Multi-target transaction strategy and system for water-wind-light power generation based on improved hybrid algorithm

Abstract

The invention is suitable for the technical field of electric power transaction, and provides a multi-target transaction strategy and system for water-wind-light power generation based on an improved hybrid algorithm, and the strategy comprises the following steps: collecting system parameters of a hydropower station, a photovoltaic power station, a wind power station and a pumped storage power station, and determining boundary values of constraint conditions; constructing a multi-objective optimization scheduling model, wherein the multi-objective optimization scheduling model comprises an objective function and a constraint condition; an improved fast non-dominated genetic algorithm and a time-varying multi-objective particle swarm optimization algorithm are adopted, and global optimization is carried out on the multi-objective optimization scheduling model through a double-population strategy; and displaying an optimization result at a client through a graphical interface, wherein the optimization result comprises the power generation plan of each power station, the change of the reservoir capacity and the economic benefit of the system. By combining the genetic algorithm of fast non-dominated sorting and the time-varying multi-objective particle swarm optimization algorithm, global optimization is carried out by adopting a double-population strategy, the advantages of the two algorithms are effectively combined, and the search efficiency is improved by dynamically adjusting the strategy and parameters.

Description

Technical Field

[0001] The present invention relates to the technical field of power trading, and in particular, to a multi-objective trading strategy and system for hydropower, wind power and photovoltaic power generation based on an improved hybrid algorithm. Background Technique

[0002] With the continuous increase in the penetration rate of renewable energy in the power system, how to efficiently integrate and utilize non-carbon resources such as small hydropower stations, photovoltaic power generation stations, and wind power generation stations, and at the same time optimize their scheduling strategies, has become a key challenge to ensure the stable operation of the power grid and improve energy utilization efficiency. The output of these renewable energy power generation systems is significantly affected by natural conditions and has high intermittency and uncertainty, which undoubtedly increases the complexity and risk of power grid scheduling. In response to this problem, it is particularly important to develop new optimization scheduling strategies with strong adaptability and high flexibility, especially to pay attention to the effective utilization of clean energy in small and medium-sized river basins, especially the optimal management of small cascaded hydropower stations (SCHPs). For small cascaded hydropower stations, although the regulation ability of a single power station is limited, more flexible scheduling can be achieved by comprehensively using the water storage and discharge capabilities of multiple cascaded power stations. This requires the establishment of an accurate hydrological prediction model, combined with real-time weather data and reservoir status, to dynamically adjust the operation strategies of each power station to achieve optimal water resource allocation and power output. In addition, the use of advanced control algorithms and artificial intelligence technologies, such as machine learning and deep learning, can further improve the intelligence level of scheduling decisions and enhance the adaptability to natural changes. To overcome the instability of wind power and photovoltaic power generation, integrating energy storage devices, especially pumped storage power stations (PS), into a multi-energy complementary power system (MECPG) is an effective way to improve the overall reliability and economy of the system. Pumped storage power stations can not only pump and store energy using excess electricity during low power demand periods, but also discharge water for power generation during peak periods, effectively balancing supply and demand fluctuations. For small cascaded hydropower stations, coordinated scheduling with pumped storage power stations can further optimize water resource utilization and enhance the power grid's ability to absorb renewable energy fluctuations. Constructing an intelligent microgrid to integrate distributed energy sources such as small hydropower stations, photovoltaics, wind power, and energy storage devices into unified management, and realizing efficient configuration and scheduling of energy through a distributed energy management system (DEMS). The DEMS can real-time monitor the status of each energy point, and based on advanced prediction algorithms and optimization strategies, automatically adjust energy production and consumption to ensure the balance of supply and demand within the microgrid, while promoting the local consumption of excess energy or transmission to the large power grid, improving energy utilization efficiency.

