Intelligent scheduling method and system for improving quality and efficiency of pumped storage power stations

Abstract

The present invention discloses an intelligent scheduling method and system for improving the quality and efficiency of pumped-storage power stations. The method includes: extracting typical daily scenarios of grid load and renewable energy output based on grid source-load characteristics and renewable energy output characteristics, and determining typical operating scenarios and operating modes of the pumped-storage power station; establishing a scheduling model with improving quality and efficiency as the optimization objective function and the power generation and pumping power of the pumped-storage power station as decision variables; and optimizing the power generation and pumping scheduling process of the pumped-storage power station using an intelligent evolutionary algorithm based on typical historical scenarios and predicted scenarios of equivalent loads, and compiling a scheduling plan that can improve quality and efficiency. The present invention can not only accurately extract the operating scenarios of pumped-storage power stations, but also reduce the impact of renewable energy grid connection while bringing considerable economic benefits, providing technical support for promoting the development and utilization of renewable energy and the transformation of the power system.

Description

Technical Field

[0001] The present invention belongs to the technical field of pumped storage power station scheduling, and specifically relates to an intelligent scheduling method and system for improving the quality and efficiency of pumped storage power stations. Background Art

[0002] Pumped-storage power stations are currently the most technologically mature, economically reliable, and largest energy storage method, offering multiple functions, including peak-load shifting, frequency regulation, emergency backup, and voltage regulation. Research on optimized scheduling of pumped-storage power stations can not only reduce the impact of wind and solar grid integration on the power grid and alleviate peak load regulation challenges, but also promote optimal power generation and enhance the economic benefits of power stations.

[0003] Compared with the intelligent scheduling of conventional hydropower stations, the technical difficulties and challenges of intelligent scheduling of pumped-storage power stations include: ① The scheduling model of a pumped-storage power station needs to take into account the two-way process of power generation and pumping, involving two-dimensional decision variables of power generation power and pumping power. In addition, there are multiple operating conditions during the operation of the power station, and it is subject to the multi-dimensional influence of more physical constraints such as grid power balance constraints and transmission line power constraints, which increases the difficulty of solving the problem; ② Given the multi-condition and multi-dimensional characteristics of the pumped-storage power station scheduling model, how to effectively improve the fitness function design of the intelligent evolutionary algorithm, while balancing the goals of improving quality and efficiency, to adapt it to the two-way operating characteristics of the pumped-storage power station, so as to improve the convergence efficiency of the algorithm in high-dimensional nonlinear models and avoid falling into local optimality, is a difficult problem that needs to be solved urgently. Summary of the Invention

[0004] In order to overcome the deficiencies of the above-mentioned prior art, the present invention provides an intelligent scheduling method and system for improving the quality and efficiency of pumped-storage power stations. The method is based on the source-load characteristics of the power grid and the output characteristics of renewable energy, extracts typical daily scenarios of power grid load and renewable energy output, and determines the typical operating scenarios and operating modes of the pumped-storage power station; establishes a scheduling model with improving quality and efficiency as the optimization objective function and the power generation and pumping power of the pumped-storage power station as decision variables; and adopts an intelligent evolutionary algorithm to optimize the power generation and pumping scheduling process of the pumped-storage power station based on typical historical scenarios and predicted scenarios of equivalent load, and compiles a scheduling plan that can improve quality and efficiency.

[0005] According to one aspect of the present invention, there is provided an intelligent scheduling method for improving the quality and efficiency of a pumped storage power station, comprising:

[0006] Based on the grid source-load characteristics and renewable energy output characteristics, typical daily scenarios of grid load and renewable energy output are extracted to determine the typical operating scenarios and modes of pumped storage power stations;

[0007] Establish a scheduling model with quality and efficiency improvement as the optimization objective function and the power generation and pumping power of the pumped storage power station as the decision variables;

[0008] Based on typical historical and predicted scenarios of equivalent load, an intelligent evolutionary algorithm is used to optimize the power generation and pumping scheduling processes of pumped-storage power stations, and a scheduling plan that can improve quality and efficiency is formulated.

[0009] As a further technical solution, based on the grid source-load characteristics and renewable energy output characteristics, typical daily scenarios of grid load and renewable energy output are extracted to determine the typical operating scenarios and modes of pumped storage power stations, including:

[0010] Based on the multi-year long-term daily output or load time series data of the study area, the output variation patterns and characteristics are analyzed from the power supply side and the load side using randomness, volatility, intermittency, and source-load correlation indicators, including grid load characteristics and the spatiotemporal attributes of clean energy output;

[0011] To improve the precision of load classification, Gaussian mixture model clustering was used to extract typical daily load scenarios and renewable energy output scenarios. Combined with the research area's grid load and clean energy output trends, typical grid net load scenarios after prioritizing renewable energy were obtained, integrating data dimensionality reduction and clustering tasks to comprehensively cover various wind, solar, and hydropower output scenarios.

