An optimal scheduling method for multi-objective and multi-mode intelligent switching of cascade hydropower station group

Abstract

The application discloses a kind of cascade hydropower station group multi-objective multi-mode intelligent switching optimization scheduling method, comprising the following steps: S1, for all scheduling requirements and business scenarios of cascade hydropower station group, develop multiple optimization scheduling modes, including several single-objective scheduling modes and multi-objective scheduling modes;S2, establish the optimization target library, optimization scheduling constraint library and optimization scheduling algorithm library corresponding to the developed optimization scheduling mode;S3, for different scheduling requirements and business scenarios, according to optimization target library and optimization scheduling constraint library Intelligent construction optimization scheduling model, and from optimization scheduling algorithm library Matching optimization scheduling algorithm suitable for solving the optimization scheduling model, generating optimization scheduling scheme.The present application can intelligently switch the optimization scheduling mode of cascade hydropower station group according to the basin cascade scheduling requirement, solve the low calculation efficiency problem existing in the traditional power station scheduling mode.

Description

Technical Field

[0001] This invention relates to hydropower station dispatching technology, and in particular to an optimized dispatching method for multi-objective, multi-mode intelligent switching of a cascade hydropower station group. Background Technology

[0002] The scientific scheduling and operation of hydropower station clusters is crucial to ensuring water security and power production safety in the basin, and to fully realizing the comprehensive benefits of hydropower. However, each power station has different regulation characteristics, functions, and operational requirements. Coupled with complex boundary conditions, dispatch orders under different periods and operating conditions, multi-objective requirements, and numerous influencing factors such as dynamically changing hydrological conditions and operating conditions, the scheduling and operation of cascade hydropower stations always faces diverse states and complex scientific decision-making. Currently, hydropower station scheduling decisions are usually based on the traditional production model of automated water dispatching systems and human experience, which suffers from low efficiency, poor accuracy, suboptimal schemes, and insufficient data mining. The traditional human experience-driven scheduling model is no longer suitable for the more intelligent development direction and management requirements of the new era.

[0003] The intelligent joint dispatch of large-scale cascade hydropower station groups integrates advanced computer computing and automatic control technologies to achieve "intelligent formulation" of dispatch plans. Therefore, it is urgent to combine new technologies such as big data and artificial intelligence with traditional theoretical technologies to achieve intelligent generation of dispatch plans under different operating conditions, and to propose intelligent dispatch technology for cascade hydropower station groups in river basins. Summary of the Invention

[0004] Purpose of the invention: The purpose of this invention is to provide an optimized scheduling method for multi-objective and multi-mode intelligent switching of cascade hydropower station groups. This method can intelligently switch the optimized scheduling mode according to the optimized scheduling needs of the cascade hydropower station group in the basin, so as to solve the problem of low computational efficiency in traditional power station scheduling methods.

[0005] Technical solution: The present invention provides an optimized scheduling method for multi-objective, multi-mode intelligent switching of a cascade hydropower station group, comprising the following steps:

[0006] S1. Develop multiple optimized scheduling modes for all scheduling needs and business scenarios of cascade hydropower station groups, including several single-objective scheduling modes and multi-objective scheduling modes;

[0007] S2. Establish an optimization target library, an optimization constraint library, and an optimization algorithm library corresponding to the developed optimization scheduling mode;

[0008] S3. For different scheduling needs and business scenarios, intelligently construct an optimized scheduling model based on the optimized target library and the optimized scheduling constraint library, and match the optimized scheduling algorithm suitable for solving the optimized scheduling model from the optimized scheduling algorithm library to generate an optimized scheduling scheme.

[0009] Furthermore, in step S1, several single-objective scheduling modes include the maximum power generation mode, the maximum power generation benefit mode, the maximum energy storage mode, the minimum water wastage mode, the minimum power generation water consumption mode, and the flood control optimization scheduling mode; the multi-objective scheduling mode is constructed by combining several single-objective scheduling modes.