[0003] To improve the complementary operation efficiency and conduct multi-objective optimization, the existing technology will optimize based on the particle swarm optimization algorithm. The application of PSO in the power system dispatch optimization, especially when considering multiple objectives (such as cost minimization, pollution minimization, system stability maximization, etc.), can effectively search the solution space and find the optimal solution that meets multiple objectives. However, the particle swarm optimization algorithm is prone to premature convergence when solving complex problems, that is, the algorithm may converge to the local optimal solution rather than the global optimal solution prematurely; in multi-objective optimization problems, maintaining the diversity of solutions is very important to ensure finding more non-dominated solutions. After a long time of iteration in the PSO algorithm, the diversity of the particle swarm may decrease; when facing optimization problems with complex structures and many constraints, the standard PSO algorithm may be difficult to handle effectively.

[0004] Therefore, it is necessary to provide a multi-objective trading strategy and system for water, wind, and solar power generation based on an improved hybrid algorithm, aiming to solve the above problems. Summary of the Invention

[0005] Aiming at the deficiencies of the existing technology, the purpose of the present invention is to provide a multi-objective trading strategy and system for water, wind, and solar power generation based on an improved hybrid algorithm to solve the problems in the above background technology.

[0006] The present invention is implemented as follows. A multi-objective trading strategy for water, wind, and solar power generation based on an improved hybrid algorithm, the strategy includes the following steps:

[0007] Collect the system parameters of hydropower stations, photovoltaic power, wind power, and pumped-storage power stations, and determine the boundary values of the constraint conditions;

[0008] Construct a multi-objective optimal scheduling model, the multi-objective optimal scheduling model includes an objective function and constraint conditions;

[0009] Adopt an improved fast non-dominated genetic algorithm and a time-varying multi-objective particle swarm optimization algorithm to globally optimize the multi-objective optimal scheduling model through a dual-population strategy;

[0010] Display the optimization results on the client through a graphical interface, and the optimization results include the power generation plans of each power station, the changes in reservoir capacity, and the economic benefits of the system.

[0011] As a further solution of the present invention: when globally optimizing the multi-objective optimal scheduling model through the dual-population strategy, the initial population is divided into two parts, and they are respectively optimized according to the improved MOPSO and NSGA3 algorithms. The population is updated by comparing and selecting non-dominated solutions, and finally the optimal solution set is obtained. The specific steps include: population initialization, randomly dividing the initial population into two sub-populations and respectively assigning them to the NSGA3 and MOPSO algorithms; independent optimization, each sub-population performs independent optimization under its respective algorithm framework. The NSGA3 sub-population maintains the diversity and convergence of solutions through fast non-dominated sorting and crowding degree calculation, and the MOPSO sub-population enhances the global search ability through time-varying inertia weight and dynamic adjustment strategy; information exchange, after each generation of optimization is completed, information exchange is carried out between the two sub-populations; population update, by comparing and selecting non-dominated solutions, the individuals of the two sub-populations are updated; iterative optimization, repeating the above steps until the termination condition is met to obtain the final solution set.

[0012] As a further solution of the present invention: the objective functions include the daily total water consumption of the power station, the daily economic benefit, and the standard deviation of the remaining load.

[0013] As a further solution of the present invention: the function of the daily total water consumption is: The function of the daily economic benefit is:

[0014] The function of the standard deviation of the remaining load is: k1 to k6 are respectively the electricity prices corresponding to the output.

[0015] As a further solution of the present invention: the constraint conditions include: wind power output constraint: In the formula, P t min , P t max are respectively the maximum and minimum outputs of wind turbine i; j is 0 or 1, indicating whether the unit operates independently or jointly; photovoltaic output constraint: In the formula, P i,min , P i,max are respectively the maximum and minimum outputs of photovoltaic unit i; j is 0 or 1, indicating whether the unit operates independently or jointly; generating head constraint: In the formula, Zt is the water level of the hydropower station at the t-th time period, is the tail water level of the hydropower station at the t-th time period, is the head loss of the hydropower station at the t-th time period, which can be expressed as a linear function of the generating flow rate: In the formula, a and b are both constants; water balance constraint: In the formula, V t is the reservoir storage at the beginning of the t-th time period, is the reservoir inflow during period t, is the reservoir spillage flow during period t; Reservoir water storage constraint: V t min ≤V t ≤V t max , where V t min and V t max are the minimum and maximum water storages of the reservoir during period t respectively; Reservoir operating water level constraint: In the formula, are the minimum and maximum values of the reservoir operating water level during period t respectively; Power generation flow constraint: In the formula, are the minimum and maximum values of the reservoir discharge flow during period t respectively; Outflow constraint: In the formula, is the maximum value of the reservoir discharge flow during period t; Hydropower station output constraint: P i min ≤AQ t H t ≤P i max In the formula, P i min and P i max are the minimum and maximum values of the output of hydropower station unit i respectively, and A is the output coefficient of the hydropower station.

