Optimization control method, device, equipment and storage medium for power supply vehicle

Abstract

The present invention discloses an optimization control method, device, equipment and storage medium for a power supply vehicle. The method includes: in response to optimization control requests for multiple power supply vehicles in a grid-connected operation environment, determining a target power supply vehicle for grid-connected operation, and collecting historical operation data of each target power supply vehicle within a preset time period; based on a preset grid load model, state model and environmental factor model, determining the predicted operation data of each target power supply vehicle according to the historical operation data; determining the target output power corresponding to each target energy vehicle according to the target neural network model and the predicted operation data, so as to optimize and control each target energy vehicle. The technical solution of the present invention can comprehensively analyze the operation data of the power supply vehicle, thereby using the neural network model to predict the accurate output power, realize precise control of the target energy vehicle, improve the efficiency of the grid-connected operation of the power supply vehicle, and enhance the stability of the power grid.

Description

Technical Field

[0001] The present invention relates to the field of power grids, and in particular to an optimization control method, device, equipment and storage medium for a power supply vehicle. Background Art

[0002] With the increasing popularity of renewable energy and the continuous improvement of the intelligence level of power grids, power supply vehicles, as an innovative means of energy supply, are of great significance in ensuring the safe, stable and efficient operation of the power grid due to their efficiency and stability in grid-connected operation.

[0003] Therefore, how to conduct a comprehensive analysis of the operating data of the power supply vehicle, so as to use the neural network model to predict the accurate output power, realize the precise control of the target energy vehicle, improve the efficiency of the power supply vehicle's grid-connected operation, and enhance the stability of the power grid, is an urgent problem to be solved. Summary of the Invention

[0004] The present invention provides an optimization control method, device, equipment and storage medium for a power supply vehicle to achieve precise control of a target energy vehicle, improve the efficiency of the power supply vehicle's grid-connected operation, and enhance the stability of the power grid.

[0005] According to one aspect of the present invention, there is provided a method for optimizing control of a power supply vehicle, comprising:

[0006] In response to a request for optimized control of multiple power supply vehicles in a grid-connected operation environment, a target power supply vehicle for grid-connected operation is determined, and historical operating data of each target power supply vehicle within a preset time period is collected;

[0007] Based on the preset grid load model, state model and environmental factor model, and according to historical operation data, the predicted operation data of each target power supply vehicle is determined;

[0008] According to the target neural network model and predicted operating data, the target output power corresponding to each target energy vehicle is determined to optimize the control of each target energy vehicle.

[0009] According to another aspect of the present invention, there is provided an optimization control device for a power supply vehicle, comprising:

[0010] The acquisition module is used to respond to the optimization control request for multiple power supply vehicles in the grid-connected operation environment, determine the target power supply vehicle for grid-connected operation, and collect the historical operation data of each target power supply vehicle within a preset time period;

[0011] A determination module is used to determine the predicted operating data of each target power supply vehicle based on a preset grid load model, state model, and environmental factor model and according to historical operating data;

[0012] The control module is used to determine the target output power corresponding to each target energy vehicle based on the target neural network model and predicted operation data, so as to optimize the control of each target energy vehicle.

[0013] According to another aspect of the present invention, an electronic device is provided, comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the optimization control method of the power supply vehicle according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the optimization control method of the power supply vehicle according to any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the optimization control method of the power supply vehicle according to any embodiment of the present invention.