[0012] Through operating environment and scenario analysis, the operating environment and operating boundaries of the pumped-storage power station are clarified. Then, based on the historical data of the pumped-storage power station under study, the aforementioned Gaussian mixture model clustering algorithm is used to extract the typical operating scenarios and operating modes of the power station.

[0013] As a further technical solution, the optimization objective function for improving quality and efficiency is:

[0014] maxF=c·ω1·F1-ω2·F2

[0015] ω1+ω2=1

[0016]

[0017] Where: max F1 is the objective function for maximizing the power generation efficiency of the pumped storage power station, min F2 is the objective function for minimizing the equivalent load deviation coefficient; ω1 and ω2 are weight coefficients, c is a constant for adjusting the order of magnitude; T is the total number of time periods in the dispatch period; 0-1 variables are introduced, x t =1 means the power station is in power generation operation during the t period, x t =0 means the power station is in a non-power-generating state during this period, t =1 means the power station is in pumping operation at time t, y t =0 means the power station is in non-pumping operation state; are the on-grid electricity price and pumped electricity price of the pumped storage power station in period t, respectively; They represent the power generation and pumping power of the pumped storage power station in period t; R 0,tR is the equivalent load of the original load of the pumped storage power station before operation optimization in period t minus the output of renewable energy; t L is the equivalent load of the original load after the pumped storage power station is put into operation in period t minus the output of renewable energy; t is the total power load of the entire network system in period t; They represent the predicted output of wind power and photovoltaic power in period t respectively; is the predicted hydropower output in period t; is the power of the pumped storage power station in period t; The power transmitted from the external network to the power grid during the t period, The power transmitted from the power grid to the external grid in period t;

[0018] When establishing the dispatching model of a pumped-storage power station, the power generation and pumping power of the pumped-storage power station are taken as decision variables, the peak-shaving and valley-filling function of the pumped-storage power station is considered, and the daily power generation process of the pumped-storage power station is deduced.

[0019] As a further technical solution, each reservoir / power station in the scheduling model meets the following constraints on power, water volume, and water energy conversion:

[0020] Active power balance constraints of the entire network; power generation and pumping power limits of pumped-storage power stations; operating condition constraints of pumped-storage power stations; water-energy conversion relationship of pumped-storage power stations; water balance of the upper and lower reservoirs of pumped-storage power stations; water storage capacity constraints of the upper and lower reservoirs of pumped-storage power stations; and storage capacity constraints at the beginning and end of dispatching.

[0021] As a further technical solution, an intelligent evolutionary algorithm is used to optimize the operating conditions of the pumped storage power station and its power generation or pumping power process during the scheduling period according to the collaborative scheduling module, including:

[0022] Initialize algorithm parameters and encode decision variables; evaluate fitness; perform selection, crossover, and mutation operations; and determine termination conditions.

[0023] According to one aspect of the present invention, there is provided an intelligent dispatching system for improving the quality and efficiency of a pumped storage power station, comprising:

[0024] The scenario extraction module is used to extract typical daily scenarios of grid load and renewable energy output based on the grid source-load characteristics and renewable energy output characteristics, and determine the typical operating scenarios and operating modes of pumped-storage power stations;

[0025] A model building module is used to establish a scheduling model with quality and efficiency improvement as the optimization objective function and the power generation and pumping power of the pumped storage power station as the decision variables;

[0026] The intelligent solution module is used to optimize the power generation and pumping scheduling processes of pumped-storage power stations based on typical historical and predicted equivalent load scenarios using intelligent evolutionary algorithms, and to develop scheduling plans that can improve quality and efficiency.

[0027] As a further technical solution, the scene extraction module is further configured to execute the following instructions:

[0028] Based on the multi-year long-term daily output or load time series data of the study area, the output variation patterns and characteristics of the power supply side and the load side are analyzed. By studying the randomness, volatility, intermittency and source-load correlation of the power supply output, the grid load characteristics and the spatiotemporal attributes of clean energy output are specifically analyzed;

[0029] To improve the precision of load classification, a Gaussian mixture model clustering algorithm was used to extract typical scenarios of daily load and renewable energy output. Combined with the development trends of regional grid load and clean energy output, this algorithm further derived typical scenarios of grid net load after prioritizing renewable energy consumption. This integrated data dimensionality reduction and clustering tasks, comprehensively covering various scenarios of wind, solar, and hydropower output.

[0030] Through operating environment and scenario analysis, the operating environment and operating boundaries of the pumped-storage power station are clarified. Then, based on the historical data of the pumped-storage power station under study, the aforementioned Gaussian mixture model clustering algorithm is used to extract the typical operating scenarios and operating modes of the power station.

