviation judgments. When encountering sudden situations such as sudden changes in inflow, load fluctuations, and extreme weather, it is difficult to quickly trigger the adjustment process, resulting in poor adaptability of the dispatching scheme and easy to cause operational risks. Summary of the Invention

[0004] The purpose of this invention is to provide a multi-objective optimization-based cascade joint dynamic scheduling method and system for hydropower stations. It aims to solve the technical problems in the prior art, such as the inability to monitor changes in operating conditions and judge parameter deviations in real time, the difficulty in quickly triggering adjustment processes when encountering sudden situations such as sudden changes in inflow, load fluctuations, and extreme weather, resulting in poor adaptability of the scheduling scheme and easy to cause operational risks.

[0005] To achieve the above objectives, this invention employs a multi-objective optimization-based joint dynamic scheduling method for hydropower stations, comprising the following steps: Deploy data collection nodes across the entire region, define the content to be collected from multiple sources, collect real-time data from the nodes, preprocess the real-time data from the nodes, and obtain real-time operation and working condition data of the cascade hydropower stations. Determine the decision variables and boundary conditions, construct a multi-objective optimization model, set the population size and iteration number parameters, and generate the optimal solution in the non-dominated solution set as the initial scheduling scheme; Real-time monitoring of operating conditions, determination of parameter deviations, obtaining an adjusted scheduling plan adapted to the actual operating conditions, and execution feedback.

[0006] Among the steps, the following steps are involved: deploying global data acquisition nodes, defining the content to be acquired from multiple sources, acquiring real-time data from the nodes, preprocessing the real-time data, and obtaining real-time operation and condition data of the cascade hydropower stations: The plan outlines the layout of data collection nodes across the entire cascade hydropower station area, establishing a full-chain data collection node network. These nodes include the inlet and outlet of each reservoir, dam monitoring sections, and key hydrological stations in the basin, where flow and water level monitoring terminals are deployed. The scope of multi-source data collection is divided into four core categories: hydrological dynamic data, unit operation data, power grid load data, and meteorological early warning data. Among them, hydrological dynamic data includes real-time inflow, outflow, water level and basin rainfall of each reservoir; unit operation data includes real-time output, power generation flow and equipment operating status of each unit; power grid load data includes real-time power load demand and peak-valley electricity price period division; and meteorological early warning data includes short-term heavy rainfall and typhoon extreme weather forecast information. Trigger a real-time data acquisition request for the node, set the data acquisition frequency, and obtain real-time data from the node.

[0007] After triggering the node's real-time data acquisition request, setting the data acquisition frequency, and obtaining the node's real-time data: The real-time data of the nodes is preprocessed, noise reduction is used to eliminate interference signals during data transmission, outlier data is removed by outlier detection, and the collected data of different formats are standardized into a unified data format.

[0008] The process includes preprocessing real-time node data, using noise reduction to eliminate interference signals during data transmission, removing outlier data through outlier detection, and standardizing collected data of different formats into a unified data format. Verify data integrity, generate real-time operation and status data for cascade hydropower stations, and output the data.

[0009] Among the steps, the following steps are involved: determining decision variables and boundary conditions, constructing a multi-objective optimization model, setting population size and iteration number parameters, and generating the optimal solution in the non-dominated solution set as the initial scheduling scheme: The decision variables and boundary conditions for multi-objective optimization are determined, with the power generation flow and outflow of each hydropower station at different times as the core decision variables, and the boundary conditions are set in combination with the cascade operation. The boundary conditions include the upper and lower limits of reservoir capacity, the upper and lower limits of unit output, the minimum ecological base flow outflow limit, and the reservoir flood control limit water level constraint. Establish a multi-objective optimization model that balances multiple objective requirements; The system acquires real-time operation and status data of cascade hydropower stations, optimizes and filters each decision variable through algorithmic iteration, generates a non-dominated solution set containing multiple feasible schemes, and selects an initial scheduling scheme.

[0010] Among the steps in establishing a multi-objective optimization model that balances multiple objective requirements: With the core optimization objectives of maximizing power generation efficiency, ensuring flood control safety, and guaranteeing ecological base flow, decision variables and boundary conditions are integrated.

