Intelligent scheduling method and device for energy storage power station based on artificial intelligence, and storage medium

Abstract

The invention relates to the technical field of artificial intelligence, energy management and intelligent power grids, in particular to an intelligent scheduling method and device for an energy storage power station based on artificial intelligence and a storage medium. The method comprises the steps of screening energy storage units according to an operation plan and power grid requirements of an energy storage power station; selecting a preset number of energy storage units as priority scheduling units based on the capacity, efficiency and state of the energy storage units; calculating an optimal charging and discharging scheme of the energy storage power station in power grid operation as a scheduling sequence of the energy storage units; selecting an energy storage unit which is ranked at the top in the priority scheduling units, carrying out optimal scheduling by adopting an artificial intelligence algorithm, adjusting a charging and discharging scheme in real time, and evaluating a scheduling effect; and if the effect is not good, executing the scheduling strategy and effect evaluation by adopting the second energy storage unit, circulating in sequence, and executing the scheduling strategy by using the optimal energy storage unit. Efficient, flexible and real-time optimal scheduling of the energy storage power station is realized, and the operation efficiency of the energy storage power station and the stability of a power grid are improved.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence, energy management, and smart grid technologies, and in particular to an artificial intelligence-based intelligent scheduling method, device, and storage medium for energy storage power stations. Background Art

[0002] In the field of intelligent scheduling of energy storage power plants, existing technologies typically rely on traditional algorithms and manual experience to select energy storage units and develop charging and discharging plans. These methods often suffer from low efficiency, slow response, and difficulty adapting to rapidly changing grid demands. Especially when faced with large-scale energy storage plants and complex and changing grid environments, traditional methods struggle to achieve optimal scheduling of energy storage units. Summary of the Invention

[0003] In view of this, the present invention provides an artificial intelligence-based intelligent scheduling method, device and storage medium for energy storage power stations to solve the problem that the existing technology is difficult to adapt the scheduling of energy storage units to the needs of the power grid.

[0004] In a first aspect, the present invention provides an intelligent scheduling method for an energy storage power station based on artificial intelligence, the method comprising: screening energy storage units participating in scheduling in the energy storage power station according to the operation plan of the energy storage power station and the demand of the power grid; sorting the screened energy storage units based on the efficiency and status of the energy storage units, and selecting a preset number of energy storage units before the sorting as priority scheduling units; calculating the optimal charge and discharge plan of each priority scheduling unit, and determining the scheduling order of the priority scheduling units based on the optimal discharge plan; scheduling the priority scheduling unit at the top of the scheduling order, adjusting the charge and discharge plan of the scheduled priority scheduling unit using an artificial intelligence algorithm, and evaluating the scheduling effect. If the scheduling effect does not meet the preset requirements, scheduling the next priority scheduling unit, adjusting the charge and discharge plan, and evaluating the scheduling effect, until a priority scheduling unit that meets the scheduling effect is obtained for scheduling.

[0005] The AI-based intelligent scheduling method for energy storage power stations provided in embodiments of the present invention achieves efficient operation of energy storage power stations and precise matching of power grid demand through the screening and sorting of energy storage units, calculation of optimal charging and discharging plans, and implementation of real-time optimized scheduling. Furthermore, during scheduling, the introduction of AI technology enables efficient and intelligent sorting and scheduling of energy storage units. For example, AI algorithms can dynamically optimize and adjust charging and discharging plans. This method not only improves the operating efficiency of energy storage power stations and reduces energy loss, but also enhances the stability and economic efficiency of the power grid.

[0006] In an optional embodiment, the energy storage units participating in the scheduling of the screened energy storage power station include a variety of energy storage unit combinations that meet the operation plan and power grid requirements, and each energy storage unit combination includes multiple energy storage units; the screened energy storage units are sorted based on the efficiency and status of the energy storage units, and a preset number of energy storage units before the sorting are selected as priority scheduling units, including: weighting and assigning scores to the importance of each energy storage unit in each energy storage unit combination to obtain a first score matrix reflecting the importance of the energy storage unit; based on the first parameter characteristics of the energy storage unit and a pre-constructed efficiency status index prediction model, an efficiency status index reflecting the energy storage unit is obtained; based on the scoring of the efficiency status index, a second score matrix reflecting the efficiency and status of the energy storage unit is constructed; the screened energy storage units are sorted according to a third score matrix obtained by weighted merging of the first score matrix and the second score matrix, and a preset number of energy storage units before the sorting are selected as priority scheduling units.