[0019] The technical solution of the embodiment of the present invention, in response to the optimization control request for multiple power supply vehicles in the grid-connected operation environment, determines the target power supply vehicle for grid-connected operation, and collects the historical operation data of each target power supply vehicle within a preset time period; based on the preset grid load model, state model and environmental factor model, the predicted operation data of each target power supply vehicle is determined according to the historical operation data; based on the target neural network model and the predicted operation data, the target output power corresponding to each target energy vehicle is determined to optimize the control of each target energy vehicle. By comprehensively analyzing the operating data of the power supply vehicle and using the neural network model to predict the accurate output power, it is possible to achieve precise control of the target energy vehicle, improve the efficiency of the grid-connected operation of the power supply vehicle, and enhance the stability of the power grid.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 This is a flow chart of an optimization control method for a power supply vehicle provided in the first embodiment of the present invention;

[0023] Figure 2 This is a flow chart of an optimization control method for a power supply vehicle provided in the second embodiment of the present invention;

[0024] Figure 3 This is a structural block diagram of an optimization control device for a power supply vehicle provided in a third embodiment of the present invention;

[0025] Figure 4 It is a structural diagram of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solutions of the present invention, 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 embodiments described are only 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 efforts should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", "target", "candidate", "alternative", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0028] Example 1

[0029] Figure 1This is a flow chart of an optimization control method for a power supply vehicle provided in the first embodiment of the present invention; this embodiment is applicable to the case of optimizing and controlling the output power of multiple power supply vehicles in a grid-connected environment. The method can be executed by an optimization control device of the power supply vehicle. The optimization control device of the power supply vehicle can be implemented in the form of hardware and / or software. The optimization control device of the power supply vehicle can be configured in an electronic device, such as an electronic device with an optimization control function for a power supply vehicle, and executed by a grid-connected control system, such as Figure 1 As shown, the optimization control method of the power supply vehicle includes:

[0030] S101. In response to an optimization control request for multiple power supply vehicles in a grid-connected operation environment, a target power supply vehicle for grid-connected operation is determined, and historical operation data of each target power supply vehicle within a preset time period is collected.

[0031] Among them, the optimization control request refers to a request to predict the output power of multiple power supply vehicles in a grid-connected operating environment for optimized control. The target power supply vehicle refers to the power supply vehicle managed under the grid-connected control system. The number of target power supply vehicles can be at least two. The preset time period refers to a preset historical time period. The preset time period can be, for example, 5 minutes before the current moment. Historical operation data refers to relevant data when each target energy vehicle is operating within the preset time period. The historical operation data may include the grid load value, the status of the power supply vehicle, and environmental factors. Environmental factors may include temperature, humidity, wind speed, solar radiation, rainfall, and dust concentration.

[0032] Optionally, when the grid-connected control system detects optimization control requests for multiple power supply vehicles in a grid-connected operating environment, it can determine the power supply vehicle in the grid-connected environment managed by the system as the target power supply vehicle. Furthermore, it can interact with each target power supply vehicle to obtain the historical operating data of each target power supply vehicle within a preset time period, and can also directly obtain the historical operating data of each target power supply vehicle within a preset time period from a preset storage module.

[0033] S102 : Based on a preset grid load model, state model, and environmental factor model, and according to historical operation data, the predicted operation data of each target power supply vehicle is determined.

[0034] The grid load model refers to a preset model that predicts the grid load value of the target power supply vehicle at the next moment. The grid load value refers to the total load value of the power supply network composed of each target power supply vehicle. The state model refers to a preset model that predicts the power state value of the target power supply vehicle at the next moment. The environmental factor model refers to a preset model that predicts the environmental factor value of the target power supply vehicle at the next moment. The predicted operation data may include the predicted grid load value, the predicted power state value, and the predicted environmental factor vector.

[0035] Optionally, the historical grid load values ​​in the historical operation data can be substituted into the preset grid load model to obtain the corresponding predicted grid load values, the historical power state values ​​in the historical operation data can be substituted into the preset state model to obtain the corresponding predicted power state values, the historical environmental factors in the historical operation data can be integrated to generate a historical environmental factor vector and substituted into the preset environmental factor model to obtain the corresponding predicted environmental factor vector, and the predicted operation data can be generated based on the predicted grid load values, predicted power state values ​​and predicted environmental factor vectors.