[0016] Another object of the present invention is to provide a multi-objective trading system for water-wind-solar power generation based on an improved hybrid algorithm, and the system includes:

[0017] A data acquisition hardware module, which is used to collect system parameters of hydropower stations, photovoltaic power, wind power and pumped storage power stations, and determine the boundary values of constraint conditions;

[0018] A scheduling model construction module, which is used to construct a multi-objective optimal scheduling model, and the multi-objective optimal scheduling model includes an objective function and constraint conditions;

[0019] A scheduling model optimization module, which is used to adopt an improved fast non-dominated genetic algorithm and a time-varying multi-objective particle swarm optimization algorithm to globally optimize the multi-objective optimal scheduling model through a dual-population strategy;

[0020] An optimization result display module, which is used to display the optimization results on the client through a graphical interface, and the optimization results include the power generation plans of each power station, the changes in reservoir capacity and the economic benefits of the system.

[0021] As a further solution of the present invention: The system includes a data processing server, a computing optimization server, and an application server. The data processing server is responsible for collecting and preprocessing data; the computing optimization server is used to execute an improved hybrid intelligent algorithm for optimization calculation; the application server processes user requests, invokes the optimization model, and feeds back the results to the client.

[0022] As a further solution of the present invention: The data acquisition hardware module includes monitoring devices and sensors in the power station, which are used to monitor the power generation, water level, and environmental conditions in real time.

[0023] Compared with the prior art, the beneficial effects of the present invention are:

[0024] By combining the genetic algorithm based on fast non-dominated sorting (NSGA3) and the time-varying multi-objective particle swarm optimization (MOPSO) algorithm, and adopting a dual-population strategy for global optimization, the present invention can effectively combine the advantages of the two algorithms, and improve the search efficiency by dynamically adjusting the strategy and parameters. In addition, in order to improve the global search ability and the diversity of solutions of the algorithm, the present invention adopts a dual-population strategy, divides the initial population into two parts, optimizes them respectively according to the improved MOPSO and NSGA3 algorithms, then updates the population by comparing and selecting non-dominated solutions, and finally obtains a high-quality solution set. Description of the Drawings

[0025] Figure 1 It is a flowchart of a multi-objective trading strategy for water, wind, and photovoltaic power generation based on an improved hybrid algorithm.

[0026] Figure 2 It is a schematic structural diagram of a multi-objective trading system for water, wind, and photovoltaic power generation based on an improved hybrid algorithm.

[0027] Figure 3 It is a flowchart of globally optimizing a multi-objective optimal scheduling model through a dual-population strategy. Detailed Embodiments

[0028] In order to make the objectives, technical solutions, and advantages of the present invention clearer, the following further details the present invention in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0029] The following details the specific implementation of the present invention in conjunction with specific embodiments.

[0030] As Figure 1 shown, an embodiment of the present invention provides a multi-objective trading strategy for water, wind, and photovoltaic power generation based on an improved hybrid algorithm. The strategy includes the following steps:

[0031] S100, Collect the system parameters of hydropower stations, photovoltaics, wind power, and pumped-storage power stations, and determine the boundary values of the constraint conditions;

[0032] S200, Construct a multi-objective optimal scheduling model, where the multi-objective optimal scheduling model includes an objective function and constraint conditions;

[0033] S300, Use an improved fast non-dominated genetic algorithm and a time-varying multi-objective particle swarm optimization algorithm to globally optimize the multi-objective optimal scheduling model through a dual-population strategy;

[0034] S400, Display the optimization results on the client through a graphical interface, where the optimization results include the power generation plans of each power station, the changes in reservoir capacity, and the economic benefits of the system.