[0011] Among these steps are: real-time monitoring of operating conditions, assessment of parameter deviations, obtaining an adjusted scheduling plan adapted to the actual operating conditions, and execution of feedback. Continuously receive real-time operation and status data of cascade hydropower stations, and monitor key parameters such as actual inflow, water level, actual output of generating units, and real-time load demand of the power grid for each reservoir. Perform parameter deviation judgment, set deviation thresholds for each key parameter, and compare the actual parameters monitored in real time with the initial parameters of the initial scheduling scheme; Generate an adjusted scheduling scheme adapted to the actual working conditions. Based on the type and degree of parameter deviation that triggers the adjustment process, modify the multi-objective optimization model to generate an adjusted scheduling scheme adapted to the current actual working conditions.

[0012] Among the steps, in determining parameter deviations, setting deviation thresholds for each key parameter, and comparing the real-time monitored parameters with the initial parameters of the initial scheduling scheme: If the deviation between the actual parameters and the initial parameters exceeds the set threshold, the scheduling scheme adjustment process will be triggered. If the deviation between the actual parameters and the initial parameters does not exceed the threshold, the initial scheduling scheme will continue to execute normally.

[0013] Among them, after generating an adjusted scheduling scheme adapted to the actual working conditions, and correcting the multi-objective optimization model based on the type and degree of parameter deviation that triggers the adjustment process, the following steps are taken: Implement the adjusted scheduling plan and provide feedback on the results.

[0014] This invention also provides a multi-objective optimization-based cascade joint dynamic scheduling system for hydropower stations, comprising a real-time dynamic data acquisition module, a multi-objective preliminary optimization module, and a dynamic adjustment and execution module for scheduling schemes; wherein: The dynamic data real-time acquisition module is used to deploy global acquisition nodes, define multi-source acquisition content, acquire real-time data from nodes, preprocess the real-time data from nodes, and obtain real-time operation and working condition data of cascade hydropower stations. The multi-objective preliminary optimization module is used to determine decision variables and boundary conditions, construct a multi-objective optimization model, set population size and iteration number parameters, and generate the optimal solution in the non-dominated solution set as the initial scheduling scheme. The scheduling scheme dynamic adjustment and execution module is used to monitor the working conditions in real time, determine parameter deviations, obtain an adjusted scheduling scheme adapted to the actual working conditions, and execute feedback.

[0015] This invention discloses a multi-objective optimization-based dynamic scheduling method and system for cascade hydropower stations, comprising the following steps using a real-time dynamic data acquisition module, a multi-objective preliminary optimization module, and a dynamic adjustment and execution module for scheduling schemes: deploying global acquisition nodes and defining multi-source acquisition content; acquiring real-time data from the nodes; preprocessing the real-time data to obtain real-time operation and condition data of the cascade hydropower stations; determining decision variables and boundary conditions; constructing a multi-objective optimization model; setting parameters such as population size and iteration number; generating the optimal solution in the non-dominated solution set as the initial scheduling scheme; monitoring operating conditions in real time; judging parameter deviations; obtaining an adjusted scheduling scheme adapted to the actual operating conditions; and executing feedback. Through the above methods, real-time monitoring of operating condition changes and parameter deviation judgment are achieved, improving the adaptability of the scheduling scheme. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of the steps of the multi-objective optimization-based hydropower station cascade joint dynamic scheduling method of the present invention.

[0018] Figure 2 This is a flowchart of steps S100 of the present invention.

[0019] Figure 3 This is a flowchart of steps S200 of the present invention.

[0020] Figure 4 This is a flowchart of steps S300 of the present invention.

[0021] Figure 5 This is a schematic diagram of the structural principle of the multi-objective optimization-based cascade joint dynamic dispatching system for hydropower stations according to the present invention.

[0022] Figure 6 This is a schematic diagram of the electronic device of the present invention.