[0031] As a further technical solution, the intelligent solution module further includes:

[0032] The first submodule is used to initialize algorithm parameters and encode decision variables;

[0033] The second submodule is used to calculate the quality improvement and efficiency enhancement function and evaluate the fitness;

[0034] The third submodule is used to perform selection, crossover and mutation operations on the population;

[0035] The fourth submodule is used to prepare a scheduling plan based on the optimization results.

[0036] According to one aspect of the present invention, there is provided an electronic device, which is configured in a pumped-storage power station and includes a memory and a processor. The memory is used to store a computer program. When the processor runs the computer program stored in the memory, the processor executes the intelligent scheduling method for improving the quality and efficiency of the pumped-storage power station.

[0037] According to one aspect of the present invention, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to execute the intelligent scheduling method for improving the quality and efficiency of pumped storage power stations.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] 1. The pumped-storage power station scheduling model constructed in this paper takes into account the two-way process of power generation and pumping. It adopts a weighted approach to introduce an objective function for improving quality and efficiency. This aims to balance the conflicting relationship between maximizing power generation benefits and minimizing the equivalent load dispersion coefficient. This allows for the development of a coordinated optimization operation strategy for the pumped-storage power station, increasing the operational benefits of the pumped-storage power station while improving peak-shaving capacity and grid stability.

[0040] 2. The present invention constructs an optimization scheduling model for pumped-storage power stations, adopts an intelligent evolutionary algorithm to optimize the power generation and pumping scheduling processes, comprehensively considers physical constraints such as grid power balance, and designs objective functions to improve quality and efficiency. This improves the algorithm's convergence efficiency and global search capabilities in high-dimensional nonlinear problems, effectively avoids local optimality, ensures the efficiency and robustness of the scheduling scheme, and provides technical support for the stable operation and green transformation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief introduction will be given below to the drawings used in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0042] Figure 1 This is a flow chart of an intelligent scheduling method for improving the quality and efficiency of a pumped storage power station provided by an embodiment of the present invention;

[0043] Figure 2 This is a flow chart of the intelligent evolutionary algorithm solution model provided by an embodiment of the present invention;

[0044] Figure 3 This is a comparison diagram of the equivalent load process before and after the optimized operation of the pumped storage power station under the typical daily load scenario involved in the embodiment of the present invention. DETAILED DESCRIPTION

[0045] The terms "including" and "having" and any variations thereof in the description and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions, for example, a process, method, system, product or apparatus that includes a series of steps or units is not necessarily limited to the steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0046] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In addition, the technical features in the various embodiments or single embodiments provided by the present invention are arbitrarily combined with each other to form a new technical solution. This combination is not restricted by the sequence of steps and / or structural composition mode, but must be based on the ability of ordinary technicians in this field to implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that this combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0047] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0048] like Figure 1 As shown, an embodiment of the present invention provides an intelligent scheduling method for improving the quality and efficiency of a pumped storage power station, comprising the following steps:

[0049] Step 1: Based on the grid source-load characteristics and renewable energy output characteristics, extract the typical daily scenarios of grid load and renewable energy output, and determine the typical operation scenarios and operation modes of the pumped storage power station.

[0050] With a time resolution of 15 minutes, the long series of 96-point daily output or load time series data in the study area are used to calculate the randomness, volatility, intermittency, and source-load correlation indicators, and analyze the output change patterns and characteristics from the power supply side and the load side, including the grid load characteristics and the spatiotemporal attributes of clean energy output.

[0051] To improve the precision of load classification, a Gaussian mixture model clustering was used to extract typical daily load scenarios and renewable energy output scenarios. Combined with the research area's grid load and clean energy output trends, typical grid net load scenarios after prioritizing renewable energy were obtained, integrating data dimensionality reduction and clustering tasks to comprehensively cover various wind, solar, and hydropower output scenarios. The expectation maximization algorithm is generally used to solve the Gaussian mixture model parameters. The general steps are as follows:

[0052] Step 1: Collect the grid load and clean energy output data, perform data preprocessing and splitting, and form a known sample set D = {x1, x2, ..., x m}, initialize the Gaussian mixture model parameters, select the number of Gaussian mixture components k, which is the number of cluster centers, and randomly initialize the mean vector μ for each Gaussian mixture component i , covariance matrix ∑i and mixing coefficient αi , the Gaussian mixture distribution function can be defined as:

[0053]

[0054] Where: P(·) is the probability density function, p(x|μ i ,∑i) is the i-th probability distribution model of the Gaussian mixture model, μ i and ∑i are the mean vector and covariance matrix of the i-th Gaussian mixture component, respectively, α i is the mixing coefficient, satisfying α i ≥0 and

[0055] Step 2: Expectation-step (E-step) in the expectation maximization algorithm, under the current model parameters, according to Bayesian theorem, calculate the sample x j The posterior probability of belonging to the i-th Gaussian component, that is, the degree of responsibility:

[0056]

[0057] Where: j = 1, 2,…, m; i = 1, 2,…, k.