[0035] It should be noted that the embodiment of the present invention combines the advantages of the NSGA3 (fast non-dominated genetic) algorithm and the MOPSO (time-varying multi-objective particle swarm optimization) algorithm, and proposes an improved hybrid intelligent algorithm to solve the multi-objective optimal scheduling problem of a small hydropower-photovoltaic-wind power-pumped-storage power generation system. By coordinating the energy storage advantages of SCHPs and PSs and the characteristics of wind power and photovoltaics being vulnerable to nature, the grid-connected operation mode of the system is determined, and considering various operation constraint conditions, a scheduling model is established. Using the improved hybrid intelligent algorithm, the superiority of the algorithm and the applicability of the system are verified.

[0036] It should be noted that the technical solution of Particle Swarm Optimization (PSO) is mainly based on a heuristic algorithm that simulates the foraging behavior of bird flocks and is used to solve optimization problems. Specifically, in the application scenarios of the existing technology, PSO is used for multi-objective optimization problems, including but not limited to the scheduling optimization of power systems. In the scheduling optimization of power systems, PSO searches for the optimal or near-optimal solution by simulating the flight of particles (solutions) in the solution space and updating the particle positions based on the individual historical best positions and the global historical best positions. The key steps of the existing technology (PSO) include: 1. Initialization: Randomly initialize the positions and velocities of a group of particles. Each particle represents a potential solution. 2. Evaluation: Calculate the fitness value of each particle, that is, evaluate the quality of each solution according to the objective function of the optimization problem. 3. Update individual historical best: For each particle, if the fitness value of the current position is better than its historical best position, update its historical best position to the current position. 4. Update global historical best: If the fitness value of the current position of any particle is better than the global historical best position, update the global historical best position. 5. Update velocity and position: Update the velocity and position of each particle according to the current velocity, individual historical best position, and global historical best position. The velocity update takes into account the inertia of the particle, the individual cognitive component (the component pointing to the individual historical best position), and the social cognitive component (the component pointing to the global historical best position). 6. Iteration: Repeat steps 2 to 5 until the termination condition is met, such as reaching the maximum number of iterations or the quality of the solution reaching a preset threshold. The application of PSO in the scheduling optimization of power systems, especially when considering multiple objectives (such as cost minimization, pollution minimization, system stability maximization, etc.), can effectively search the solution space and find the optimization solution that meets multiple objectives. However, the standard PSO algorithm may face challenges such as slow convergence speed or getting trapped in local optimal solutions when dealing with complex multi-objective problems. Therefore, in practical applications, it may be necessary to improve the algorithm or combine it with other optimization techniques to improve performance.

[0037] However, the disadvantages of the Particle Swarm Optimization (PSO) technical solution in multi-objective optimization scheduling include: 1. Premature convergence problem: The Particle Swarm Optimization algorithm is prone to premature convergence when solving complex problems, that is, the algorithm may converge to a local optimal solution rather than the global optimal solution too early. This is mainly because particles rely too much on individual historical optimal positions and swarm historical optimal positions when updating their positions, resulting in limited exploration ability of the search space. 2. Diversity maintenance problem: In multi-objective optimization problems, maintaining the diversity of solutions is very important to ensure finding more non-dominated solutions. After long-term iteration of the PSO algorithm, the diversity of the particle swarm may decrease, making it difficult for the algorithm to cover the entire Pareto front. 3. Parameter adjustment difficulty: The performance of the PSO algorithm depends to a large extent on the setting of parameters such as inertia weight, cognitive and social learning factors. The optimal selection of these parameters is not only complex but also significantly sensitive to different problems, resulting in limitations in the generalization ability and adaptability of the algorithm. 4. Adaptability to complex models: When facing optimization problems with complex structures and many constraint conditions, the standard PSO algorithm may be difficult to handle effectively and needs to be improved through algorithm improvement or combined with other optimization techniques to enhance its performance. Generally speaking, although the Particle Swarm Optimization algorithm has shown good performance in many optimization problems, when dealing with multi-objective optimization problems with high complexity, the above disadvantages limit the application effect and scope. Therefore, researchers usually consider improving PSO or combining it with other algorithms to overcome these limitations in order to improve the quality of solutions and the adaptability of the algorithm.