[0023] 401 - Real-time dynamic data acquisition module; 402 - Preliminary multi-objective optimization module; 403 - Dynamic adjustment and execution of scheduling scheme module. Detailed Implementation

[0024] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0025] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0026] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0027] Please see Figures 1-4 This invention provides a multi-objective optimization-based method for joint dynamic scheduling of hydropower station cascades, comprising the following steps: S100: Deploy global data acquisition nodes, define multi-source acquisition content, acquire real-time data from nodes, preprocess the real-time data from nodes, and obtain real-time operation and working condition data of cascade hydropower stations.

[0028] In this embodiment, global data acquisition nodes are deployed, and the content to be acquired from multiple sources is defined. Real-time data from these nodes is collected and preprocessed to obtain real-time operation and status data of the cascade hydropower stations. The specific process is as follows: S101: Plan the layout of data collection nodes for the entire cascade hydropower station area and build a full-chain data collection node network; the data collection nodes include the reservoir inlets and outlets, dam monitoring sections, and key hydrological stations in the basin to deploy flow and water level monitoring terminals. S102: Define the scope of multi-source data collection, and define four core categories of data collection content: hydrological dynamic data, unit operation data, power grid load data, and meteorological early warning data. Among them, hydrological dynamic data includes real-time inflow, outflow, water level and basin rainfall of each reservoir; unit operation data includes real-time output, power generation flow and equipment operating status of each unit; power grid load data includes real-time power load demand and peak-valley electricity price period division; and meteorological early warning data includes short-term heavy rainfall and typhoon extreme weather forecast information. S103: Trigger a real-time data acquisition request for the node, set the data acquisition frequency, and acquire real-time data from the node; S104: Preprocess the real-time data of the nodes, use noise reduction to eliminate interference signals during data transmission, remove abnormal data by judging outliers, and standardize the collected data of different formats into a unified data format; S105: Verify data integrity, generate real-time operation and status data of cascade hydropower stations, and output the data.

[0029] In the aforementioned process, a comprehensive data collection node layout for the cascade hydropower stations was planned. Combining the basin's topography, hydrological characteristics, and cascade operation requirements, a full-chain data collection node network was established, encompassing the basin, reservoirs, generating units, and the power grid. Specifically, high-precision flow and water level monitoring terminals were deployed at the inlets (including major tributary confluences), outlets, upstream and downstream monitoring sections of the dam, and key hydrological stations in the basin (including runoff monitoring stations during the dry season). Ultrasonic radar flowmeters (measurement accuracy ±1%) and submersible water level gauges (measurement accuracy ±0.01m) were used to ensure accurate collection of key hydrological data. Simultaneously, output monitoring modules were deployed in the control cabinets of each hydropower station generating unit, load data acquisition terminals were deployed at the power grid dispatch interface, and meteorological early warning data receiving modules were connected to meteorological stations in the basin. This achieved comprehensive coverage of multi-dimensional data collection nodes, eliminating blind spots in data collection.

[0030] The scope of multi-source data collection is divided into four core categories: hydrological dynamic data, unit operation data, power grid load data, and meteorological early warning data. Among them, hydrological dynamic data includes real-time inflow, outflow, water level and rainfall in the basin of each reservoir; unit operation data includes real-time output, power generation flow and equipment operating status of each unit; power grid load data includes real-time power load demand and peak-valley electricity price period division; and meteorological early warning data includes short-term heavy rainfall and typhoon extreme weather forecast information.

[0031] The system triggers real-time data acquisition requests, setting differentiated acquisition frequencies based on the timeliness requirements of different data types: flow and water level data are acquired at a high frequency of 10 seconds per acquisition to ensure the capture of sudden flow changes caused by floods; unit output data is acquired at a frequency of 30 seconds per acquisition to balance data real-time performance and transmission pressure; grid load data is synchronized in real-time with the grid dispatch center data (updated every minute); meteorological early warning data is accessed through the meteorological department's real-time early warning system to ensure that the reception delay of extreme weather information (such as typhoons and short-term heavy rainfall) does not exceed 30 seconds; and various real-time data are transmitted to the dispatch center data processing platform through a 5G industrial private network (transmission rate ≥100Mbps) to ensure the stability and timeliness of data transmission.