[0036] For example, the grid load model may be:

[0037]

[0038] Where L(t) represents the grid load value at time t, μ represents the grid load value when there are no other factors affecting it, and φ i The weight coefficient of the load L(ti) at time ti on the load L(t) at the current time t, θ j It represents the weight coefficient of the influence of the random error of the grid load at time tj on the load at time t, ε(tj) represents the random error value of the grid load at time tj, p represents the time lag of the historical load data, that is, the influence of the load value of p previous time points on the current load is considered, and q represents the time lag of the past random error, that is, the influence of the random error of q previous time points on the current load is considered.

[0039] For example, the state model may be:

[0040] S i (t) = S i (t-1)+α·A c (t)-β·A dc (t)+γ·ε(t)

[0041] Among them, S i (t) represents the state value of the power supply vehicle i at time t, α and β represent the efficiency coefficients of charging and discharging respectively, A c and A dc They represent the charging and discharging power of power supply vehicle i at time t, γ is the parameter for adjusting the degree of influence of random fluctuations of environmental factors on the state of the power supply vehicle, and ε(t) represents the random error value of environmental factors at time t.

[0042] For example, the environmental factor model may be:

[0043] E(t)=ρ·E(t-1)+ε(t)

[0044] Where E(t) and E(t-1) represent the environmental factor vectors at time t and time t-1, respectively. Environmental factors include temperature, humidity, wind speed, solar radiation, rainfall, and dust concentration. ρ is the autocorrelation coefficient, which indicates the correlation between environmental factors at adjacent time points. ε(t) represents the random error value of the environmental factor at time t.

[0045] S103. Determine the target output power corresponding to each target energy vehicle based on the target neural network model and the predicted operation data, so as to optimize the control of each target energy vehicle.

[0046] Among them, the target neural network refers to a preset network used to evaluate the correlation between the predicted grid load value, the predicted power state value and the predicted environmental factor vector to determine the output power adjustment value. The input of the target neural network is the predicted operation data, and the output is the output power adjustment value.

[0047] Optionally, the predicted operating data can be input into the target neural network model to obtain the output power adjustment value corresponding to each target energy vehicle, and further based on the historical output power and output power adjustment value of each target energy vehicle, the target output power corresponding to each target energy vehicle can be determined to optimize the control of each target energy vehicle.

[0048] For example, the output-input relationship of the target neural network can be expressed by the following formula:

[0049] y=[L(t),S1(t),S2(t)...,S n (t),E(t)]

[0050] Among them, L(t) represents the grid load value at time t, S i (t) represents the state value of the target power supply vehicle i at time t, E(t) represents the environmental factor vector at time t; y represents the output power adjustment value of each target power supply vehicle. Specifically, y=[P1,P2,...,P n ], where P i Represents the output power adjustment value of the i-th target power supply vehicle.

[0051] Optionally, the target output power corresponding to each target energy vehicle is determined based on the target neural network model and the predicted operating data, including: iteratively updating the predicted operating data based on the dung beetle optimization algorithm and the target neural network model until the iteration end condition is met; if it is detected that the iteration end condition is met, the target output power corresponding to each target energy vehicle is determined based on the final operating data and the target neural network model.

[0052] Optionally, based on the dung beetle optimization algorithm and the target neural network model, the predicted operation data is iteratively updated until the iteration end condition is met, including: based on the dung beetle optimization algorithm and the target neural network model, according to the predicted operation data, predicting the predicted output power of each target energy vehicle; based on the predicted output power and the predicted operation data, evaluating the candidate dung beetle individuals based on a preset reward function, and updating the predicted operation data according to the evaluation results; using the updated predicted operation data to iteratively perform prediction operations and evaluation operations until it is detected that the iteration end condition is met.

[0053] The Dung Beetle Optimizer (DBO) is a pre-set optimization algorithm used to determine optimal operating data. The predicted output power is the power ultimately used to instruct each target energy vehicle to adjust its power for optimal control. The reward function is a pre-set function used to evaluate the quality of each candidate dung beetle. The prediction operation is the process of using a target neural network to predict the output power corresponding to each predicted operating data, and the evaluation operation is the process of determining the evaluation value based on the pre-set reward function.