[0058] Step 3: The M-step (maximization step, M-step) in the expectation maximization algorithm, that is, calculating the model parameters of the new round of iteration based on the responsibility calculated in the E-step:

[0059] Mean vector update:

[0060]

[0061] Covariance matrix update:

[0062]

[0063] Mixing coefficient update:

[0064]

[0065] Step 4: Repeat Step 2 and Step 3 until convergence or the preset maximum number of iterations is reached.

[0066] Step 5: Using the results of the EM algorithm, the sample set D is divided into k clusters C = {C1, C2, ..., C k}, each sample point x j Belongs to cluster C with the largest posterior probability i , whose cluster label λ j Determine by pressing the formula:

[0067] λj =argmaxγ ji ,i∈{1,2,…,k}

[0068] Through the clustering results, the representative center point of each cluster is extracted to form a typical scenario. The cluster center of the load and output time series data can represent the typical load or output scenario of the time period.

[0069] Through operating environment and scenario analysis, the operating environment and operating boundaries of the pumped-storage power station are clarified. Then, based on the power generation output process and pumping power process of the studied pumped-storage power station at 15-minute intervals in recent years, as well as the corresponding upper and lower reservoir water level processes, the aforementioned Gaussian mixture model clustering algorithm is used to extract the typical operating scenarios and operating modes of the power station.

[0070] Step 2: Establish a scheduling model with quality improvement and efficiency enhancement as the optimization objective function and the power generation and pumping power of the pumped storage power station as the decision variables.

[0071] The optimization objective function for improving quality and efficiency is:

[0072] maxF=c·ω1·F1-ω2·F2

[0073] ω1+ω2=1

[0074]

[0075]

[0076]

[0077] Where: max F1 is the objective function for maximizing the power generation benefit of the pumped storage power station, max F2 is the objective function for minimizing the equivalent load deviation coefficient; ω1 and ω2 are weight coefficients, c is a constant for adjusting the order of magnitude; T is the total number of time periods in the dispatch period; compared with conventional hydropower stations, pumped storage power stations have various operating conditions, and the operating cost is related to the operating conditions of the units. For the convenience of expression, a 0-1 variable is introduced, x t =1 means the power station is in power generation operation during the t period, x t =0 means the power station is in a non-power-generating state during this period, t =1 means the power station is in pumping operation at time t, y t =0 means the power station is in non-pumping operation state; are the on-grid electricity price and pumped electricity price of the pumped storage power station in period t, respectively; They represent the power generation and pumping power of the pumped storage power station in period t; R 0,t The original load of the pumped storage power station before operation optimization in period t is equivalent to the load of renewable energy output minus the original load; R tThe equivalent load of the original load after the pumped storage power station is put into operation in period t is deducted from the output of new energy; L t The total power load of the entire network system in time period t; They represent the predicted output of wind power and photovoltaic power in period t respectively; is the predicted hydropower output in period t; is the power of the pumped storage power station in period t, Can be positive or negative, negative value means pumping (i.e. ), positive values ​​indicate power generation (i.e. ); The power transmitted from the external network to the power grid during the t period, is the power transmitted from the power grid to the external grid in period t.

[0078] When establishing a pumped-storage power station dispatching and operation model, the power generation and pumping power of the pumped-storage power station are used as decision variables. The peak-shaving and valley-filling capabilities of the pumped-storage power station are considered to determine the daily power generation process of the pumped-storage power station. The model uses a daily dispatching period and a 15-minute time interval.

[0079] In step 2, each reservoir / power station must meet the following constraints on power, water volume, and water energy conversion:

[0080] a. Active power balance constraints of the entire network:

[0081]

[0082] In the formula, R t It can be considered as thermal power output, and the other variables have the same meanings as above;

[0083] b. Transmission line power constraints:

[0084]

[0085] Where, L in ( L out ), They represent the lower limit and upper limit of the power input (output) from the external network to the power grid respectively;

[0086] c. Power generation and pumping capacity limits of pumped storage power stations:

[0087]

[0088] Where, A negative value indicates the maximum power when the power station is pumping water; A positive value indicates the maximum capacity during power generation; It can be positive or negative, negative value means pumping water, positive value means power generation, Indicates shutdown or phase adjustment operation; in addition, when pumping water, the pumping power point of the power station is discrete, and the mathematical expression is as follows:

[0089]

[0090] Where P1, P2, …, P n Indicates the power point when pumping water;

[0091] d. Pumped storage power station operating constraints:

[0092] From the perspective of the power plant as a whole, the following constraints are generally considered:

[0093] ① The power station cannot be in power generation and pumping operation at the same time:

[0094] x t +y t ≤1

[0095] ② The switching between power generation operation and pumping operation of the power station shall be separated by at least one period:

[0096] x t +y t+1 ≤1 and y t +x t+1 ≤1

[0097] e. Water-energy conversion relationship of pumped storage power stations;

[0098]

[0099] Where Q t represents the power station flow in period t, Q t >0 means water flows from the upper reservoir to the lower reservoir, and the power station is in power generation operation. t Indicates the generating head; Q t <0 means water flows from the lower reservoir to the upper reservoir, and the power station is in pumping operation. t Indicates pumping head; They represent the efficiency of the power station when generating electricity and when pumping water respectively;

[0100] The calculation formulas for head and lift are as follows:

[0101] Head:

[0102] Lift:

[0103] Where, Respectively represent the average water level of the upper reservoir and the lower reservoir in the t period; Δh t Indicates the head loss in the pipe;

[0104] f. Water balance between upper and lower reservoirs of pumped storage power station:

[0105] Without considering other inflow supplements to the upper and lower reservoirs, there are

[0106] Upload:

[0107] Download library:

[0108] Where, Respectively represent the water storage capacity (storage capacity) of the upper and lower reservoirs at the beginning of the tth period; τ is the unit conversion coefficient;

[0109] g. Constraints on water storage capacity of upper and lower reservoirs of pumped storage power stations:

[0110] Upload:

[0111] Download library:

[0112] Where, Respectively represent the dead storage capacity of the lower reservoir (upper reservoir) and the storage capacity corresponding to the normal water level; V B Indicates the reserved emergency reserve storage capacity;

[0113] h. Storage capacity constraints at the beginning and end of scheduling:

[0114] The storage capacity V1 at the beginning of the scheduling period is given in advance, and the storage capacity V at the end of the scheduling period is T+1 is also given. According to the scheduling arrangement, the constraint can be expressed as:

[0115] V T+1 =V1(1+δ)

[0116] Where δ is the allowable deviation rate.

[0117] Step three: Based on typical historical and predicted scenarios of equivalent load, an intelligent evolutionary algorithm is used to optimize the power generation and pumping scheduling process of the pumped storage power station, and a scheduling plan that can improve quality and efficiency is compiled.

[0118] Based on the typical equivalent load scenario obtained in step 1 and the dispatch model for improving the quality and efficiency of the pumped-storage power station constructed in step 2, the intelligent evolutionary algorithm is used to optimize the power generation and pumping dispatch process of the pumped-storage power station as follows:

[0119] ① Initialize algorithm parameters and encoding decision variables: set evolutionary generation counter t, maximum evolutionary generation T, initial population size M, crossover probability P c , mutation probability P m ; Use real number coding to encode and randomly generate a certain scale of decision variables, i.e. power generation or pumping power of the power station

[0120] ②Evaluate fitness: Use the following fitness function, i.e., the quality and efficiency improvement objective function, to calculate the fitness of each individual in the population;

[0121] maxF=c·ω1·F1-ω2·F2

[0122] ω1+ω2=1

[0123]

[0124]

[0125]

[0126]

[0127] ③ Selection operation: Use the roulette wheel method to select individuals with high fitness to generate a subpopulation with a population size of M;

[0128] ④ Crossover operation: Using the simulated binary crossover operator, the two individuals in the tth generation and Generate the t+1th generation individual x 1 (t+1) and x 2 The specific calculation process of (t+1) is as follows:

[0129]

[0130] in,

[0131]

[0132] Where n is the number of genes encoded in the chromosome, β is the expansion factor or uniform distribution factor, and η c is the cross-distribution index, which is an arbitrary non-negative real number specified by yourself, and u is a random number between 0 and 1;

[0133] ⑤ Mutation operation: Apply the mutation operator to the population and use polynomial mutation to change the gene values ​​of certain loci of the individual strings in the population. The mutation form is:

[0134]

[0135] in,

[0136]

[0137] Where, is the k-th gene in the i-th individual in the t-th generation population. The corresponding gene after mutation is u k and l k are the upper and lower bounds of the variable, ηm is the distribution index, u is a random number between 0 and 1;

[0138] ⑥ Termination condition judgment: If t = T, the individual with the maximum fitness obtained in the evolution process is output as the optimal solution and the calculation is terminated.

[0139] After trial calculation, setting the population size to 500, the evolutionary generations to 200, the crossover probability to 0.9, and the mutation probability to 0.01 can meet the requirements of computational efficiency and convergence.