[0032] The real-time node data undergoes standardized preprocessing using a three-step process: noise reduction, outlier removal, and format standardization, to ensure data quality. The first step involves dual-algorithm collaborative noise reduction. To address electromagnetic interference (low-frequency noise) and high-frequency noise caused by signal attenuation during data transmission, a Kalman filter algorithm is first used for noise reduction. The state equation is set as follows: X(k)=A·X(k-1)+B·u(k)+w(k); The observation equation is: Z(k) = H·X(k) + v(k); Where A is the state transition matrix, B is the control matrix, H is the observation matrix, and w(k) and v(k) are the process noise and observation noise, respectively (both set as Gaussian white noise with variances of 0.01 and 0.02, respectively), to achieve accurate filtering of low-frequency noise; Then, a second denoising process is performed using wavelet analysis algorithm. The db4 wavelet basis is selected, and the number of decomposition layers is set to 3. The high-frequency coefficients after decomposition are processed by a soft thresholding function w'=sign(w)(|w|-λ) (λ is the threshold value of 0.05) to filter high-frequency noise, and finally a smooth original data sequence is obtained.

[0033] The second step involves outlier removal based on the 3σ criterion. First, the mean μ and standard deviation σ of each data sequence (e.g., flow rate, water level) are calculated. The outlier determination interval is set as [μ-3σ, μ+3σ]. If a data point exceeds this interval, it is considered an outlier. Simultaneously, historical operating data from cascade hydropower stations are used to establish empirical thresholds for verification. For example, if the flow rate exceeds 1.5 times the historical maximum flow rate for the same period or is less than 0.5 times the historical minimum flow rate for the same period, it is considered an outlier even if it is within the 3σ interval. After manual verification, outliers are removed, and missing values ​​are filled in using linear interpolation with normal data from adjacent time points. The third step involves format and unit standardization. JSON format is adopted as the unified data exchange format. A standardized data structure is defined, containing six core fields: "collection timestamp, collection node ID, data type, data value, unit, and checksum." Units from different data sources are uniformly converted; for example, the flow rate unit is standardized to m. 3 / s (The L / s unit for some stations is set to 1m) 3 / s=1000L / s conversion), water level unit is unified to m (the cm unit of some stations is converted to 1m=100cm), power unit is unified to MW (the kW unit of some units is converted to 1MW=1000kW) to ensure the consistency of data format and units, which is convenient for subsequent model calls.

[0034] Verify data integrity, generate real-time operation and status data for cascade hydropower stations, and output the data.

[0035] S200: Determine the decision variables and boundary conditions, construct a multi-objective optimization model, set the population size and iteration number parameters, and generate the optimal solution in the non-dominated solution set as the initial scheduling scheme.

[0036] In this implementation, decision variables and boundary conditions are determined, a multi-objective optimization model is constructed, and parameters such as population size and iteration count are set to generate the optimal solution in the non-dominated solution set as the initial scheduling scheme. The specific process is as follows: S201: Determine the decision variables and boundary conditions for multi-objective optimization, with the power generation flow and outflow of each hydropower station at different times as the core decision variables, and set boundary conditions in combination with cascade operation; among which the boundary conditions include the upper and lower limits of reservoir capacity, the upper and lower limits of unit output, the minimum ecological base flow outflow limit, and the reservoir flood control limit water level constraint. S202: Taking the maximization of power generation efficiency, flood control safety, and ecological base flow as the core optimization objectives, a multi-objective optimization model is established by integrating decision variables and boundary conditions to balance the needs of multiple objectives. S203: Obtain real-time operation and working condition data of cascade hydropower stations, optimize and filter each decision variable through algorithm iteration calculation, generate a non-dominated solution set containing multiple feasible schemes, and select an initial scheduling scheme.