[0010] Furthermore, the optimization objective library established in step S2 includes: the hydropower station scheduling objectives corresponding to the following modes: maximum power generation, maximum power generation efficiency, maximum energy storage, minimum water wastage, minimum power generation water consumption, flood control optimization scheduling, and multi-objective scheduling. The specific objective function is as follows:

[0011] (1) Maximum power generation target:

[0012] (1);

[0013] in, express The hydropower station during the dispatch cycle Total electricity generation within the region; For the first The output coefficient of a hydropower station; , They are the first The first hydropower station in Power generation flow and power generation head within a specific time period; For time intervals;

[0014] (2) The goal of maximizing power generation benefits:

[0015] (2);

[0016] in, express The hydropower station during the dispatch cycle Total power generation benefits within the region; For the first Hydropower station Contract electricity price for a given period; For the first Hydropower station Contracted electricity volume for the specified time period; For the first Hydropower station Spot auction price for electricity during specific time periods; For the first Hydropower station Spot auction volume during the specified time period;

[0017] (3) Maximum energy storage target:

[0018] (3);

[0019] in, express The hydropower station during the dispatch cycle Total energy storage within; , , For the first Hydropower station Inflow and outflow rates and water head during different time periods; No. Hydropower station power generation coefficient;

[0020] (4) Minimum target for water disposal:

[0021] (4);

[0022] in, express The hydropower station during the dispatch cycle Total wastewater within the area; For the first Hydropower station The amount of water discharged during a given time period;

[0023] (5) Minimize water consumption for power generation:

[0024] (5);

[0025] in, express The hydropower station during the dispatch cycle Total water consumption for power generation within the area; For the first Hydropower station Electricity generation during a given period;

[0026] (6) Flood control optimization scheduling objectives:

[0027] (6);

[0028] in, This indicates the highest water level of the target hydropower station within the forecast period; This indicates the highest water level of the target hydropower station within the forecast period.

[0029] (7) Multi-objective scheduling mode scheduling objectives:

[0030] The multi-objective scheduling mode is constructed by combining several modes from the modes of maximizing power generation, maximizing power generation efficiency, maximizing energy storage, minimizing water wastage, minimizing power generation water consumption, and optimizing flood control scheduling. The objective functions of each mode are the same as those above.

[0031] Furthermore, the optimized scheduling constraint library established in step S2 includes: water balance constraints, power balance constraints, electricity balance constraints, power plant output constraints, flow balance constraints, power generation flow constraints, downstream flow constraints, and water level constraints; specifically:

[0032] (1) Water balance constraint:

[0033] (7);

[0034] in, , The first The first hydropower station , Hydropower station water storage capacity during a given period; , The first Hydropower station Inbound and outbound flow rates for different time periods; The duration of the time period;

[0035] (2) Power balance constraint:

[0036] (8);

[0037] in, express The hydropower station during the dispatch cycle Electricity generation within the region; For the first Hydropower station Output during specific time periods;

[0038] (3) Power balance constraints:

[0039] (9);

[0040] in, This indicates that N hydropower stations are in the th... Load during a specific time period Indicates the first The first hydropower station During specific time periods;

[0041] (4) Power plant output constraints:

[0042] (10);

[0043] in, , The first Hydropower station Lower and upper limits of unit output during specific time periods; Indicates the first The first hydropower station During specific time periods;

[0044] (5) Flow balance constraint:

[0045] (11);

[0046] in, , , The first Hydropower station Time-specific outflow, power generation flow, and water discharge;

[0047] (6) Power generation flow constraints:

[0048] (12);

[0049] in, , The first Hydropower station Lower and upper limits of power generation flow rate during a given time period; For the first Hydropower station Power generation flow during specific time periods;

[0050] (7) Downflow constraint:

[0051] (13);

[0052] in, , The first Hydropower station Upper and lower limits of discharge flow during specific time periods; For the first Hydropower station Outbound flow during a specific time period;

[0053] (8) Water level constraint:

[0054] (14);

[0055] in, , The first Hydropower station The lower and upper limits of water levels for a given period of time. For the first The first hydropower station Water level at a given time period.

[0056] Furthermore, the optimization scheduling algorithm library in step S2 includes: a dynamic programming algorithm suitable for solving the optimization scheduling problem of a single power station; an improved dynamic programming algorithm suitable for solving the scheduling problem of a power station group; a stepwise optimization algorithm suitable for short-term or real-time hydropower station optimization scheduling problems with solution rate requirements; a large system decomposition and coordination algorithm suitable for solving the stochastic optimization scheduling problem of a power station group; and a genetic algorithm suitable for solving large-scale, nonlinear, and multi-dimensional power station group optimization scheduling problems.