[0140] The optimal dispatching scheme of the pumped storage power station under the typical daily load scenario from January to December is obtained through calculation. The equivalent load process diagram of the optimized operation and the actual operation is shown in Figure 3 , reflecting the changing trend of the equivalent load of the power grid before and after optimization in different months.

[0141] Pumped storage power stations supplement the load gap by generating electricity during peak load periods, and absorb excess electricity by pumping water during low load periods. Figure 3 It can be seen that after the intelligent dispatching of the pumped-storage power station, the equivalent load curve of the power grid has become smoother and its volatility has been reduced. The process line before optimization had large peaks and troughs, while the optimized curve is more continuous, indicating that the optimized operation of the pumped-storage power station has significantly improved peak-shaving and valley-filling, giving full play to the regulation performance of the hydropower station and effectively reducing the deviation coefficient of the equivalent load. This regulation method achieves power regulation of the equivalent load through power generation or pumping in different time periods, which has a positive effect on the load balance of the power grid, can reduce the pressure on the power grid system operation, and ensure the stable operation of the power system under different load scenarios.

[0142] Furthermore, an embodiment of the present invention provides an intelligent dispatching system for improving the quality and efficiency of a pumped storage power station, comprising:

[0143] The scenario extraction module is used to extract typical daily scenarios of grid load and renewable energy output based on the grid source-load characteristics and renewable energy output characteristics, and determine the typical operating scenarios and operating modes of pumped-storage power stations;

[0144] A model building module is used to establish a scheduling model with quality and efficiency improvement as the optimization objective function and the power generation and pumping power of the pumped storage power station as the decision variables;

[0145] The intelligent solution module is used to optimize the power generation and pumping scheduling processes of pumped-storage power stations based on typical historical and predicted equivalent load scenarios using intelligent evolutionary algorithms, and to develop scheduling plans that can improve quality and efficiency.

[0146] Based on the content of the above system embodiment, as a preferred embodiment, an intelligent scheduling system for improving the quality and efficiency of a pumped storage power station provided in an embodiment of the present invention is further configured to execute the following instructions:

[0147] Based on a multi-year, long-term series of daily output or load time series data from the study area, we analyze the output variation patterns and characteristics on both the power supply and load sides. By studying the randomness, volatility, and intermittency of power output, as well as the source-load correlation, we specifically analyze the grid load characteristics and the spatiotemporal attributes of clean energy output.

[0148] In order to improve the precision of load classification, the Gaussian mixture model clustering algorithm is used to extract typical scenarios of daily load and renewable energy output. Combined with the development trend of regional power grid load and clean energy output, the typical scenarios of net load of the power grid after the priority absorption of renewable energy are further obtained, realizing the integration of data dimensionality reduction and clustering tasks, and comprehensively covering various scenarios of wind, solar and hydropower output.

[0149] On this basis, through operating environment and scenario analysis, the operating environment and operating boundaries of the pumped-storage power station are clarified. Then, based on the historical data of the pumped-storage power station under study, the aforementioned Gaussian mixture model clustering algorithm is used to extract the typical operating scenarios and operating modes of the power station.

[0150] Based on the content of the above system embodiment, as a preferred embodiment, an intelligent scheduling system for improving the quality and efficiency of a pumped storage power station provided in the embodiment of the present invention, wherein the intelligent solution module further includes:

[0151] The first submodule is used to initialize algorithm parameters and encode decision variables;

[0152] The second submodule is used to calculate the quality improvement and efficiency enhancement function and evaluate the fitness;

[0153] The third submodule is used to perform selection, crossover and mutation operations on the population;

[0154] The fourth submodule is used to prepare a scheduling plan based on the optimization results.

[0155] An embodiment of the present invention further provides an electronic device configured in a pumped-storage power station, comprising a memory and a processor, wherein the memory is used to store a computer program. When the processor runs the computer program stored in the memory, the processor executes the intelligent scheduling method for improving the quality and efficiency of the pumped-storage power station, comprising:

[0156] When the electronic device according to the embodiment of the present invention performs intelligent scheduling to improve the quality and efficiency of a pumped-storage power station, based on the source-load characteristics of the power grid and the output characteristics of renewable energy, typical daily scenarios of the power grid load and renewable energy output are extracted to determine the typical operating scenarios and operating modes of the pumped-storage power station; a scheduling model is established with improving quality and efficiency as the optimization objective function and the power generation and pumping power of the pumped-storage power station as decision variables; based on typical historical scenarios and predicted scenarios of equivalent load, an intelligent evolutionary algorithm is used to optimize the power generation and pumping scheduling process of the pumped-storage power station, and a scheduling plan that can improve quality and efficiency is compiled.