[0037] In the above process, decision variables and dynamic boundary conditions for multi-objective optimization are determined. The generation flow and outflow of each hydropower station at different time periods (the scheduling period is divided into 1-hour units) are used as the core decision variables. Boundary conditions are dynamically set in combination with the seasonal characteristics of cascade operation and hydrological conditions. The specific boundary conditions include: upper and lower limits of reservoir capacity (the lower limit of reservoir capacity during the dry season is higher than that during the flood season to ensure emergency water supply capacity), upper and lower limits of unit output (dynamically adjusted according to the operating years of the units and maintenance plans, with the upper limit of output of old units reduced by 5% to 10%), minimum ecological base flow outflow limit (the ecological base flow during the fish breeding season is increased by 20% to 30% compared with the dry season), and reservoir flood control limit water level constraint (the flood control limit water level is strictly implemented during the flood season, and the water level can be appropriately increased according to the inflow situation during the non-flood season, but not exceeding 80% of the check flood level).

[0038] With maximizing power generation efficiency, ensuring flood control safety, and guaranteeing ecological base flow as the core optimization objectives, a multi-objective optimization model that balances multiple objectives is established by integrating decision variables and boundary conditions.

[0039] The initial scheduling scheme is generated through a complete process of real-time data import, improved NSGA-Ⅲ algorithm solution, and analytic hierarchy process (AHP) optimization. The first step is real-time data import and parameter mapping. The real-time operation and working condition data of the cascade hydropower stations output in step S105 are classified and mapped according to data type. Among them, hydrological dynamic data (inflow and reservoir water level) are mapped to the inflow parameters of the model, unit operation data (current output and equipment status) are mapped to the initial operation parameters of the model, grid load data (real-time load and peak-valley electricity price) are mapped to the constraint and target parameters of the model, and meteorological warning data (probability of short-term heavy rainfall) are mapped to the risk weight parameters of the model, so as to ensure accurate matching between input data and model parameters.

[0040] The second step involves improving the NSGA-Ⅲ algorithm to solve the multi-objective optimization model. The core improvement lies in introducing an adaptive crossover and mutation probability and an elite preservation strategy: the population size is set to 120, the maximum number of iterations is 60, and the crossover probability adopts an adaptive adjustment mechanism, i.e., Pc = 0.9 - 0.3 * (gen / gen) max (gen is the current iteration number, gen) max (To maximize the number of iterations), a higher crossover probability (0.9) is used in the early stages of iteration to ensure population diversity, and the crossover probability is reduced (0.6) in the later stages of iteration to improve the convergence speed; Mutation probability Pm = 0.05 + 0.05 * (gen / gen) max In the later stages of iteration, the mutation probability is increased to avoid the algorithm getting trapped in local optima. The elite retention strategy is to retain the top 20% of the excellent individuals in the non-dominated solution set after each iteration and directly enter the next generation population. The remaining individuals are selected from the parents and offspring through a roulette wheel selection method. During the algorithm iteration process, the three objective function values ​​(power generation efficiency, flood control safety, and ecological base flow satisfaction) of each individual are calculated first. Then, the non-dominated sorting is performed to divide the dominance level. The crowding distance of each individual is calculated (using Euclidean distance). Finally, after the maximum number of iterations, a non-dominated solution set containing 30 feasible solutions is output.

[0041] The third step involves using the Analytic Hierarchy Process (AHP) to select the optimal solution and construct a three-layer evaluation system: the objective layer is the overall optimal initial scheduling scheme; the criteria layer includes the achievement rate of power generation benefits (weight 0.4), the flood control safety guarantee rate (weight 0.35), and the ecological base flow satisfaction rate (weight 0.25); and the scheme layer consists of 30 feasible schemes in the non-dominated solution set. A judgment matrix is ​​constructed using the 1-9 scaling method, the overall weight of each scheme is calculated, and the scheme with the highest overall weight is selected as the initial scheduling scheme. At the same time, the values ​​of each decision variable of the scheme (power generation flow and outflow flow in each time period) and the objective function value are output, forming a standardized initial scheduling scheme document.

[0042] S300: Monitors operating conditions in real time, determines parameter deviations, obtains an adjusted scheduling plan adapted to the actual operating conditions, and executes feedback.