[0038] As Figure 3 shown, in the embodiment of the present invention, it aims to solve the multi-objective optimization scheduling problem of a small hydropower - photovoltaic - wind power - pumped storage power generation system (CH-PV-Wind-PS) through an improved hybrid intelligent algorithm. It includes specific details such as the software implementation process, the interaction between the server and the client, the coding method, the multi-layer server-side distribution, and the software and hardware collaborative work process. First, data preparation is required. The system parameters of hydropower stations (SCHPs), photovoltaic (PV), wind power, and pumped storage power stations (PS) are collected, and the boundary values of the constraint conditions are determined. Then, a multi-objective optimization scheduling model is constructed on the server. The multi-objective optimization scheduling model includes an objective function and constraint conditions; the objective function includes the daily total water consumption of the power station, the daily economic benefit, and the standard deviation of the remaining load. When globally optimizing the multi-objective optimization scheduling model through a double-population strategy, the initial population is divided into two parts, and they are optimized respectively according to the improved MOPSO and NSGA3 algorithms. The population is updated by comparing and selecting non-dominated solutions, and finally the optimal solution set is obtained. The specific steps are as follows:

[0039] S301, Population initialization: Randomly divide the initial population into two sub-populations and allocate them to the NSGA3 and MOPSO algorithms respectively.

[0040] S302, Independent Optimization: Each sub-population is independently optimized under its respective algorithm framework. The NSGA3 sub-population maintains the diversity and convergence of solutions through fast non-dominated sorting and crowding degree calculation; the MOPSO sub-population enhances the global search ability through time-varying inertia weight and dynamic adjustment strategy.

[0041] S303, Information Exchange: After each generation of optimization, information is exchanged between the two sub-populations. Specifically, the non-dominated solutions in the NSGA3 sub-population are introduced into the MOPSO sub-population as the global optimal solutions of the particle swarm; at the same time, the high-quality solutions in the MOPSO sub-population are also introduced into the NSGA3 sub-population as the parent individuals of the genetic algorithm.

[0042] S304, Population Update: By comparing and selecting non-dominated solutions, the individuals of the two sub-populations are updated to ensure the diversity and convergence of solutions.

[0043] S305, Iterative Optimization: Repeat the above steps until the termination condition is met, and finally obtain a high-quality solution set.

[0044] It can be seen that by integrating the NSGA3 and MOPSO algorithms, the present invention can effectively combine the advantages of the two algorithms. The NSGA3 algorithm has advantages in maintaining the diversity and convergence of solutions, while the MOPSO algorithm performs excellently in global search ability and dynamic adjustment strategy. Through the dual-population strategy, the NSGA3 sub-population can provide high-quality non-dominated solutions to ensure the diversity and convergence of solutions; the MOPSO sub-population enhances the global search ability through time-varying inertia weight and dynamic adjustment strategy, avoiding the problem of premature convergence. The collaborative work of the two algorithms enables the optimization process to improve the search efficiency while ensuring the quality of solutions. Especially when facing complex multi-objective optimization problems, it can effectively handle multiple constraint conditions and obtain a better scheduling scheme. During the optimization process, the parameters of the NSGA3 and MOPSO algorithms are dynamically adjusted according to the optimization progress. Specifically, the crossover probability and mutation probability of the NSGA3 algorithm are adaptively adjusted according to the diversity of the population to ensure the diversity and convergence of solutions; the inertia weight and learning factor of the MOPSO algorithm are time-varyingly adjusted according to the optimization progress to enhance the global search ability. Through this dynamic adjustment strategy, the two algorithms can give full play to their respective advantages at different optimization stages, ensuring the efficiency and stability of the optimization process.

