Optimized scheduling method and system for source-load coordinated water-wind-solar complementary system

Abstract

The invention belongs to the technical field of power system planning, and more specifically relates to a source-load collaborative water-wind-solar complementary system optimization scheduling method and system, and the method comprises the steps: carrying out the preprocessing and time sequence prediction of an energy load historical data set, obtaining a target energy load prediction set, building a target energy scheduling model through the target energy load prediction set, and carrying out the optimization scheduling of a water-wind-solar complementary system. And solving the target energy scheduling model through an improved multi-target single-corner whale optimization algorithm to obtain an optimal energy scheduling scheme capable of accurately meeting two targets of the maximum total power generation amount and the minimum source-load difference. Through the deviation between the real operation values and the predicted values of the photovoltaic output and the wind power output after the execution of the target energy scheduling scheme, the quantitative evaluation of the hydroelectric compensation risk is realized, and the adaptability and robustness during the scheduling of the water-wind-solar complementary system can be effectively improved.

Description

Technical Field

[0001] This application belongs to the field of power system planning, and more specifically, relates to an optimized scheduling method and system for a water-wind-solar complementary system with source-load coordination. Background Technology

[0002] The inherent intermittency, volatility, and randomness of wind and solar energy pose significant challenges to the real-time power balance and safe, stable operation of power systems. Against this backdrop, utilizing flexible power sources such as hydropower to form a multi-energy complementary system with wind and solar power, and through the rapid start-up, shutdown, and output regulation of hydropower stations, can effectively mitigate fluctuations in wind and solar power output, transforming unstable energy sources into stable, reliable, and clean electricity for transmission to the grid.

[0003] Currently, the optimal scheduling models for hydro-wind-solar hybrid systems mostly focus on a single objective on the generation side, such as maximizing total system power generation or minimizing operational resource consumption. However, the essential requirement of a power system is instantaneous supply-demand balance. Considering only the demand objective on the generation side while neglecting the demand objective on the load side makes it difficult to ensure that the output curves of hydro-wind-solar systems after complementary scheduling match the actual electricity demand. This may lead to serious source-load imbalance risks, resulting in energy scheduling schemes generated by the optimal scheduling models failing to meet actual power supply needs. Summary of the Invention

[0004] To address the aforementioned deficiencies in existing technologies, this application provides an optimized scheduling method and system for a water-wind-solar hybrid system with source-load coordination. The aim is to generate an energy scheduling scheme that can meet the multi-objective needs of both the energy supply side and the load side based on the historical energy load data of the water-wind-solar hybrid system.

[0005] In a first aspect, this application provides an optimized scheduling method for a water-wind-solar hybrid system with source-load coordination, comprising: S1. Preprocess the acquired historical energy load dataset and perform time-series prediction on the preprocessed historical energy load dataset based on the target time-series prediction model to obtain the target energy load prediction set, which includes various types of energy output prediction data and power load prediction data. S2. Based on the predicted output data of each energy source and the predicted power load data, construct a target energy dispatch model. The target energy dispatch model includes a set of multiple objective functions and objective constraint functions. S3. Based on the improved multi-objective narwhal optimization algorithm and the set of objective constraint functions, each objective function is solved to obtain the objective energy scheduling scheme, and the operating parameters of the water-wind-solar hybrid system are scheduled based on the objective energy scheduling scheme.

[0006] Furthermore, the acquired historical energy load dataset is preprocessed, including: Obtain historical data of energy output and power load from the historical energy load dataset, and perform missing value imputation and outlier removal operations on each historical energy output and power load dataset.

[0007] The data in the historical energy load dataset may have some missing or abrupt changes in the time series due to the bias during collection. Therefore, preprocessing the data can ensure the prediction accuracy of the subsequent target time series prediction model.

[0008] Furthermore, the energy output forecast data includes hydropower output, wind power output, and photovoltaic output, while the power load forecast data includes the power load demand of hydro-wind-solar hybrid systems.