[0007] In this embodiment, the first score matrix is ​​determined based on importance, the second score matrix is ​​determined based on efficiency and indicators, and the priority scheduling unit is determined by the third score matrix determined by weighting the first score matrix and the second score matrix, which can ensure the scientificity and rationality of the scheduling plan.

[0008] In an optional embodiment, a combination of multiple energy storage units is determined using an optimization algorithm, and the efficiency status indicators include charging and discharging efficiency and response time; a second score matrix reflecting the efficiency and status of the energy storage units is constructed based on the scoring of the efficiency status indicators, including: arranging the efficiency status indicators in descending order to construct an indicator matrix; constructing an efficiency status score matrix based on cluster analysis; multiplying the indicator matrix and the score matrix, and combining them with the number of the energy storage units to obtain a second score matrix.

[0009] In this embodiment, an optimization algorithm is used to determine the energy storage unit combination, which can enhance the flexibility and adaptability of the scheduling scheme. When determining the second score matrix, the indicator matrix is ​​multiplied by the score matrix, making the determined second score matrix more objective and enabling accurate assessment of the energy storage unit efficiency status indicators.

[0010] In an optional embodiment, the optimal charging and discharging plan of each priority scheduling unit is calculated, including: training a machine learning model based on the second parameter characteristics of the energy storage unit and the optimal charging and discharging plan to obtain a charging and discharging prediction model; and predicting the optimal charging and discharging plan of each priority scheduling unit based on the current second parameter characteristics of each priority scheduling unit and the charging and discharging prediction model.

[0011] In this embodiment, the optimal charging and discharging plan is predicted by training the charging and discharging prediction model, which provides a data basis for the scheduling and efficient scheduling of energy storage units.

[0012] In an optional embodiment, the second parameter characteristics include the location, capacity, efficiency, current state of the energy storage unit and the degree of matching with the grid demand, and the optimal charging and discharging plan includes the time point, power size and duration of charging and discharging.

[0013] In this embodiment, by determining the second parameter characteristics including the location, capacity, efficiency, current state of the energy storage unit and the degree of matching with the grid demand, the optimal charging and discharging plan includes the time point, power size and duration of charging and discharging, thereby achieving the best match between the energy storage unit and the grid demand.

[0014] In an optional embodiment, an artificial intelligence algorithm is used to adjust the charging and discharging scheme of the priority scheduling unit, including: adjusting the charging and discharging scheme of the priority scheduling unit based on a preset objective function and using a deep reinforcement learning algorithm according to operating scenario data.

[0015] In an optional embodiment, the deep reinforcement learning algorithm uses a policy network and a value network to adjust the charging and discharging plan; the policy network is used to obtain the charging and discharging plan based on the operating scenario data; the value network is used to obtain the operating scenario data and the charging and discharging plan, determine the matching degree between the energy storage power station and the grid demand and the operating efficiency of the energy storage unit as a reward, generate a reward function based on the reward, and use the reward function to optimize the policy network.

[0016] In this embodiment, the strategy network and the value network work in coordination to achieve dynamic adjustment and optimization of the energy storage unit charging and discharging plan.

[0017] In a second aspect, the present invention provides an intelligent scheduling device for an energy storage power station based on artificial intelligence, the device comprising: a screening module for screening energy storage units participating in scheduling in the energy storage power station according to the operation plan of the energy storage power station and the demand of the power grid; a priority scheduling determination module for sorting the screened energy storage units based on the efficiency and status of the energy storage units, and selecting a preset number of energy storage units before and after the sorting as priority scheduling units; a scheduling sorting module for calculating the optimal charging and discharging scheme of each priority scheduling unit, and determining the scheduling sorting of the priority scheduling units based on the optimal discharge scheme; a sorting module for scheduling the priority scheduling unit at the top based on the scheduling sorting, adjusting the charging and discharging scheme of the scheduled priority scheduling unit by using an artificial intelligence algorithm, and evaluating the scheduling effect. If the scheduling effect does not meet the preset requirements, the next priority scheduling unit is scheduled, the charging and discharging scheme is adjusted, and the scheduling effect is evaluated until a priority scheduling unit that meets the scheduling effect is obtained for scheduling.