[0054] Optionally, the predicted operating data of the target energy vehicle can be divided into multiple groups, and the predicted operating data of each group of target energy vehicles can be determined as corresponding candidate dung beetle individuals. For each candidate dung beetle individual, a process of predicting the predicted output power and evaluating based on the reward function is performed, thereby iterating to determine the optimal dung beetle individual from the candidate dung beetle individuals.

[0055] Optionally, based on the dung beetle optimization algorithm and the target neural network model, the predicted output power of each target energy vehicle is predicted according to the predicted operation data, including: based on the dung beetle optimization algorithm, the predicted operation data of each group of target energy vehicles is determined as the corresponding candidate dung beetle individual; for each candidate dung beetle individual, based on the target neural network model, the corresponding candidate adjustment value is determined, and the candidate output power is determined according to the candidate adjustment value and the historical output power of each target energy vehicle; based on a preset reward function and a preset sorting algorithm, the optimal dung beetle individual is determined from the candidate dung beetle individuals according to the candidate output power and the predicted operation data, and the candidate output power corresponding to the optimal dung beetle individual is determined as the predicted output power.

[0056] The candidate adjustment value refers to the power adjustment value corresponding to the candidate dung beetle individual. The preset sorting algorithm may be, for example, a non-dominated sorting algorithm.

[0057] Optionally, for each candidate dung beetle individual, its corresponding predicted operating data can be input into the target neural network model to obtain the corresponding candidate adjustment value, and the sum of the candidate adjustment value and the historical output power of each target energy vehicle can be determined as the candidate output power.

[0058] Optionally, based on a preset reward function and a preset sorting algorithm, the optimal dung beetle individual is determined from the candidate dung beetle individuals according to the candidate output power and the predicted operating data, including: based on the preset reward function, determining the evaluation value corresponding to each candidate dung beetle individual according to the candidate output power and the predicted operating data; based on the preset sorting algorithm, sorting the candidate dung beetle individuals according to the evaluation value to obtain a sorting result, and determining the optimal dung beetle individual from the candidate dung beetle individuals according to the sorting result.

[0059] For example, the reward function can be expressed as follows:

[0060]

[0061] Among them, λ1, λ2 and λ3 are the grid load weight coefficient, output power weight coefficient and state weight coefficient respectively, L(t) represents the grid load at time t, OP i (t) represents the output power of the i-th power supply vehicle at time t, Indicates the degree of matching between the output power of the power supply vehicle and the grid load. The smaller the value, the closer the output power of the power supply vehicle is to the actual load demand of the grid. It represents the standard deviation between the grid load and the output power of all power supply vehicles. A smaller standard deviation means a lower grid load volatility. i (t) represents the state value of power supply vehicle i at time t, represents the ideal state value of power car i, Indicates the gap between the status of the power supply vehicle and the ideal status. The smaller the value, the closer the status of the power supply vehicle is to the ideal status and the more stable the status of the power supply vehicle is.

[0062] Exemplarily, a certain number of candidate dung beetle individuals can be randomly generated, each candidate dung beetle individual represents a candidate solution, that is, a possible adjustment value, and these adjustment values ​​are represented by the parameters of the target neural network; for each dung beetle individual, based on the current environmental model, interaction is performed to perform a series of grid-connected operations, specifically including: in a simulated environment, the dung beetle individual performs a grid-connected operation according to the adjustment value output by its neural network model, and after executing each operation, the changes in the grid load, the power supply vehicle status and the environmental factors are recorded, and the performance of each dung beetle individual on different optimization objectives is calculated according to a predefined reward function to determine an evaluation value; according to the characteristics of the multi-objective optimization problem, a non-dominated sorting algorithm is used to sort the dung beetle individuals according to their performance and assign them to solution sets of different levels. The optimization objectives of the sorting process mainly include the response effect of the power supply vehicle grid-connected operation to the grid load, the volatility of the grid load and the stability of the power supply vehicle status; finally, according to the non-dominated sorting results, the position of the dung beetle individual is updated through operations such as mutation, crossover, and bootstrapping, that is, the target neural network model parameters corresponding to each dung beetle individual are updated.