[0009] Furthermore, based on the power output forecast data and electricity load forecast data of each energy source, a target energy dispatch model is constructed, including: Based on the predicted power output data of each energy source, the total power generation of the hydro-wind-solar hybrid system is obtained, and the first objective function is constructed with the goal of maximizing the total power generation. Based on the power load forecast data and the energy output forecast data, the source-load difference fluctuation of the hydro-wind-solar hybrid system is obtained. With the goal of minimizing the source-load difference fluctuation, a second objective function is constructed. The source-load difference fluctuation is used to characterize the deviation between the power load forecast data and the energy output forecast data.

[0010] Furthermore, a target energy dispatch model is constructed, including: Establish a set of objective constraint functions, which includes multiple sets of constraint functions. Each constraint function is used to constrain the range of values ​​of at least one functional variable, including hydropower output, wind power output, and photovoltaic output.

[0011] Furthermore, based on the improved multi-objective narwhal optimization algorithm and the set of objective constraint functions, each objective function is solved to obtain the objective energy scheduling scheme, including: S31. Based on the set of objective constraint functions and each objective function, generate a large number of initial energy scheduling schemes, and construct an initial population with each initial energy scheduling scheme as an individual. S32. Use the first objective function and the second objective function as fitness functions, and initialize the maximum preset number of iterations, the target position of each individual, the prey energy, and the decay coefficient. S33. Obtain the target fitness of each individual based on the fitness function, and obtain the non-dominated solutions in the initial population based on the target fitness of each individual, and store the non-dominated solutions in the target archive. S34. Based on the hypervolume index and distribution index, obtain the improvement of fitness of each target, and based on the improvement of target fitness and the current prey energy, adaptively switch the operation phase of each individual. The operation phase includes the exploration phase and the predation phase. S35. Based on the operation stage of each entity, update the prey energy and target position of each entity, repeat step S33 until the current iteration number reaches the maximum preset iteration number, and take the initial energy scheduling scheme corresponding to the non-dominated solution with the lowest prey energy in the target archive as the target energy scheduling scheme.

[0012] Among them, the improvement of target fitness and current prey energy, which are derived from the operational stage of each individual, is the main improvement point of the multi-target narwhal optimization algorithm. This improvement can effectively improve the predation efficiency in the predation stage, while avoiding insufficient exploration space in the exploration stage, which would cause the predation result in the predation stage to fall into a local optimum, and thus effectively obtain the global optimal non-dominated solution in the initial population.

[0013] Furthermore, after scheduling the operating parameters of the hydro-wind-solar hybrid system based on the target energy dispatch scheme, it also includes: Based on the scheduling results of the target energy dispatch scheme on the hydro-wind-solar hybrid system, the actual energy output data of the hydro-wind-solar hybrid system is obtained. The actual energy output data includes the actual hydropower output, the actual wind power output, and the actual photovoltaic output. The first deviation value between actual wind power output and the second deviation value between actual photovoltaic output are obtained. Based on the first deviation value and the second deviation value and the preset risk quantification algorithm, the quantitative assessment result of the hydropower compensation risk of the hydro-wind-solar hybrid system is obtained.

[0014] Among them, the risk of hydropower compensation is determined by the deviation between the predicted values ​​and the actual operating values ​​of photovoltaic and wind power output. If the actual operating value is less than the predicted value, it means that the actual operating value of wind and solar power is insufficient to support the load demand, and hydropower needs to increase its output to compensate. This may lead to an increase in the peak-shaving and frequency regulation pressure of hydropower. Therefore, quantifying the risk of hydropower compensation is conducive to effective early warning of the operational safety of hydro-wind-solar complementary systems.

[0015] Secondly, this application also provides an optimized scheduling system for a water-wind-solar hybrid system with source-load coordination, used to implement any of the methods in the first aspect, including: The preprocessing module is used to preprocess the acquired historical energy load dataset; The time-series forecasting module is used to perform time-series forecasting on the preprocessed historical energy load dataset based on the target time-series forecasting model, so as to obtain the target energy load forecast set. The energy dispatch model construction module is used to construct a target energy dispatch model based on the output forecast data of each energy source and the power load forecast data. The energy dispatch scheme acquisition module is used to solve each objective function based on the improved multi-objective narwhal optimization algorithm and the set of objective constraint functions to obtain the target energy dispatch scheme; The energy dispatch scheme execution module is used to schedule the operating parameters of the hydro-wind-solar hybrid system based on the target energy dispatch scheme.