[0057] Furthermore, step S3 specifically includes:

[0058] To address different scheduling needs and business scenarios, the system automatically extracts relevant elements from the optimization objective library, optimization scheduling constraint library, and optimization scheduling algorithm library, and intelligently combines and configures them to achieve intelligent construction of the optimization scheduling model. During high-water years, to maximize the economic benefits of cascade hydropower, the system needs to maximize power generation. Since the grid-connected electricity price varies for different hydropower stations at different times, it also needs to ensure maximum power generation efficiency. To ensure power generation efficiency during low-water years, excess water energy needs to be stored to maximize the total energy storage of the cascade hydropower stations. Based on the scheduling needs of the cascade hydropower stations, the system automatically selects a multi-objective mode composed of three objective functions: maximum power generation, maximum power generation efficiency, and maximum total energy storage. The system extracts water balance constraints, power balance constraints, electricity balance constraints, power plant output constraints, flow balance constraints, power generation flow constraints, downstream flow constraints, and water level constraints from the algorithm library. For the intelligently constructed optimal scheduling model, it extracts suitable optimal scheduling algorithms from the optimal scheduling algorithm library to solve the model and generate an optimal scheduling scheme. When solving a single power plant optimal scheduling model, the system automatically extracts a dynamic programming algorithm from the algorithm library. When solving short-term or real-time hydropower plant optimal scheduling models, the system automatically extracts a stepwise optimization algorithm from the algorithm library. When solving a group of hydropower plants stochastic optimal scheduling models, the system automatically extracts a large-system decomposition and coordination algorithm from the algorithm library.

[0059] Beneficial effects: This invention can reduce the repetitive work of traditional power plant scheduling methods. It can intelligently construct and optimize scheduling models for different scheduling needs and business scenarios, and solve and generate optimized scheduling schemes, which can significantly improve computational efficiency. Based on the intelligently constructed scheduling model, it can intelligently match the optimal solution algorithm, which can significantly improve the utilization rate of hydropower and power generation efficiency. Attached Figure Description

[0060] Figure 1 This is a schematic diagram of the method flow of the present invention;

[0061] Figure 2 The water level process of Hongjiadu Hydropower Station was obtained by using the orthogonal discrete differential dynamic programming method to solve the model considering the maximum power generation in the example.

[0062] Figure 3 The water level process of the Puding Hydropower Station was obtained by solving the model considering the maximum power generation in the example using the orthogonal discrete differential dynamic programming method.

[0063] Figure 4 The water level process of Hongjiadu Hydropower Station was obtained by using the orthogonal discrete differential dynamic programming method to solve the maximum energy storage model in the example.

[0064] Figure 5 The water level process of the Puding Hydropower Station is obtained by solving the maximum energy storage model considered in the example using the orthogonal discrete differential dynamic programming method. Detailed Implementation

[0065] The present invention will be further described below with reference to the accompanying drawings and specific embodiments. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and should not be construed as limiting the scope of protection of the present invention.

[0066] like Figure 1 As shown in the figure, the optimized scheduling method for multi-objective, multi-mode intelligent switching of a cascade hydropower station group provided by the present invention specifically includes the following steps:

[0067] S1. Develop multiple optimized scheduling modes for all scheduling needs and business scenarios of cascade hydropower station groups, including several single-objective scheduling modes and multi-objective scheduling modes;

[0068] Single-objective scheduling modes include the maximum power generation mode, the maximum power generation benefit mode, the maximum energy storage mode, the minimum water wastage mode, the minimum power generation water consumption mode, and the flood control optimization scheduling mode; multi-objective scheduling modes are constructed by combining several single-objective scheduling modes.