[0063] The non-dominated sorting algorithm (NSA) is a commonly used method for multi-objective optimization problems. Its purpose is to sort candidate solutions based on the non-dominance relationship among multiple objectives to identify one or more sets of solutions (called Pareto frontiers or Pareto frontier solution sets) that perform well on all objectives and have no absolute advantage over each other. In other words, any solution that improves on one objective will deteriorate on other objectives.

[0064] Exemplarily, according to the characteristics of the multi-objective optimization problem, a non-dominated sorting algorithm is used to sort the dung beetle individuals according to their performance and assign them to solution sets of different levels, including the following steps S33-1 to S33-7:

[0065] S33-1, create an empty list F for storing the Pareto frontiers at all levels, initialize the dominated count n to 0 for each dung beetle individual p, and initialize the set of individuals Sp dominated by it;

[0066] S33-2, for each pair of dung beetle individuals p and q, compare their performance on each optimization goal. If p dominates q, add q to Sp; otherwise, increase the dominated count n by 1.

[0067] S33-3, add all dung beetle individuals p whose dominated count n is 0 to the first-level Pareto frontier F1;

[0068] S33-4, initialize i=1, and when Fi is not empty, initialize the empty list Q;

[0069] S33-5, for each individual p in Fi, for each individual q it dominates, reduce the dominated count n by 1. If the dominated count n of individual q is 0 after deduction, add q to Q;

[0070] S33-6, add 1 to the value of i and use Q as the new Pareto frontier Fi of the i-th level;

[0071] S33-7, repeat S33-5 to S33-6 until all dung beetle individuals are graded.

[0072] Exemplarily, based on the non-dominated sorting result, the positions of the dung beetle individuals are updated through operations such as mutation, crossover, and guidance, including the following steps S34-1 to S34-3:

[0073] S34-1, for the first-level Pareto frontier individuals, fine-tune the parameters of these individuals and exchange some parameters with other first-level Pareto frontier individuals;

[0074] S34-2, for the secondary Pareto frontier individuals, one or more dung beetle individuals with the best performance are selected from the first-level Pareto frontier, and the neural network model parameters of the secondary Pareto frontier individuals are adjusted to make them close to the parameters of the selected first-level frontier individuals;

[0075] S34-3, for the Pareto frontier individuals at level three and below, significantly adjust the parameters of these individuals, eliminate the worst performing individuals and regenerate new individuals.

[0076] Optionally, if it is detected that the iteration end condition is met, the target output power corresponding to each target energy vehicle is determined based on the final operating data and the target neural network model, including: if it is detected that the iteration end condition is met, the final operating data is input into the target neural network model to obtain the target adjustment value of the output power of each target power vehicle; based on the target adjustment amount, the target output power of each target energy vehicle is determined, and based on the target output power, each target energy vehicle is optimized and controlled.

[0077] The final running data refers to the latest predicted running data. The iteration end condition can be reaching the maximum number of training generations or meeting the convergence accuracy requirement.

[0078] Optionally, the sum of the target adjustment value and the historical output power of each target energy vehicle can be determined as the target output power of each target energy vehicle, and each target energy vehicle can be controlled to perform grid-connected operation to achieve the corresponding target output power, thereby realizing optimized control of each target energy vehicle.

[0079] The technical solution of the embodiment of the present invention, in response to the optimization control request for multiple power supply vehicles in the grid-connected operation environment, determines the target power supply vehicle for grid-connected operation, and collects the historical operation data of each target power supply vehicle within a preset time period; based on the preset grid load model, state model and environmental factor model, the predicted operation data of each target power supply vehicle is determined according to the historical operation data; based on the target neural network model and the predicted operation data, the target output power corresponding to each target energy vehicle is determined to optimize the control of each target energy vehicle. By comprehensively analyzing the operating data of the power supply vehicle and using the neural network model to predict the accurate output power, it is possible to achieve precise control of the target energy vehicle, improve the efficiency of the grid-connected operation of the power supply vehicle, and enhance the stability and reliability of the power grid.