[0016] Thirdly, this application also provides an electronic device, characterized in that it comprises: At least one memory for storing computer programs; At least one processor is configured to execute a program stored in the memory, such that, when the program is executed, the processor performs the method described in the first aspect or any possible implementation thereof.

[0017] Fourthly, this application also provides a computer-readable storage medium storing a computer program that, when run on a processor, causes the processor to perform the method described in the first aspect or any possible implementation thereof.

[0018] In summary, the technical solutions conceived by this invention have the following beneficial effects compared with the prior art: This application provides a source-load coordinated hydro-wind-solar hybrid system optimization scheduling method and system. 1. By preprocessing and time-series prediction of historical energy load datasets, a target energy load prediction set is obtained. A target energy scheduling model is constructed using this prediction set. An improved multi-objective unicorn optimization algorithm is then used to solve the target energy scheduling model, yielding an optimal energy scheduling scheme that accurately satisfies both the maximum total power generation and the minimum source-load difference. 2. By analyzing the deviation between the actual and predicted values ​​of photovoltaic and wind power output after the target energy scheduling scheme is implemented, a quantitative assessment of hydropower compensation risk is achieved, thereby effectively improving the adaptability and robustness of the hydro-wind-solar hybrid system scheduling. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application or related technologies, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1This is a flowchart illustrating the optimized scheduling method for a hydro-wind-solar hybrid system provided in an embodiment of this application.

[0021] Figure 2 This is a schematic diagram of the structure of the optimized scheduling system for the hydro-wind-solar hybrid system provided in the embodiments of this application.

[0022] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0023] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0024] In the following description, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. The following description provides multiple embodiments of this application, which can be substituted or combined with each other. Therefore, this application can also be considered to include all possible combinations of the same and / or different embodiments described. Thus, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then this application should also be considered to include embodiments containing one or more other possible combinations of A, B, C, and D, even if such embodiments are not explicitly described in the following text.

[0025] The following description provides examples and does not limit the scope, applicability, or examples set forth in the claims. Changes may be made to the function and arrangement of the described elements without departing from the scope of this application. Various processes or components may be appropriately omitted, substituted, or added to the examples. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Furthermore, features described with respect to some examples may be combined into other examples.

[0026] Figure 1 This is a flowchart illustrating the optimized scheduling method for a water-wind-solar hybrid system with source-load coordination provided in an embodiment of this application. Figure 1 As shown, the method includes at least the following steps: S1. The acquired historical energy load dataset is preprocessed, and time-series prediction is performed on the preprocessed historical energy load dataset based on the target time-series prediction model to obtain the target energy load prediction set, which includes various types of energy output prediction data and power load prediction data.

[0027] In one possible implementation, the acquired historical energy load dataset is preprocessed, including: Obtain historical data of energy output and power load from the historical energy load dataset, and perform missing value imputation and outlier removal operations on each historical energy output and power load dataset.

[0028] In this embodiment, the executing entity of the source-load coordinated hydro-wind-solar hybrid system optimization scheduling method can be the central controller of the hydro-wind-solar hybrid system, and the energy load historical dataset is the historical data recorded by the hydro-wind-solar hybrid system. Due to biases during acquisition, some nodes in this historical data may have missing or abrupt changes in their time series values. Therefore, preprocessing this data ensures the prediction accuracy of the subsequent target time series prediction model. Missing values ​​can be filled by averaging the values ​​of multiple nodes before and after the node containing the missing value. Nodes with abrupt changes in value can be determined using the slope of the fitting curves corresponding to various types of data in the historical data. The target time series prediction model can employ a Long Short-Term Memory Network (LSTM) to predict various types of data in the energy load historical dataset in the form of time series. The energy output prediction data includes hydropower output, wind power output, and photovoltaic output, while the power load prediction data includes the power load demand of the hydro-wind-solar hybrid system. These demands can be the sum of the power loads required for the prediction of hydropower, wind power, and photovoltaic equipment.