[0043] In this embodiment, the operating conditions are monitored in real time, parameter deviations are determined, an adjusted scheduling plan adapted to the actual operating conditions is obtained, and feedback is executed. The specific process is as follows: S301: Continuously receives real-time operation and status data of cascade hydropower stations, and monitors key parameters such as actual inflow, water level, actual output of generating units, and real-time load demand of the power grid for each reservoir. S302: Perform parameter deviation judgment, set deviation thresholds for each key parameter, and compare the actual parameters monitored in real time with the initial parameters of the initial scheduling plan; if the deviation between the actual parameters and the initial parameters exceeds the set threshold, the scheduling plan adjustment process is triggered; if the deviation between the actual parameters and the initial parameters does not exceed the threshold, the initial scheduling plan is maintained to execute normally. S303: Generate an adjusted scheduling scheme adapted to the actual working conditions. Based on the type and degree of parameter deviation that triggers the adjustment process, correct the multi-objective optimization model and generate an adjusted scheduling scheme adapted to the current actual working conditions. S304: Execute the adjusted scheduling plan and report the results.

[0044] During the above process, real-time operation and working condition data of cascade hydropower stations are continuously received, and key parameters such as actual inflow, water level, actual output of generating units, and real-time load demand of the power grid are monitored for each reservoir.

[0045] Parameter deviations are assessed, and differentiated deviation thresholds are set based on the operational stability requirements of cascade hydropower stations: the inflow deviation threshold is set at ±10%, the reservoir water level deviation threshold is set at ±0.5m, the unit output deviation threshold is set at ±8%, and the grid load demand deviation threshold is set at ±10%. The real-time monitored parameters are automatically compared with the initial parameters of the initial dispatch plan through the dispatch center's data processing module to calculate the deviation value. If the deviation value of any key parameter exceeds the corresponding threshold, the dispatch plan adjustment process is automatically triggered. If the deviation values ​​of all key parameters do not exceed the threshold, the initial dispatch plan is maintained and the changes in operating conditions are continuously monitored.

[0046] Generate an adjusted scheduling scheme adapted to the actual working conditions. Based on the type and degree of parameter deviation that triggers the adjustment process, correct the input parameters of the multi-objective optimization model, rerun the optimization algorithm to solve the model, and generate an adjusted scheduling scheme that can adapt to the current actual working conditions. During the adjustment process, priority is given to ensuring flood control safety and ecological base flow objectives.

[0047] The adjusted scheduling plan is executed and the results are fed back. The adjusted scheduling plan is sent to the execution agencies of each hydropower station through the remote control interface to drive the unit output adjustment, floodgate operation and other operations. At the same time, the actual operation data after the plan is executed is collected in real time and fed back to the dispatch center to provide data support for the next round of scheduling optimization.

[0048] Corresponding to the aforementioned embodiments of the hydropower station cascade joint dynamic scheduling method based on multi-objective optimization, this application also provides embodiments of a hydropower station cascade joint dynamic scheduling system based on multi-objective optimization.

[0049] Figure 5 This is a block diagram of a multi-objective optimization-based cascade joint dynamic dispatching system for hydropower stations, illustrated according to an exemplary embodiment. (Refer to...) Figure 5 The system may include: a dynamic data real-time acquisition module 401, a multi-objective preliminary optimization module 402, and a scheduling scheme dynamic adjustment and execution module 403; wherein: The dynamic data real-time acquisition module 401 is used to deploy global acquisition nodes, define multi-source acquisition content, acquire real-time data from nodes, preprocess the real-time data from nodes, and obtain real-time operation and working condition data of cascade hydropower stations. The multi-objective preliminary optimization module 402 is used to determine decision variables and boundary conditions, construct a multi-objective optimization model, set population size and iteration number parameters, and generate the optimal solution in the non-dominated solution set as the initial scheduling scheme. The scheduling scheme dynamic adjustment and execution module 403 is used to monitor the working conditions in real time, determine parameter deviations, obtain an adjusted scheduling scheme adapted to the actual working conditions, and execute feedback.