[0080] Example 2

[0081] Figure 2 This is a flow chart of an optimization control method for a power supply vehicle provided in the second embodiment of the present invention; based on the above embodiment, this embodiment provides a preferred example of realizing optimization control of a power supply vehicle by using a neural network model, a dung beetle optimization algorithm and a preset reward function.

[0082] like Figure 2 As shown, the method includes the following processes:

[0083] S201 : In response to an optimization control request for multiple power supply vehicles in a grid-connected operation environment, a target power supply vehicle for grid-connected operation is determined, and historical operation data of each target power supply vehicle within a preset time period is collected.

[0084] S202 : Based on a preset grid load model, state model, and environmental factor model, and according to historical operation data, the predicted operation data of each target power supply vehicle is determined.

[0085] S203. Based on the dung beetle optimization algorithm and the target neural network model, and according to the predicted operating data, predict the predicted output power of each target energy vehicle.

[0086] S204 : According to the predicted output power and the predicted operation data, the candidate dung beetle individuals are evaluated based on a preset reward function, and the predicted operation data is updated according to the evaluation results.

[0087] S205: Iteratively perform prediction and evaluation operations using the updated prediction operation data until it is detected that an iteration end condition is met.

[0088] S206. If it is detected that the iteration end condition is met, the final operation data is input into the target neural network model to obtain the target adjustment value of the output power of each target power supply vehicle.

[0089] S207: Determine the target output power of each target energy vehicle according to the target adjustment amount, and optimize and control each target energy vehicle according to the target output power.

[0090] The technical solution of the present invention, by constructing an operating environment model of the power grid and the power supply vehicle, can comprehensively consider multiple factors such as the power grid load, the status of the power supply vehicle, and environmental factors, effectively reducing power grid fluctuations. At the same time, it predicts changes in the power grid load through a deep learning neural network, and combines the dung beetle optimization algorithm to determine the optimization strategy of the power supply vehicle, which can improve grid connection efficiency and power grid stability, and help promote the improvement of the intelligent level of the power grid.

[0091] Example 3

[0092] Figure 3This is a structural block diagram of an optimization control device for a power supply vehicle provided in the third embodiment of the present invention; this embodiment is applicable to the case of optimizing and controlling the output power of multiple power supply vehicles in a grid-connected environment. The optimization control device for a power supply vehicle provided in the embodiment of the present invention can execute the optimization control method for a power supply vehicle provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method; the optimization control device for a power supply vehicle can be implemented in the form of hardware and / or software, and configured in an electronic device having the optimization control function of a power supply vehicle, such as Figure 3 As shown, the optimization control device of the power supply vehicle specifically includes:

[0093] The acquisition module 301 is used to respond to the optimization control request for multiple power supply vehicles in the grid-connected operation environment, determine the target power supply vehicle for grid-connected operation, and collect the historical operation data of each target power supply vehicle within a preset time period;

[0094] Determination module 302, for determining predicted operating data of each target power supply vehicle based on a preset grid load model, state model, and environmental factor model and according to historical operating data;

[0095] The control module 303 is used to determine the target output power corresponding to each target energy vehicle based on the target neural network model and the predicted operation data, so as to optimize the control of each target energy vehicle.

[0096] The technical solution of the embodiment of the present invention, in response to the optimization control request for multiple power supply vehicles in the grid-connected operation environment, determines the target power supply vehicle for grid-connected operation, and collects the historical operation data of each target power supply vehicle within a preset time period; based on the preset grid load model, state model and environmental factor model, the predicted operation data of each target power supply vehicle is determined according to the historical operation data; based on the target neural network model and the predicted operation data, the target output power corresponding to each target energy vehicle is determined to optimize the control of each target energy vehicle. By comprehensively analyzing the operating data of the power supply vehicle and using the neural network model to predict the accurate output power, it is possible to achieve precise control of the target energy vehicle, improve the efficiency of the grid-connected operation of the power supply vehicle, and enhance the stability of the power grid.