[0029] S2. Based on the predicted output data of each energy source and the predicted power load data, construct a target energy dispatch model. The target energy dispatch model includes a set of multiple objective functions and objective constraint functions.

[0030] In one possible implementation, a target energy dispatch model is constructed based on the power output forecast data and power load forecast data of each energy source, including: Based on the predicted power output data of each energy source, the total power generation of the hydro-wind-solar hybrid system is obtained, and the first objective function is constructed with the goal of maximizing the total power generation. Based on power load forecast data and energy output forecast data, the source-load difference fluctuation of the hydro-wind-solar hybrid system is obtained. With the goal of minimizing the source-load difference fluctuation, a second objective function is constructed. The source-load difference fluctuation is used to characterize the deviation between the power load forecast data and the energy output forecast data.

[0031] In this embodiment, the target energy dispatch model is constructed considering both the source and load sides. For the source side, the core objective is to maximize the utilization of clean energy sources such as hydropower, wind power, and solar power, thereby increasing the system's total energy output and economic benefits, and driving hydropower to actively compensate for fluctuations in wind and solar power. Therefore, the first objective function is set to maximize the system's total power generation, which is composed of the sum of the outputs of all energy sources. For the load side, the core objective is to ensure the safe and stable operation of the power grid, achieve real-time power balance between power generation and consumption, and reduce the system's regulation costs. Therefore, the second objective function is set to minimize the source-load difference fluctuation.

[0032] For ease of understanding, the embodiments of this application will be described from the perspective of objective function and constraint function using the following functions.

[0033] The objective function includes: (1) The objective function on the source side is to maximize the total power generation of the system. ):

[0034] in, for Total output of the time-slot complementary system For the scheduling period, This refers to the scheduling period.

[0035] (2) The objective function on the load side is to minimize the fluctuation of the source load difference. ):

[0036] in, For power output fluctuation, For the fluctuation of residual load, This is a angular oscillation. , , These are the weighting coefficients.

[0037] The set of objective constraint functions includes: (1) Hydropower output constraints:

[0038] in, Power output for hydroelectricity, , This represents the upper and lower limits of output.

[0039] (2) Water balance constraints:

[0040]

[0041] in, For storage capacity, For inbound flow, To discard water, , These are the upper and lower limits for water disposal.

[0042] (3) Storage capacity constraints:

[0043] in, , These are the upper and lower limits of the storage capacity.

[0044] (4) Water level constraints:

[0045] in, For water level, , These are the upper and lower limits of the water level.

[0046] (5) Wind power output constraints:

[0047] in, To contribute to wind power, This is the upper limit of wind power output.

[0048] (6) Photovoltaic output constraints:

[0049] in, Contribute to photovoltaic power The upper limit of photovoltaic output, water balance constraints, reservoir capacity constraints, and water level constraints are used to constrain the operating parameters of hydropower stations corresponding to hydropower output.

[0050] S3. Based on the improved multi-objective narwhal optimization algorithm and the set of objective constraint functions, each objective function is solved to obtain the objective energy scheduling scheme, and the operating parameters of the water-wind-solar hybrid system are scheduled based on the objective energy scheduling scheme.

[0051] In one possible implementation, based on the improved multi-objective narwhal optimization algorithm and a set of objective constraint functions, each objective function is solved to obtain the objective energy scheduling scheme, including: S31. Based on the set of objective constraint functions and each objective function, generate a large number of initial energy scheduling schemes, and construct an initial population with each initial energy scheduling scheme as an individual. S32. Use the first objective function and the second objective function as fitness functions, and initialize the maximum preset number of iterations, the target position of each individual, the prey energy, and the decay coefficient. S33. Obtain the target fitness of each individual based on the fitness function, and obtain the non-dominated solutions in the initial population based on the target fitness of each individual, and store the non-dominated solutions in the target archive. S34. Based on the hypervolume index and distribution index, obtain the improvement of fitness of each target, and based on the improvement of target fitness and the current prey energy, adaptively switch the operation phase of each individual. The operation phase includes the exploration phase and the predation phase. S35. Based on the operation stage of each entity, update the prey energy and target position of each entity, repeat step S33 until the current iteration number reaches the maximum preset iteration number, and take the initial energy scheduling scheme corresponding to the non-dominated solution with the lowest prey energy in the target archive as the target energy scheduling scheme.