[0050] In this embodiment, the dynamic data real-time acquisition module 401 deploys global acquisition nodes, defines multi-source acquisition content, acquires real-time data from the nodes, preprocesses the real-time data, and obtains real-time operation and working condition data of the cascade hydropower station; the multi-objective preliminary optimization module 402 determines decision variables and boundary conditions, constructs a multi-objective optimization model, sets parameters such as population size and iteration number, and generates the optimal solution in the non-dominated solution set as the initial scheduling scheme; the scheduling scheme dynamic adjustment and execution module 403 monitors the working conditions in real time, judges parameter deviations, obtains an adjusted scheduling scheme adapted to the actual working conditions, and executes feedback; through the above methods, real-time monitoring of changes in working conditions and judgment of parameter deviations are achieved, improving the adaptability of the scheduling scheme.

[0051] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0052] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0053] Accordingly, this application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; and, when the one or more programs are executed by the one or more processors, causing the one or more processors to implement the above-described multi-objective optimization-based cascade joint dynamic scheduling method for hydropower stations. Figure 6 The diagram shown is a hardware structure diagram of any device with data processing capabilities in a multi-objective optimization-based cascade joint dynamic dispatching system for hydropower stations, as provided in an embodiment of the present invention. (Except for...) Figure 6 In addition to the processor, memory, and network interface shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.

[0054] Accordingly, this application also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the multi-objective optimization-based cascade joint dynamic scheduling method for hydropower stations described above. The computer-readable storage medium can be an internal storage unit of any data processing-capable device as described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any data processing-capable device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the data processing-capable device, and can also be used to temporarily store data that has been output or will be output.

[0055] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0056] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A multi-objective optimization-based method for joint dynamic scheduling of hydropower station cascades, characterized in that, Includes the following steps: Deploy data collection nodes across the entire region, define the content to be collected from multiple sources, collect real-time data from the nodes, preprocess the real-time data from the nodes, and obtain real-time operation and working condition data of the cascade hydropower stations. Determine the decision variables and boundary conditions, construct a multi-objective optimization model, set the population size and iteration number parameters, and generate the optimal solution in the non-dominated solution set as the initial scheduling scheme; Real-time monitoring of operating conditions, determination of parameter deviations, obtaining an adjusted scheduling plan adapted to the actual operating conditions, and execution feedback.

2. The multi-objective optimization-based cascade joint dynamic scheduling method for hydropower stations as described in claim 1, characterized in that, In the steps of deploying global data acquisition nodes, defining multi-source acquisition content, acquiring real-time data from the nodes, and preprocessing the real-time data to obtain real-time operation and condition data of the cascade hydropower station: The plan outlines the layout of data collection nodes across the entire cascade hydropower station area, establishing a full-chain data collection node network. These nodes include the inlet and outlet of each reservoir, dam monitoring sections, and key hydrological stations in the basin, where flow and water level monitoring terminals are deployed. The scope of multi-source data collection is divided into four core categories: hydrological dynamic data, unit operation data, power grid load data, and meteorological early warning data. Among them, hydrological dynamic data includes real-time inflow, outflow, water level and basin rainfall of each reservoir; unit operation data includes real-time output, power generation flow and equipment operating status of each unit; power grid load data includes real-time power load demand and peak-valley electricity price period division; and meteorological early warning data includes short-term heavy rainfall and typhoon extreme weather forecast information. Trigger a real-time data acquisition request for the node, set the data acquisition frequency, and obtain real-time data from the node.

3. The multi-objective optimization-based cascade joint dynamic scheduling method for hydropower stations as described in claim 2, characterized in that, After triggering the node's real-time data acquisition request, setting the data acquisition frequency, and obtaining the node's real-time data: The real-time data of the nodes is preprocessed, noise reduction is used to eliminate interference signals during data transmission, outlier data is removed by outlier detection, and the collected data of different formats are standardized into a unified data format.

4. The multi-objective optimization-based cascade joint dynamic scheduling method for hydropower stations as described in claim 3, characterized in that, After preprocessing the real-time node data, using noise reduction methods to eliminate interference signals during data transmission, removing outlier data through outlier detection, and standardizing the collected data of different formats into a unified data format: Verify data integrity, generate real-time operation and status data for cascade hydropower stations, and output the data.