[0157] An embodiment of the present invention further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions cause the computer to execute the intelligent scheduling method for improving the quality and efficiency of a pumped storage power station, including:

[0158] Based on the grid source-load characteristics and renewable energy output characteristics, typical daily scenarios of grid load and renewable energy output are extracted to determine the typical operating scenarios and modes of pumped storage power stations;

[0159] Establish a scheduling model with quality and efficiency improvement as the optimization objective function and the power generation and pumping power of the pumped storage power station as the decision variables;

[0160] Based on typical historical and predicted scenarios of equivalent load, an intelligent evolutionary algorithm is used to optimize the power generation and pumping scheduling processes of pumped-storage power stations, and a scheduling plan that can improve quality and efficiency is formulated.

[0161] In summary, the above embodiments can not only accurately extract the operating scenarios of pumped-storage power stations, but also reduce the impact of new energy grid connection while bringing considerable economic benefits, providing technical support for promoting the development and utilization of new energy and the transformation of the power system.

[0162] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent dispatching method for improving the quality and efficiency of a pumped storage power station, characterized in that: include: Based on the grid source-load characteristics and renewable energy output characteristics, typical daily scenarios of grid load and renewable energy output are extracted to determine the typical operating scenarios and modes of pumped storage power stations; A scheduling model is established with quality improvement and efficiency enhancement as the optimization objective function and the power generation and pumping power of the pumped storage power station as the decision variables. The optimization objective function for quality improvement and efficiency enhancement is: ， in: is the objective function for maximizing the power generation benefit of the pumped storage power station, The objective function is to minimize the equivalent load dispersion coefficient; and is the weight coefficient, c is the constant for adjusting the order of magnitude; T is the total number of time periods in the scheduling period; 0-1 variables are introduced, Indicates that the power station is in power generation operation during the t period. Indicates that the power station is in a non-power-generating state during this period. Indicates that the power station is in pumping operation during period t. Indicates that the power station is in non-pumping operation state; are the on-grid electricity price and pumped electricity price of the pumped storage power station in period t, respectively; They represent the power generation and pumping power of the pumped storage power station in period t respectively; The equivalent load of the pumped storage power station before optimization is the original load at period t minus the output of renewable energy; The equivalent load of the pumped storage power station after it is put into operation in period t is the original load minus the output of renewable energy; is the total power load of the entire network system in period t; They represent the predicted output of wind power and photovoltaic power in period t respectively; is the predicted hydropower output in period t; is the power of the pumped storage power station in period t; The power transmitted from the external network to the power grid during the t period, The power transmitted from the power grid to the external grid in period t; When establishing the dispatching model of a pumped storage power station, the power generation and pumping power of the pumped storage power station are used as decision variables, the peak-shaving and valley-filling function of the pumped storage power station is considered, and the daily power generation process of the pumped storage power station is derived. Based on typical historical and predicted scenarios of equivalent load, an intelligent evolutionary algorithm is used to optimize the power generation and pumping scheduling processes of pumped-storage power stations, and a scheduling plan that can improve quality and efficiency is formulated.

2. The intelligent dispatching method for improving the quality and efficiency of a pumped storage power station according to claim 1, characterized in that: Based on the grid source-load characteristics and renewable energy output characteristics, typical daily scenarios of grid load and renewable energy output are extracted to determine the typical operating scenarios and modes of pumped storage power stations, including: Based on the multi-year long-term daily output or load time series data of the study area, the output variation patterns and characteristics are analyzed from the power supply side and the load side using randomness, volatility, intermittency, and source-load correlation indicators, including grid load characteristics and the spatiotemporal attributes of clean energy output; To improve the precision of load classification, Gaussian mixture model clustering was used to extract typical daily load scenarios and renewable energy output scenarios. Combined with the research area's grid load and clean energy output trends, typical grid net load scenarios after prioritizing renewable energy were obtained, integrating data dimensionality reduction and clustering tasks to comprehensively cover various wind, solar, and hydropower output scenarios. Through operating environment and scenario analysis, the operating environment and operating boundaries of the pumped-storage power station are clarified. Then, based on the historical data of the pumped-storage power station under study, the aforementioned Gaussian mixture model clustering algorithm is used to extract the typical operating scenarios and operating modes of the power station.

3. The intelligent dispatching method for improving the quality and efficiency of a pumped storage power station according to claim 1, characterized in that: Each reservoir / power station in the dispatching model meets the following constraints on power, water volume, and water energy conversion: Active power balance constraints of the entire network; power generation and pumping power limits of pumped-storage power stations; operating condition constraints of pumped-storage power stations; water-energy conversion relationship of pumped-storage power stations; water balance of the upper and lower reservoirs of pumped-storage power stations; water storage capacity constraints of the upper and lower reservoirs of pumped-storage power stations; and storage capacity constraints at the beginning and end of dispatching.