[0052] In this embodiment, the improved multi-objective narwhal optimization algorithm, compared to existing narwhal optimization algorithms, employs a method that considers both hypervolume (HV) and spacing indices to calculate the improvement in fitness for each objective. Based on this improvement and the current prey energy, it adaptively switches the operational phase of each individual. HV is an index evaluating convergence and diversity; a higher value indicates better convergence and diversity. Spacing is a uniformity index; a lower value indicates a more uniform solution set, as shown in the following formula:

[0053]

[0054]

[0055]

[0056]

[0057] in, This indicates the extent of the improvement in target fitness. and Let them represent the best individual in the population and the th individual, respectively. t -1 individual, This represents the Lebesgue measure, used to measure volume; Represents the union of sets; Indicates the reference point and the first solution in the solution set. The hypervolume formed by the solutions; Indicates the number of solutions in the target archive; Indicates the first The minimum distance from one solution to all other solutions; Indicates all The average value, Indicates the dynamic conversion coefficient. Indicates the prey's energy. and This represents a preset constant.

[0058] When updating the prey energy and target location of each individual based on its operational phase, the dynamic transition coefficient between the exploration and predation phases should be considered. Determine how to perform a location update. When During the exploration phase, when During the predation phase, this place The value is a random number between [0, 1]. Specifically, when the fitness function improves significantly, the algorithm tends to be in a large-scale exploration phase; when the fitness function improves slightly, it indicates that the algorithm is close to the optimal solution and tends to be in the predation phase; furthermore, when the fitness function improves negatively, the algorithm needs to explore a larger space to avoid getting trapped in local optima, thus tending to be in the exploration phase. When the prey energy is high, the probability of a narwhal successfully preying on it is low, and the algorithm tends to be in the exploration phase; when the prey energy is low, the probability of a narwhal successfully preying on it is high, thus the algorithm tends to be in the predation phase.

[0059] In one possible implementation, after scheduling the operating parameters of the hydro-wind-solar hybrid system based on the target energy dispatch scheme, the method further includes: Based on the scheduling results of the target energy dispatch scheme on the hydro-wind-solar hybrid system, the actual energy output data of the hydro-wind-solar hybrid system is obtained. The actual energy output data includes the actual hydropower output, the actual wind power output, and the actual photovoltaic output. The first deviation value between actual wind power output and the second deviation value between actual photovoltaic output are obtained. Based on the first deviation value and the second deviation value and the preset risk quantification algorithm, the quantitative assessment result of the hydropower compensation risk of the hydro-wind-solar hybrid system is obtained.

[0060] In this embodiment of the application, since there is a deviation between the predicted value and the actual operating value of wind power and photovoltaic power output, if the actual operating value is less than the predicted value, it means that the actual operating value of wind and solar power is insufficient to support the load demand, and hydropower needs to increase its output to compensate, which leads to an increase in the peak-shaving and frequency regulation pressure of hydropower and a certain risk of hydropower compensation. This can be achieved by using the CVaR (Conditional Value at Risk) algorithm and related calculation tools.

[0061] In one possible implementation, after scheduling the operating parameters of the hydro-wind-solar hybrid system based on the target energy dispatch scheme, the method further includes: Based on the scheduling results of the target energy dispatch scheme on the hydro-wind-solar hybrid system, the actual energy output data and actual total load data of the hydro-wind-solar hybrid system are obtained. The actual energy output data includes the actual hydropower output, actual wind power output and actual photovoltaic output, and the actual total load data is the actual total power load demand required by the hybrid system. The actual total output of the hydro-wind-solar hybrid system is obtained based on actual energy output data. Based on a preset risk quantification algorithm and the deviation between the actual total output and the actual total power load demand, the quantitative assessment result of the source-load mismatch risk of the hydro-wind-solar hybrid system is obtained.