[0069] S2. Establish an optimization target library, an optimization constraint library, and an optimization algorithm library corresponding to the developed optimization scheduling mode;

[0070] Optimization Target Library: The target function library contains the hydropower station scheduling targets corresponding to the above seven modes. Different scheduling targets can be selected according to different power station scheduling time scales and needs. The specific target functions are as follows:

[0071] (1) Maximum power generation target:

[0072] (1);

[0073] in, express The hydropower station during the dispatch cycle Total electricity generation within the region; For the first The output coefficient of a hydropower station; , They are the first The first hydropower station in Power generation flow and power generation head within a specific time period; This refers to the time interval.

[0074] (2) The goal of maximizing power generation benefits:

[0075] (2);

[0076] in, express The hydropower station during the dispatch cycle Total power generation benefits within the region; For the first Hydropower station Contract electricity price for a given period; For the first Hydropower station Contracted electricity volume for the specified time period; For the first Hydropower station Spot auction price for electricity during specific time periods; For the first Hydropower station Electricity volume during the spot auction period.

[0077] (3) Maximum energy storage target:

[0078] (3);

[0079] in, express The hydropower station during the dispatch cycle Total energy storage within; , , For the first Hydropower station Inflow and outflow rates and water head during different time periods; No. Hydropower station power generation coefficient.

[0080] (4) Minimum target for water disposal:

[0081] (4);

[0082] in, express The hydropower station during the dispatch cycle Total wastewater within the area; For the first Hydropower station The amount of water discharged during a given time period.

[0083] (5) Minimize water consumption for power generation:

[0084] (5);

[0085] in, express The hydropower station during the dispatch cycle Total water consumption for power generation within the area; For the first Hydropower station Electricity generation during a given period.

[0086] (6) Flood control optimization scheduling objectives:

[0087] (6);

[0088] in, This indicates the highest water level of the target hydropower station within the forecast period; This indicates the highest water level of the target hydropower station within the forecast period.

[0089] (7) Multi-objective scheduling mode scheduling objectives:

[0090] The multi-objective scheduling mode is constructed by combining several modes from the modes of maximizing power generation, maximizing power generation efficiency, maximizing energy storage, minimizing water wastage, minimizing power generation water consumption, and optimizing flood control scheduling. The objective functions of each mode are the same as those above.

[0091] Optimize the scheduling constraint library: Establish necessary constraints based on the cascade hydropower station group, taking water balance constraints, power balance constraints, electricity balance constraints, power station output constraints, flow balance constraints, power generation flow constraints, downstream flow constraints, and water level constraints as examples:

[0092] (1) Water balance constraint:

[0093] (7);

[0094] in, , The first The first hydropower station , Hydropower station water storage capacity during a given period; , The first Hydropower station Inbound and outbound flow rates for different time periods; This refers to the duration of the time period.

[0095] (2) Power balance constraint:

[0096] (8);

[0097] in, express The hydropower station during the dispatch cycle Electricity generation within the region; For the first Hydropower station Output during specific time periods.

[0098] (3) Power balance constraints:

[0099] (9);

[0100] in, This indicates that N hydropower stations are in the th... Load during a specific time period Indicates the first The first hydropower station Output during specific time periods.

[0101] (4) Power plant output constraints:

[0102] (10);

[0103] in, , The first Hydropower station Lower and upper limits of unit output during specific time periods; Indicates the first The first hydropower station Output during specific time periods.

[0104] (5) Flow balance constraint:

[0105] (11);

[0106] in, , , The first Hydropower station Time period outflow, power generation flow, and water discharge.

[0107] (6) Power generation flow constraints:

[0108] (12);

[0109] in, , The first Hydropower station Lower and upper limits of power generation flow rate during a given time period; For the first Hydropower station Power generation flow during a given time period.

[0110] (7) Downflow constraint:

[0111] (13);

[0112] in, , The first Hydropower station Upper and lower limits of discharge flow during specific time periods; For the first Hydropower station Outbound flow during a specific time period.

[0113] (8) Water level constraint:

[0114] (14);

[0115] in, , The first Hydropower station The lower and upper limits of water levels for a given period of time. For the first The first hydropower station Water level at a given time period.