4. The intelligent dispatching method for improving the quality and efficiency of a pumped storage power station according to claim 1, characterized in that: The intelligent evolutionary algorithm is used to optimize the operating conditions of the pumped storage power station and its power generation or pumping power process in each period during the scheduling period according to the collaborative scheduling module, including: Initialize algorithm parameters and encode decision variables; evaluate fitness; perform selection, crossover, and mutation operations; and determine termination conditions.

5. An intelligent dispatching system for improving the quality and efficiency of a pumped storage power station, characterized in that: include: The scenario extraction module is used to extract typical daily scenarios of grid load and renewable energy output based on the grid source-load characteristics and renewable energy output characteristics, and determine the typical operating scenarios and operating modes of pumped-storage power stations; The model building module is used to establish a scheduling model with quality improvement and efficiency enhancement as the optimization objective function and the power generation and pumping power of the pumped storage power station as the decision variables; the optimization objective function for quality improvement and efficiency enhancement is: ， in: is the objective function for maximizing the power generation benefit of the pumped storage power station, The objective function is to minimize the equivalent load dispersion coefficient; and is the weight coefficient, c is the constant for adjusting the order of magnitude; T is the total number of time periods in the scheduling period; 0-1 variables are introduced, Indicates that the power station is in power generation operation during the t period. Indicates that the power station is in a non-power-generating state during this period. Indicates that the power station is in pumping operation during period t. Indicates that the power station is in non-pumping operation state; are the on-grid electricity price and pumped electricity price of the pumped storage power station in period t, respectively; They represent the power generation and pumping power of the pumped storage power station in period t respectively; The equivalent load of the pumped storage power station before optimization is the original load at period t minus the output of renewable energy; The equivalent load of the pumped storage power station after it is put into operation in period t is the original load minus the output of renewable energy; is the total power load of the entire network system in period t; They represent the predicted output of wind power and photovoltaic power in period t respectively; is the predicted hydropower output in period t; is the power of the pumped storage power station in period t; The power transmitted from the external network to the power grid during the t period, The power transmitted from the power grid to the external grid in period t; When establishing the dispatching model of a pumped storage power station, the power generation and pumping power of the pumped storage power station are used as decision variables, the peak-shaving and valley-filling function of the pumped storage power station is considered, and the daily power generation process of the pumped storage power station is derived. The intelligent solution module is used to optimize the power generation and pumping scheduling processes of pumped-storage power stations based on typical historical and predicted equivalent load scenarios using intelligent evolutionary algorithms, and to develop scheduling plans that can improve quality and efficiency.

6. The intelligent dispatching system for improving the quality and efficiency of a pumped storage power station according to claim 5, characterized in that: The scene extraction module is further configured to execute the following instructions: Based on the multi-year long-term daily output or load time series data of the study area, the output variation patterns and characteristics of the power supply side and the load side are analyzed. By studying the randomness, volatility, intermittency and source-load correlation of the power supply output, the grid load characteristics and the spatiotemporal attributes of clean energy output are specifically analyzed. To improve the precision of load classification, a Gaussian mixture model clustering algorithm was used to extract typical scenarios of daily load and renewable energy output. Combined with the development trends of regional grid load and clean energy output, this algorithm further derived typical scenarios of grid net load after prioritizing renewable energy consumption. This integrated data dimensionality reduction and clustering tasks, comprehensively covering various scenarios of wind, solar, and hydropower output. Through operating environment and scenario analysis, the operating environment and operating boundaries of the pumped-storage power station are clarified. Then, based on the historical data of the pumped-storage power station under study, the aforementioned Gaussian mixture model clustering algorithm is used to extract the typical operating scenarios and operating modes of the power station.

7. The intelligent dispatching system for improving the quality and efficiency of a pumped storage power station according to claim 5, characterized in that: The intelligent solution module further includes: The first submodule is used to initialize algorithm parameters and encode decision variables; The second submodule is used to calculate the quality improvement and efficiency enhancement function and evaluate the fitness; The third submodule is used to perform selection, crossover and mutation operations on the population; The fourth submodule is used to prepare a scheduling plan based on the optimization results.

8. An electronic device, arranged in a pumped storage power station, characterized in that: It includes a memory and a processor, the memory is used to store a computer program, and when the processor runs the computer program stored in the memory, the processor executes the intelligent scheduling method for improving the quality and efficiency of a pumped storage power station as described in any one of claims 1 to 4.

9. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to execute the intelligent scheduling method for improving the quality and efficiency of a pumped storage power station as described in any one of claims 1 to 4.

Images