[0062] In this embodiment, the source-load mismatch risk is quantitatively assessed. The operational risk factor is the deviation between the total output of the complementary system and the grid load demand. Both when the total output of the complementary system is greater than or less than the grid load demand, source-load mismatch risk will exist. This can be achieved using the CVaR (Conditional Value at Risk) algorithm and related calculation tools.

[0063] Figure 2 A schematic diagram of the structure of the source-load coordinated water-wind-solar hybrid system optimization scheduling system provided in the embodiments of this application is shown below. Figure 2 As shown, the system includes at least: The preprocessing module is used to preprocess the acquired historical energy load dataset; The time-series forecasting module is used to perform time-series forecasting on the preprocessed historical energy load dataset based on the target time-series forecasting model, so as to obtain the target energy load forecast set. The energy dispatch model construction module is used to construct a target energy dispatch model based on the output forecast data of each energy source and the power load forecast data. The energy dispatch scheme acquisition module is used to solve each objective function based on the improved multi-objective narwhal optimization algorithm and the set of objective constraint functions to obtain the target energy dispatch scheme; The energy dispatch scheme execution module is used to schedule the operating parameters of the hydro-wind-solar hybrid system based on the target energy dispatch scheme.

[0064] like Figure 3 As shown, Figure 3This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: a processor 301, a communications interface 302, a memory 303, and a communication bus 304. The processor 301, communications interface 302, and memory 303 communicate with each other via the communication bus 304. The processor 301 can call software instructions stored in the memory 303 to execute the methods described in the above embodiments.

[0065] Furthermore, the logical instructions in the aforementioned memory 303 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application.

[0066] Based on the methods in the above embodiments, this application provides a computer-readable storage medium storing a computer program that, when run on a processor, causes the processor to execute the methods in the above embodiments.

[0067] Based on the methods in the above embodiments, this application provides a computer program product that, when run on a processor, causes the processor to execute the methods in the above embodiments.

[0068] It is understood that the processor in the embodiments of this application can be a CPU (Central Processing Unit), or other general-purpose processors, DSPs (Digital Signal Processors), ASICs (Application Specific Integrated Circuits), FPGAs (Field Programmable Gate Arrays), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor.

[0069] The method steps in this application embodiment can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory (RAM), flash memory, ROM (Read-only Memory), PROM (Programmable ROM), EPROM (Erasable PROM), EEPROM (Electrically Erasable EPROM), registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can reside in an ASIC.

[0070] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in or transmitted through a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line DSL) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., SSD (Solid State Disk)).

[0071] It is understood that the various numerical designations used in the embodiments of this application are merely for the convenience of description and are not intended to limit the scope of the embodiments of this application.

[0072] Those skilled in the art will readily understand that the above are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A source-load collaborative water, wind and light complementary system optimal scheduling method, characterized in that, The method comprises the following steps: S1, preprocessing the obtained energy load historical data set, and performing time series prediction on the preprocessed energy load historical data set based on a target time series prediction model to obtain a target energy load prediction set, wherein the target energy load prediction set comprises energy output prediction data and power load prediction data of multiple types; S2, constructing a target energy scheduling model based on the energy output prediction data and the power load prediction data, wherein the target energy scheduling model comprises a plurality of target functions and a target constraint function set; S3, solving each target function based on an improved multi-objective orca optimization algorithm and the target constraint function set to obtain a target energy scheduling scheme, and scheduling the operating parameters of the water-wind-solar complementary system based on the target energy scheduling scheme.

2. The method of claim 1, wherein, The preprocessing of the obtained energy load historical data set comprises: obtaining energy output historical data and power load historical data in the energy load historical data set, and performing missing value filling and outlier removal operations on each of the energy output historical data and the power load historical data.