[0045] In addition, to verify the superiority of the NSGA3 and MOPSO fusion algorithms, we conducted multiple groups of comparative experiments. The experimental results show that the fusion algorithm is superior to the single NSGA3 and MOPSO algorithms in terms of solution diversity, convergence, and computational efficiency. Especially when dealing with complex multi-objective optimization problems, the fusion algorithm can find a high-quality solution set faster, and the distribution of solutions is more uniform, which can better meet multiple optimization objectives.

[0046] In the embodiments of the present invention, the function of the daily total water consumption is: The function of the daily economic benefit is: k1 to k6 are the electricity prices corresponding to the respective outputs, and the function of the standard deviation of the remaining load is: The constraint conditions include: wind power output constraint: In the formula, P t min and P t max are the maximum and minimum outputs of wind turbine i respectively; j is 0 or 1, indicating whether the unit operates independently or jointly; photovoltaic output constraint: In the formula, P i,min and P i,max are the maximum and minimum outputs of photovoltaic unit i respectively; j is 0 or 1, indicating whether the unit operates independently or jointly; generating head constraint: In the formula, Zt is the water level of the hydropower station at the t-th time period, is the tail water level of the hydropower station at the t-th time period, is the head loss of the hydropower station at the t-th time period, which can be expressed as a linear function of the generating flow rate: In the formula, both a and b are constants; water balance constraint: In the formula, V t is the reservoir storage volume at the beginning of the t-th time period, is the reservoir inflow at the t-th time period, is the reservoir spillage at the t-th time period; reservoir storage volume constraint: V t min ≤V t ≤V t max In the formula, V t min and V t max are the minimum and maximum reservoir storage volumes at the t-th time period respectively; reservoir operating water level constraint: In the formula, are the minimum and maximum values of the reservoir operating water level at the t-th time period respectively; generating flow rate constraint: In the formula, are the minimum and maximum reservoir discharge flows during period t, respectively; Outlet flow constraint: In the formula, is the maximum reservoir discharge flow during period t; Hydropower station output constraint: P i min ≤AQ t H t ≤P i max In the formula, P i min and P i max are the minimum and maximum outputs of hydropower station unit i respectively, and A is the hydropower station output coefficient.

[0047] Next, an improved fast non-dominated genetic algorithm and a time-varying multi-objective particle swarm optimization algorithm are adopted on the server side to globally optimize the multi-objective optimal scheduling model through a dual-population strategy; finally, the optimization results are displayed on the client through a graphical interface, and the optimization results include the power generation plan of each power station, the change in reservoir capacity, and the economic benefits of the system.

[0048] In the embodiment of the present invention, data preparation and optimization calculation are completed on the server side, while the display of optimization results is carried out on the client side. Users can view the results of optimal scheduling through a Web interface or a mobile application. Adopting a module-based coding method, the entire system is divided into a data preparation module, a modeling and optimization module, a result analysis and output module, etc. Each module is responsible for different functions, and data exchange and communication are carried out between modules through defined interfaces. The software part includes data processing and optimization calculation on the server side and result display on the client side. The data collected by the hardware is transmitted to the server through the network for processing and analysis. The server generates an optimal scheduling plan according to the analysis results and then sends it to the client side for display through the network.

[0049] Through the embodiment of the present invention, the daily economic benefits of the small hydropower - photovoltaic - wind power - pumped storage power generation system can be effectively increased. Using the improved hybrid intelligent algorithm to optimize the scheduling of the system can improve the economic benefits of the system while ensuring power supply. It also focuses on reducing the total daily water consumption of small hydropower stations. By optimizing power generation scheduling, the consumption of water resources is reduced, the utilization efficiency of water resources is further improved, and the impact on the environment is reduced. By reducing the load fluctuation in the power system, especially during the dry season, the standard deviation of the residual load is reduced through optimized scheduling, and the stability and reliability of the power system are improved.