5. The multi-objective optimization-based cascade joint dynamic scheduling method for hydropower stations as described in claim 1, characterized in that, In the steps of determining decision variables and boundary conditions, constructing a multi-objective optimization model, setting population size and iteration number parameters, and generating the optimal solution in the non-dominated solution set as the initial scheduling scheme: The decision variables and boundary conditions for multi-objective optimization are determined, with the power generation flow and outflow of each hydropower station at different times as the core decision variables, and the boundary conditions are set in combination with the cascade operation. The boundary conditions include the upper and lower limits of reservoir capacity, the upper and lower limits of unit output, the minimum ecological base flow outflow limit, and the reservoir flood control limit water level constraint. Establish a multi-objective optimization model that balances multiple objective requirements; The system acquires real-time operation and status data of cascade hydropower stations, optimizes and filters each decision variable through algorithmic iteration, generates a non-dominated solution set containing multiple feasible schemes, and selects an initial scheduling scheme.

6. The multi-objective optimization-based cascade joint dynamic scheduling method for hydropower stations as described in claim 5, characterized in that, In the steps of establishing a multi-objective optimization model that balances multiple objective requirements: With the core optimization objectives of maximizing power generation efficiency, ensuring flood control safety, and guaranteeing ecological base flow, decision variables and boundary conditions are integrated.

7. The cascade joint dynamic scheduling method for hydropower stations based on multi-objective optimization as described in claim 1, characterized in that, In the steps of real-time monitoring of operating conditions, determining parameter deviations, obtaining an adjusted scheduling plan adapted to actual operating conditions, and executing feedback: Continuously receive real-time operation and status data of cascade hydropower stations, and monitor key parameters such as actual inflow, water level, actual output of generating units, and real-time load demand of the power grid for each reservoir. Perform parameter deviation judgment, set deviation thresholds for each key parameter, and compare the actual parameters monitored in real time with the initial parameters of the initial scheduling scheme; Generate an adjusted scheduling scheme adapted to the actual working conditions. Based on the type and degree of parameter deviation that triggers the adjustment process, modify the multi-objective optimization model to generate an adjusted scheduling scheme adapted to the current actual working conditions.

8. The cascade joint dynamic scheduling method for hydropower stations based on multi-objective optimization as described in claim 7, characterized in that, In the steps of judging parameter deviations, setting deviation thresholds for each key parameter, and comparing the actual parameters monitored in real time with the initial parameters of the initial scheduling scheme: If the deviation between the actual parameters and the initial parameters exceeds the set threshold, the scheduling scheme adjustment process will be triggered. If the deviation between the actual parameters and the initial parameters does not exceed the threshold, the initial scheduling scheme will continue to execute normally.

9. The multi-objective optimization-based cascade joint dynamic scheduling method for hydropower stations as described in claim 7, characterized in that, After generating an adjusted scheduling scheme adapted to the actual working conditions, and correcting the multi-objective optimization model based on the type and degree of parameter deviations that trigger the adjustment process, the following steps are taken: Implement the adjusted scheduling plan and provide feedback on the results.

10. A multi-objective optimization-based cascade joint dynamic scheduling system for hydropower stations, employing the multi-objective optimization-based cascade joint dynamic scheduling method for hydropower stations as described in claim 1, characterized in that... It includes a dynamic data real-time acquisition module, a multi-objective preliminary optimization module, and a scheduling scheme dynamic adjustment and execution module; among which: The dynamic data real-time acquisition module is used to deploy global acquisition nodes, define multi-source acquisition content, acquire real-time data from nodes, preprocess the real-time data from nodes, and obtain real-time operation and working condition data of cascade hydropower stations. The multi-objective preliminary optimization module is used to determine decision variables and boundary conditions, construct a multi-objective optimization model, set population size and iteration number parameters, and generate the optimal solution in the non-dominated solution set as the initial scheduling scheme. The scheduling scheme dynamic adjustment and execution module is used to monitor the working conditions in real time, determine parameter deviations, obtain an adjusted scheduling scheme adapted to the actual working conditions, and execute feedback.

Images