3. The method of claim 2, wherein, The energy output prediction data comprises water power output, wind power output and photovoltaic output, and the power load prediction data comprises power load demand of the water-wind-solar complementary system.

4. The method of claim 3, wherein, The construction of the target energy scheduling model based on the energy output prediction data and the power load prediction data comprises: based on each of the energy output prediction data, obtaining the total power generation of the water-wind-solar complementary system, and constructing a first target function with the goal of maximizing the total power generation; based on each of the power load prediction data and each of the energy output prediction data, obtaining the source-load difference fluctuation of the water-wind-solar complementary system, and constructing a second target function with the goal of minimizing the source-load difference fluctuation, wherein the source-load difference fluctuation is used to represent the deviation between the power load prediction data and the energy output prediction data.

5. The method of claim 4, wherein, The construction of the target energy scheduling model comprises: establishing a target constraint function set, wherein the target constraint function set comprises a plurality of constraint functions, and the constraint functions are used to constrain the value range of at least one function variable, and the function variable comprises water power output, wind power output and photovoltaic output.

6. The method of claim 5, wherein, The solving of each target function based on the improved multi-objective orca optimization algorithm and the target constraint function set to obtain a target energy scheduling scheme comprises: S31, generating a large number of initial energy scheduling schemes based on the target constraint function set and each target function, and constructing an initial population by taking each initial energy scheduling scheme as an individual; S32, taking the first target function and the second target function as an adaptive function, and initializing a maximum preset iteration number, a target position of each individual, a prey energy and a decay coefficient; S33, obtaining the target fitness of each individual based on the adaptive function, and obtaining non-dominated solutions in the initial population based on the target fitness of each individual, and storing the non-dominated solutions in a target archive; S34, based on the hyper-volume index and the distribution index, obtain an improvement range of each target fitness, and adaptively switch an operation stage in which each individual is located based on the improvement range of the target fitness and the current prey energy, the operation stage including an exploration stage and a predation stage; S35, based on the operation stage in which each individual is located, update the prey energy and the target position of each individual, repeat step S33 until the current iteration number reaches the maximum preset iteration number, and take the initial energy scheduling scheme corresponding to the non-dominated solution with the lowest prey energy in the target archive as a target energy scheduling scheme.

7. The method of claim 6, wherein, After the operation parameters of the water-wind-solar complementary system are scheduled based on the target energy scheduling scheme, the method further includes: Based on the operation parameter scheduling result of the water-wind-solar complementary system based on the target energy scheduling scheme, obtain actual energy output data of the water-wind-solar complementary system, the actual energy output data including actual hydroelectric output, actual wind power output and actual photovoltaic output; Obtain a first deviation value between the actual wind power output and the wind power output, a second deviation value between the actual photovoltaic output and the photovoltaic output, and a quantitative evaluation result of a hydroelectric compensation risk of the water-wind-solar complementary system based on the first deviation value and the second deviation value and a preset risk quantification algorithm.

8. A source-load coordinated water, wind and light complementary system optimal scheduling system, used for implementing the method of any one of claims 1-7, characterized in that, It includes: A preprocessing module for preprocessing an obtained energy load historical data set; A time series prediction module for performing time series prediction on the preprocessed energy load historical data set based on a target time series prediction model to obtain a target energy load prediction set; An energy scheduling model construction module for constructing a target energy scheduling model based on each energy output prediction data and power load prediction data; An energy scheduling scheme acquisition module for solving each target function based on an improved multi-objective orca optimization algorithm and the target constraint function set to obtain a target energy scheduling scheme; An energy scheduling scheme execution module for scheduling operation parameters of a water-wind-solar complementary system based on the target energy scheduling scheme.

9. An electronic device, comprising: It includes: At least one memory for storing a computer program; At least one processor for executing the program stored in the memory, when the program stored in the memory is executed, the processor is used to execute the method of any one of claims 1-7.

10. A computer readable storage medium having a computer program stored thereon, the computer readable storage medium having instructions stored therein, when the instructions are run on a computer or a processor, the computer or the processor executes the method of any one of claims 1-7.

Images