[0050] In the specific steps, the technical solution first collects and processes the system parameters and constraint conditions of small hydropower, photovoltaic, wind power, and pumped-storage power stations through data preparation and system modeling. Then, an improved hybrid intelligent algorithm is used, combining the fast non-dominated genetic algorithm (NSGA3) and the time-varying multi-objective particle swarm optimization (MOPSO) algorithm, to globally optimize the scheduling problem through a dual-population strategy. This process is executed on the server side, and the final optimization results are displayed to the user through the client interface, including important information such as the power generation plan of each power station and the change in reservoir capacity. The beneficial effects of the present invention are not only reflected in improving economic benefits, reducing water resource consumption, and enhancing system stability, but also in improving the performance of the optimization algorithm by adopting the improved algorithm and the dual-population strategy, ensuring that the optimization results of the power system scheduling scheme are efficient and practical while meeting multiple objectives.

[0051] As Figure 2 shown, an embodiment of the present invention also provides a multi-objective trading system for water, wind, and photovoltaic power generation based on an improved hybrid algorithm. The system includes:

[0052] A data acquisition hardware module 100, configured to collect the system parameters of hydropower stations, photovoltaic power, wind power, and pumped-storage power stations, and determine the boundary values of constraint conditions;

[0053] A scheduling model construction module 200, configured to construct a multi-objective optimization scheduling model, where the multi-objective optimization scheduling model includes an objective function and constraint conditions;

[0054] A scheduling model optimization module 300, configured to adopt an improved fast non-dominated genetic algorithm and a time-varying multi-objective particle swarm optimization algorithm to globally optimize the multi-objective optimization scheduling model through a dual-population strategy;

[0055] An optimization result display module 400, configured to display the optimization results on the client through a graphical interface, where the optimization results include the power generation plan of each power station, the change in reservoir capacity, and the economic benefits of the system.

[0056] In an embodiment of the present invention, the system includes a data processing server, a computing and optimization server, and an application server. The data processing server is responsible for collecting and preprocessing data; the computing and optimization server is used to execute the improved hybrid intelligent algorithm for optimization calculation; the application server processes user requests, invokes the optimization model, and feeds back the results to the client. The data acquisition hardware module 100 includes monitoring devices and sensors of the power station, and is used to monitor the power generation, water level, and environmental conditions in real time.

[0057] The above only describes the preferred embodiments of the present invention in detail and is not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

[0058] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown sequentially according to the indications of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0059] Those of ordinary skill in the art can understand that to implement all or part of the processes in the above-mentioned embodiment strategies, it can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned strategies. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0060] After considering the specification and the disclosure of the embodiments, those skilled in the art will readily conceive of other embodiments of the present disclosure. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known common knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the claims.

Claims

1. A multi-objective trading strategy for water, wind and photovoltaic power generation based on an improved hybrid algorithm, characterized in that, The strategy includes the following steps: Collect the system parameters of hydropower stations, photovoltaic power stations, wind power stations and pumped-storage power stations, and determine the boundary values of the constraint conditions; Construct a multi-objective optimal scheduling model, which includes an objective function and constraint conditions; Adopt an improved fast non-dominated genetic algorithm and a time-varying multi-objective particle swarm optimization algorithm to globally optimize the multi-objective optimal scheduling model through a dual-population strategy; Display the optimization results on the client through a graphical interface, where the optimization results include the power generation plan of each power station, the change in reservoir capacity, and the economic benefits of the system.

2. The multi-objective trading strategy for water, wind and solar power generation based on the improved hybrid algorithm according to claim 1, characterized in that When globally optimizing the multi-objective optimal scheduling model through a dual-population strategy, divide the initial population into two parts, and optimize them respectively according to the improved MOPSO and NSGA3 algorithms. Update the population by comparing and selecting non-dominated solutions, and finally obtain the optimal solution set. The specific steps include: population initialization, randomly divide the initial population into two sub-populations and assign them to the NSGA3 and MOPSO algorithms respectively; independent optimization, each sub-population performs independent optimization under its own algorithm framework. The NSGA3 sub-population maintains the diversity and convergence of solutions through fast non-dominated sorting and crowding degree calculation, and the MOPSO sub-population enhances the global search ability through time-varying inertia weight and dynamic adjustment strategy; information exchange, after each generation of optimization ends, exchange information between the two sub-populations; population update, update the individuals of the two sub-populations by comparing and selecting non-dominated solutions; iterative optimization, repeat the above steps until the termination condition is met to obtain the final solution set.