[0097] Furthermore, the control module 303 may include:

[0098] An iteration unit, for iteratively updating the predicted operation data based on the dung beetle optimization algorithm and the target neural network model until an iteration end condition is met;

[0099] The determination unit is used to determine the target output power corresponding to each target energy vehicle based on the final operating data and the target neural network model if it is detected that the iteration end condition is met.

[0100] Furthermore, the iteration unit may include:

[0101] A prediction subunit, used to predict the predicted output power of each target energy vehicle based on the predicted operation data based on the dung beetle optimization algorithm and the target neural network model;

[0102] An evaluation subunit, configured to evaluate individual dung beetles according to the predicted output power and the predicted operating data and based on a preset reward function, and to update the predicted operating data according to the evaluation results;

[0103] The detection subunit is used to iteratively perform prediction operations and evaluation operations using the updated prediction operation data until it is detected that an iteration end condition is met.

[0104] Furthermore, the prediction subunit is specifically used for:

[0105] Based on the dung beetle optimization algorithm, the predicted operating data of each group of target energy vehicles is determined as the corresponding candidate dung beetle individuals;

[0106] For each candidate dung beetle individual, determine the corresponding candidate adjustment value based on the target neural network model, and determine the candidate output power based on the candidate adjustment value and the historical output power of each target energy vehicle;

[0107] Based on a preset reward function and a preset sorting algorithm, the optimal dung beetle individual is determined from the candidate dung beetle individuals according to the candidate output power and the predicted operation data, and the candidate output power corresponding to the optimal dung beetle individual is determined as the predicted output power.

[0108] Furthermore, the prediction subunit is specifically used for:

[0109] Based on the preset reward function, the evaluation value corresponding to each candidate dung beetle individual is determined according to the candidate output power and predicted operation data;

[0110] Based on a preset sorting algorithm, the candidate dung beetle individuals are sorted according to the evaluation values ​​to obtain a sorting result, and the optimal dung beetle individual is determined from the candidate dung beetle individuals according to the sorting result.

[0111] Furthermore, the determination unit is specifically used for:

[0112] If it is detected that the iteration end condition is met, the final operation data is input into the target neural network model to obtain the target adjustment value of the output power of each target power supply vehicle;

[0113] According to the target adjustment amount, the target output power of each target energy vehicle is determined, and according to the target output power, each target energy vehicle is optimized and controlled.

[0114] Example 4

[0115] Figure 4 It is a structural diagram of an electronic device provided in Embodiment 4 of the present invention. Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0116] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0117] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0118] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the optimization control method for the power supply vehicle.

[0119] In some embodiments, the optimization control method of the power supply vehicle can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the optimization control method of the power supply vehicle described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the optimization control method of the power supply vehicle in any other appropriate manner (for example, by means of firmware).

[0120] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0121] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0122] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be a machine-readable signal medium. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0123] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0124] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0125] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within a cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0126] In one embodiment, the present invention also includes a computer program product, which includes a computer program. When executed by a processor, the computer program implements the optimization control method of the power supply vehicle of any embodiment of the present invention. During the implementation of the computer program product, the computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or a combination thereof. The programming language includes an object-oriented programming language such as Java, Smalltalk, C++, and also includes a conventional procedural programming language such as "C" language or similar programming language. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, via the Internet using an Internet service provider). It should be understood that the various forms of the process shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit them here. The above specific implementation methods do not constitute limitations on the scope of protection of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An optimization control method for a power supply vehicle, characterized in that: include: In response to a request for optimized control of multiple power supply vehicles in a grid-connected operation environment, a target power supply vehicle for grid-connected operation is determined, and historical operating data of each target power supply vehicle within a preset time period is collected; Based on the preset grid load model, state model, and environmental factor model, and according to historical operating data, the predicted operating data of each target power supply vehicle is determined; wherein the predicted operating data is determined by the predicted grid load value, the predicted power state value, and the predicted environmental factor vector; Based on the dung beetle optimization algorithm and the target neural network model, the predicted operation data is iteratively updated until the iteration end condition is met; If it is detected that the iteration end condition is met, the final operation data is input into the target neural network model to obtain the target adjustment value of the output power of each target power supply vehicle; According to the target adjustment amount, the target output power of each target energy vehicle is determined, and according to the target output power, each target energy vehicle is optimized and controlled.