[0116] Optimized Scheduling Algorithm Library: In the optimized scheduling of hydropower stations, the appropriate selection of optimization algorithms can lead to more efficient and accurate results. This invention sets different solution algorithms for different optimized scheduling models:

[0117] (1) Dynamic programming and its improved algorithms

[0118] Dynamic programming is the most classic algorithm for solving the optimal scheduling of hydropower stations. Its advantages are that it guarantees the global optimal solution and can save the solution of each subprocess, which is beneficial to the analysis of the results. It is suitable for solving the optimal scheduling model of a single power station. Improved dynamic programming algorithms such as Discrete Differential Dynamic Programming (DDDP), Incremental Dynamic Programming, and Differential Dynamic Programming can effectively avoid the "curse of dimensionality" problem and are suitable for solving the optimal scheduling model of power station groups.

[0119] (2) Stepwise Optimization Algorithm (POA)

[0120] The successive optimization algorithm is suitable for multi-stage dynamic optimization problems and belongs to dynamic programming algorithms. However, POA does not require discrete state variables, consumes less memory, accelerates quickly, and can obtain more accurate solutions. It is suitable for solving short-term or real-time hydropower station optimization scheduling models with solution rate requirements.

[0121] (3) Large system decomposition and coordination algorithm

[0122] Large system decomposition and coordination decomposes a complex large system into several simple subsystems and achieves global optimization of the subsystems. It has the advantages of simplifying complexity, reducing workload, and avoiding the "curse of dimensionality". It is suitable for solving stochastic optimization scheduling models of power plant groups.

[0123] (4) Genetic Algorithm

[0124] Genetic algorithms are adaptive global optimization search algorithms with parallel computing characteristics and adaptive search capabilities. They can perform global optimal search from multiple initial points and multiple paths, and are suitable for solving large-scale, nonlinear, and multi-dimensional hydropower station group optimization scheduling models.

[0125] S3. For different scheduling needs and business scenarios, intelligently construct optimized scheduling models based on the optimized target library and optimized scheduling constraint library, and match optimized scheduling algorithms suitable for solving these models from the optimized scheduling algorithm library to generate optimized scheduling schemes; specifically:

[0126] To address different scheduling needs and business scenarios, the system automatically extracts relevant elements from the optimization objective library, optimization scheduling constraint library, and optimization scheduling algorithm library, and intelligently combines and configures them to achieve intelligent construction of the optimization scheduling model. For example, in a high-water year, to maximize the economic benefits of cascade hydropower, the system needs to maximize power generation. Since the grid-connected electricity price varies for different hydropower stations at different times, it also needs to maximize power generation efficiency. To ensure power generation efficiency in a low-water year, excess water energy needs to be stored to maximize the total energy storage of the cascade hydropower stations. Based on the scheduling needs of the cascade hydropower stations, the system automatically selects a multi-objective mode composed of three objective functions: maximizing power generation, maximizing power generation efficiency, and maximizing total energy storage. It also extracts water balance constraints, power balance constraints, power balance constraints, power station output constraints, flow balance constraints, power generation flow constraints, downstream flow constraints, and water level constraints from the optimization scheduling constraint library. For the intelligently constructed optimal scheduling model, the system extracts suitable optimal scheduling algorithms from the optimal scheduling algorithm library to solve the model, solves the optimal scheduling model, and generates an optimal scheduling scheme. For example, when solving the optimal scheduling model of a single power station, the system automatically extracts a dynamic programming algorithm from the optimal scheduling algorithm library; when solving the optimal scheduling model of a short-term or real-time hydropower station, the system automatically extracts a stepwise optimization algorithm from the optimal scheduling algorithm library; when solving the stochastic optimal scheduling model of a group of hydropower stations, the system automatically extracts a large-system decomposition and coordination algorithm from the optimal scheduling algorithm library, etc.

[0127] Example Application

[0128] Using the method of this invention, 11 cascade hydropower stations, including Hongjiadu and Puding, in the Wujiang River Basin were selected as the application objects. The optimization was carried out based on the actual operation data of the Wujiang River Basin in 2018. The optimization results of the maximum power generation model are shown in Table 1.

[0129] Table 1. Optimization results of the maximum power generation model for cascade hydropower stations (10,000 MW·h)

[0130]

[0131] As shown in Table 1, the method of this invention can increase the annual power generation of the Wujiang cascade hydropower station group by up to 376,300 MW·h, which is 1.36% more than the actual dispatching. Table 1 also shows that compared with conventional dispatching methods, this invention can make fuller use of hydropower resources and improve the utilization rate of hydropower resources. Taking the Hongjiadu and Puding hydropower stations as examples, their annual reservoir water level dispatching processes are shown in Table 1. Figure 2 and Figure 3 .