3. The multi-objective trading strategy for water, wind and photovoltaic power generation based on the improved hybrid algorithm according to claim 1, characterized in that, The objective function includes the daily total water consumption of the power station, the daily economic benefits, and the standard deviation of the remaining load.

4. The multi-objective trading strategy for water, wind and photovoltaic power generation based on the improved hybrid algorithm according to claim 3, characterized in that, The function of the daily total water consumption is as follows: The function of the daily economic benefit is as follows: The function of the standard deviation of the remaining load is as follows: k1 to k6 are the electricity prices corresponding to the respective outputs.

5. The multi-objective trading strategy for water-wind-solar power generation based on the improved hybrid algorithm according to claim 4, characterized in that, The constraint conditions include: wind power output constraint: In the formula, P t min , P t max are the maximum and minimum outputs of wind turbine i respectively; j is 0 or 1, indicating independent or combined operation of the unit; Photovoltaic output constraint: In the formula, P i,min , P i,max are the maximum and minimum outputs of photovoltaic unit i respectively; j is 0 or 1, indicating independent or combined operation of the unit; Generation head constraint: In the formula, Zt is the water level of the hydropower station at the t-th time period, is the tail water level of the hydropower station at the t-th time period, is the head loss of the hydropower station at the t-th time period, which can be expressed as a linear function of the generation flow rate: In the formula, both a and b are constants.

6. The multi-objective trading strategy for hydro-wind-solar power generation based on the improved hybrid algorithm according to claim 5, characterized in that, The constraint conditions further include: water balance constraint: In the formula, V t is the reservoir storage volume at the beginning of period t, is the reservoir inflow during period t, is the reservoir spillage flow during period t; Reservoir storage volume constraint: In the formula, are the minimum and maximum storage volumes of the reservoir during period t respectively; Reservoir operation water level constraint: In the formula, are the minimum and maximum values of the reservoir operation water level during period t respectively.

7. The multi-objective trading strategy for water-wind-solar power generation based on the improved hybrid algorithm according to claim 6, wherein The constraint conditions further include: power generation flow constraint: In the formula, are the minimum and maximum values of the reservoir discharge flow at time t respectively; the out - flow constraint: In the formula, is the maximum value of the reservoir discharge flow at time t; the power output constraint of the hydropower station: In the formula, are the minimum and maximum values of the power output of the hydropower station unit i respectively, and A is the power output coefficient of the hydropower station.

8. A multi-objective trading system for water, wind and photovoltaic power generation based on an improved hybrid algorithm, characterized in that The system includes: A data acquisition hardware module for collecting the system parameters of hydropower stations, photovoltaic power stations, wind power stations and pumped-storage power stations, and determining the boundary values of the constraint conditions; A scheduling model construction module for constructing a multi-objective optimal scheduling model, which includes an objective function and constraint conditions; A scheduling model optimization module for globally optimizing the multi-objective optimal scheduling model through a dual-population strategy by adopting an improved fast non-dominated genetic algorithm and a time-varying multi-objective particle swarm optimization algorithm; An optimization result display module for displaying the optimization results on the client through a graphical interface, where the optimization results include the power generation plan of each power station, the change in reservoir capacity, and the economic benefits of the system.

9. The multi-objective trading system for water-wind-solar power generation based on the improved hybrid algorithm according to claim 8, wherein, The system includes a data processing server, a computing and optimization server, and an application server. The data processing server is responsible for collecting and preprocessing data; The computing and optimization server is used to execute an improved hybrid intelligent algorithm for optimization calculation; The application server processes user requests, calls the optimization model and feeds back the results to the client.

10. The multi-objective trading system for water, wind and solar power generation based on the improved hybrid algorithm according to claim 8, characterized in that, The data acquisition hardware module includes monitoring devices and sensors of the power station for real-time monitoring of power generation, water level and environmental conditions.

Images