2. The method according to claim 1, characterized in that Based on the dung beetle optimization algorithm and the target neural network model, the predicted operation data is iteratively updated until the iteration end conditions are met, including: Based on the dung beetle optimization algorithm and the target neural network model, the predicted output power of each target energy vehicle is predicted according to the predicted operating data; Based on the predicted output power and the predicted operating data, the candidate dung beetle individuals are evaluated based on a preset reward function, and the predicted operating data is updated according to the evaluation results; The updated prediction operation data is used to iteratively perform prediction operations and evaluation operations until it is detected that the iteration end condition is met.

3. The method according to claim 2, characterized in that The method of predicting the output power of each target energy vehicle based on the predicted operation data based on the dung beetle optimization algorithm and the target neural network model includes: Based on the dung beetle optimization algorithm, the predicted operating data of each group of target energy vehicles is determined as the corresponding candidate dung beetle individuals; For each candidate dung beetle individual, determine the corresponding candidate adjustment value based on the target neural network model, and determine the candidate output power based on the candidate adjustment value and the historical output power of each target energy vehicle; Based on a preset reward function and a preset sorting algorithm, the optimal dung beetle individual is determined from the candidate dung beetle individuals according to the candidate output power and the predicted operation data, and the candidate output power corresponding to the optimal dung beetle individual is determined as the predicted output power.

4. The method according to claim 3, characterized in that Based on a preset reward function and a preset ranking algorithm, the optimal dung beetle individual is determined from the candidate dung beetle individuals according to the candidate output power and the predicted operation data, including: Based on the preset reward function, the evaluation value corresponding to each candidate dung beetle individual is determined according to the candidate output power and predicted operation data; Based on a preset sorting algorithm, the candidate dung beetle individuals are sorted according to the evaluation values ​​to obtain a sorting result, and the optimal dung beetle individual is determined from the candidate dung beetle individuals according to the sorting result.

5. An optimization control device for a power supply vehicle, characterized in that: include: The acquisition module is used to respond to the optimization control request for multiple power supply vehicles in the grid-connected operation environment, determine the target power supply vehicle for grid-connected operation, and collect the historical operation data of each target power supply vehicle within a preset time period; A determination module is used to determine the predicted operating data of each target power supply vehicle based on a preset grid load model, state model, and environmental factor model and according to historical operating data; a control module configured to determine a target output power corresponding to each target energy vehicle based on a target neural network model and predicted operating data, so as to optimize control of each target energy vehicle; wherein the predicted operating data is determined by a predicted grid load value, a predicted power state value, and a predicted environmental factor vector; The control module includes: an iteration unit for iteratively updating the predicted operation data based on the dung beetle optimization algorithm and the target neural network model until an iteration end condition is met; a determination unit, configured to determine the target output power corresponding to each target energy vehicle based on the final operating data and the target neural network model if it is detected that the iteration end condition is met; The determination unit is specifically used to: if it is detected that the iteration end condition is met, the final operation data is input into the target neural network model to obtain the target adjustment value of the output power of each target power supply vehicle; according to the target adjustment amount, the target output power of each target energy vehicle is determined, and according to the target output power, each target energy vehicle is optimized and controlled.

6. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the optimization control method for the power supply vehicle according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the optimization control method of the power supply vehicle according to any one of claims 1 to 4 when executed.

8. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the optimization control method for the power supply vehicle according to any one of claims 1 to 4.

Images