[0132] The optimized power generation results using the maximum energy storage model of cascade hydropower stations are shown in Table 2.

[0133] Table 2. Optimization results of the maximum energy storage model for cascade hydropower stations (100 million kWh)

[0134]

[0135] Table 2 shows that, using the method of this invention, the cascade hydropower station group on the Wujiang River can increase its cascade storage capacity by 0.91 billion kWh at the end of the year while maintaining the same annual power generation, representing a 1.53% increase compared to the actual cascade storage capacity. Compared with conventional scheduling methods, this invention can significantly reduce the water consumption rate of hydropower stations and improve water energy utilization efficiency. Taking the Hongjiadu and Puding hydropower stations as examples, their annual reservoir water level scheduling processes are shown in [Table 2]. Figure 4 and Figure 5 .

[0136] Depend on Figures 2-5 It can be seen that the scheduling scheme solved by the present invention is in a state of low water level at the end of the water supply period and high water level at the end of the water storage period, which is in line with the general law of hydropower station scheduling. The main reason is that the method of the present invention can adjust the current hydropower station scheduling scheme in real time according to the later water inflow of the hydropower station, so as to reduce water abandonment during the flood season, reduce the risk of flood control during the flood season, and ensure the water supply target of the hydropower station during the water supply period.

Claims

1. An optimized scheduling method for multi-objective, multi-mode intelligent switching of a cascade hydropower station group, characterized in that, Includes the following steps: S1. For all scheduling needs and business scenarios of cascade hydropower station groups, develop a variety of optimized scheduling modes, including several single-objective scheduling modes and multi-objective scheduling modes; the several single-objective scheduling modes include the maximum power generation mode, the maximum power generation benefit mode, the maximum energy storage mode, the minimum water wastage mode, the minimum power generation water consumption mode, and the flood control optimized scheduling mode; the multi-objective scheduling mode is constructed by combining several single-objective scheduling modes. S2. Establish an optimization target library, an optimization constraint library, and an optimization algorithm library corresponding to the developed optimization scheduling mode; The optimization objective library includes: the hydropower station scheduling objectives corresponding to the following modes: maximum power generation, maximum power generation efficiency, maximum energy storage, minimum water wastage, minimum power generation water consumption, flood control optimization scheduling, and multi-objective scheduling. The specific objective function is as follows: (1) Maximum power generation target: ； in, express The hydropower station during the dispatch cycle Total electricity generation within the region; For the first The output coefficient of a hydropower station; , They are the first The first hydropower station in Power generation flow and power generation head within a specific time period; For time intervals; (2) The goal of maximizing power generation benefits: ； in, express The hydropower station during the dispatch cycle Total power generation benefits within the region; For the first Hydropower station Contract electricity price for a given period; For the first Hydropower station Contracted electricity volume for the specified time period; For the first Hydropower station Spot auction price for electricity during specific time periods; For the first Hydropower station Spot auction volume during the specified time period; (3) Maximum energy storage target: ； in, express The hydropower station during the dispatch cycle Total energy storage within; , , For the first Hydropower station Inflow and outflow rates and water head during different time periods; No. Hydropower station power generation coefficient; (4) Minimum target for water disposal: ； in, express The hydropower station during the dispatch cycle Total wastewater within the area; For the first Hydropower station The amount of water discharged during a given time period; (5) Minimize water consumption for power generation: ； in, express The hydropower station during the dispatch cycle Total water consumption for power generation within the area; For the first Hydropower station Electricity generation during a given period; (6) Flood control optimization scheduling objectives: ； in, This indicates the highest water level of the target hydropower station within the forecast period; This indicates the highest water level of the target hydropower station within the forecast period. (7) Multi-objective scheduling mode scheduling objectives: The multi-objective scheduling mode is constructed by combining several modes from the modes of maximizing power generation, maximizing power generation efficiency, maximizing energy storage, minimizing water waste, minimizing power generation water consumption, and optimizing flood control scheduling. Its objective functions are the same as those above. The optimized scheduling constraint library includes: water balance constraints, power balance constraints, electricity balance constraints, power plant output constraints, flow balance constraints, power generation flow constraints, downstream flow constraints, and water level constraints. The optimized scheduling algorithm library includes: dynamic programming algorithms suitable for solving single power plant optimal scheduling problems; improved dynamic programming algorithms suitable for solving power plant group scheduling problems; stepwise optimization algorithms suitable for short-term or real-time hydropower plant optimal scheduling problems with solution rate requirements; large system decomposition and coordination algorithms suitable for solving stochastic optimal scheduling problems of power plant groups; and genetic algorithms suitable for solving large-scale, nonlinear, and multi-dimensional power plant group optimal scheduling problems. S3. For different scheduling needs and business scenarios, intelligently construct an optimized scheduling model based on the optimized target library and the optimized scheduling constraint library, and match the optimized scheduling algorithm suitable for solving the optimized scheduling model from the optimized scheduling algorithm library to generate an optimized scheduling scheme.

2. The optimized scheduling method for multi-objective, multi-mode intelligent switching of a cascade hydropower station group according to claim 1, characterized in that, The constraints in step S2 are as follows: (1) Water balance constraint: ； in, , The first The first hydropower station , Hydropower station water storage capacity during a given period; , The first Hydropower station Inbound and outbound flow rates for different time periods; The duration of the time period; (2) Power balance constraint: ； in, express The hydropower station during the dispatch cycle Electricity generation within the region; For the first Hydropower station Output during specific time periods; (3) Power balance constraints: ； in, This indicates that N hydropower stations are in the th... Load during a specific time period Indicates the first The first hydropower station Output during specific time periods; (4) Power plant output constraints: ； in, , The first Hydropower station Lower and upper limits of unit output during specific time periods; Indicates the first The first hydropower station Output during specific time periods; (5) Flow balance constraint: ； in, , , The first Hydropower station Time-specific outflow, power generation flow, and water discharge; (6) Power generation flow constraints: ； in, , The first Hydropower station Lower and upper limits of power generation flow rate during a given time period; For the first Hydropower station Power generation flow during specific time periods; (7) Downflow constraint: ； in, , The first Hydropower station Upper and lower limits of discharge flow during specific time periods; For the first Hydropower station Outbound flow during a specific time period; (8) Water level constraint: ； in, , The first Hydropower station The lower and upper limits of water levels for a given period of time. For the first The first hydropower station Water level at a given time period.

3. The optimized scheduling method for multi-objective, multi-mode intelligent switching of a cascade hydropower station group according to claim 1, characterized in that, Step S3 is as follows: To address different scheduling needs and business scenarios, the system automatically extracts relevant elements from the optimization objective library, optimization scheduling constraint library, and optimization scheduling algorithm library, and intelligently combines and configures them to achieve intelligent construction of the optimization scheduling model. During high-water years, to maximize the economic benefits of cascade hydropower, the system needs to maximize power generation. Since the grid-connected electricity price varies for different hydropower stations at different times, it also needs to ensure maximum power generation efficiency. To ensure power generation efficiency during low-water years, excess water energy needs to be stored to maximize the total energy storage of the cascade hydropower stations. Based on the scheduling needs of the cascade hydropower stations, the system automatically selects a multi-objective mode composed of three objective functions: maximum power generation, maximum power generation efficiency, and maximum total energy storage. The system extracts water balance constraints, power balance constraints, electricity balance constraints, power plant output constraints, flow balance constraints, power generation flow constraints, downstream flow constraints, and water level constraints from the algorithm library. For the intelligently constructed optimal scheduling model, it extracts suitable optimal scheduling algorithms from the optimal scheduling algorithm library to solve the model and generate an optimal scheduling scheme. When solving a single power plant optimal scheduling model, the system automatically extracts a dynamic programming algorithm from the algorithm library. When solving short-term or real-time hydropower plant optimal scheduling models, the system automatically extracts a stepwise optimization algorithm from the algorithm library. When solving a group of hydropower plants stochastic optimal scheduling models, the system automatically extracts a large-system decomposition and coordination algorithm from the algorithm library.

Images