[0018] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to thereby execute the artificial intelligence-based intelligent scheduling method for energy storage power stations according to the first aspect or any corresponding embodiment thereof.

[0019] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the artificial intelligence-based intelligent scheduling method for energy storage power stations according to the first aspect or any corresponding embodiment thereof.

[0020] In a fifth aspect, the present invention provides a computer program product comprising computer instructions for enabling a computer to execute the artificial intelligence-based intelligent scheduling method for energy storage power stations according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0022] Figure 1 1 is a flow chart of an intelligent scheduling method for energy storage power stations based on artificial intelligence according to an embodiment of the present invention;

[0023] Figure 2 1 is a flow chart of another method for intelligent scheduling of energy storage power stations based on artificial intelligence according to an embodiment of the present invention;

[0024] Figure 3 1 is a structural block diagram of an intelligent dispatching device for an energy storage power station based on artificial intelligence according to an embodiment of the present invention;

[0025] Figure 4 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] As described in the background technology, the existing technology has difficulty in adapting the scheduling of energy storage units to the needs of the power grid. In particular, when faced with large-scale energy storage power stations and complex and changeable power grid environments, it is difficult for traditional methods to achieve optimal scheduling of energy storage units. Specifically, first, traditional scheduling methods lack comprehensive consideration of the multi-dimensional characteristics of energy storage units, such as capacity, efficiency, status, etc., resulting in scheduling plans that may not be optimal; second, when processing large-scale data and real-time data, the existing technology's algorithm lacks computing power and real-time performance, making it difficult to meet the modern power grid's demand for rapid response; third, existing scheduling systems often lack self-learning and self-adaptation capabilities, and cannot be dynamically adjusted and optimized according to the actual situation of power grid operation. These problems limit the potential of energy storage power stations in improving the stability and economy of the power grid.

[0027] In light of this, this embodiment provides an AI-based intelligent scheduling method for energy storage power stations. This method screens energy storage units based on the power station's operating plan, grid demand, and their efficiency and status. Furthermore, it prioritizes scheduling based on the optimal charging and discharging plan, employing an AI algorithm to implement scheduling and adjust charging and discharging plans. This method potentially improves grid stability and economic efficiency.

[0028] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0029] According to an embodiment of the present invention, an embodiment of an intelligent scheduling method for an energy storage power station based on artificial intelligence is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] In this embodiment, an intelligent scheduling method for energy storage power stations based on artificial intelligence is provided, which can be used for electronic devices such as computers, mobile phones, tablet computers, etc. Figure 1 FIG. 1 is a flow chart of an intelligent scheduling method for energy storage power stations based on artificial intelligence according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0031] Step S101 screens energy storage units from the energy storage power station for scheduling based on the power station's operation plan and grid requirements. Specifically, the energy storage units can be various types, such as battery energy storage systems, pumped hydro, and compressed air energy storage. When screening energy storage units, the operation plan and grid requirements can be specified. Specifically, specific requirements for the operation plan and grid requirements, such as load requirements, peak power requirements, and power quality standards, are determined. Then, based on these specific requirements, energy storage units are screened from the energy storage power station to meet these requirements.

[0032] In step S102, the selected energy storage units are sorted based on their efficiency and status, and a preset number of energy storage units are selected as priority scheduling units. Specifically, the selected energy storage units can be further screened based on parameters such as their efficiency and status, such as charge and discharge efficiency and state of charge.

[0033] Step S103, calculate the optimal charge and discharge plan for each priority scheduling unit, and determine the scheduling order of the priority scheduling unit based on the optimal discharge plan. Specifically, after determining the priority scheduling unit, since there may be multiple priority scheduling units, it is necessary to determine the scheduling order of multiple priority scheduling units. In this embodiment, the scheduling order of the priority scheduling units is determined by the optimal charge and discharge plan of each priority scheduling unit. The optimal charge and discharge plan specifically includes relevant parameters for achieving optimal charge and discharge, and the scheduling order can be determined by comparing the relevant parameters.

[0034] Step S104, based on the scheduling order, the priority scheduling unit with the highest priority is scheduled, and the artificial intelligence algorithm is used to adjust the charge and discharge plan of the scheduled priority scheduling unit, and the scheduling effect is evaluated. If the scheduling effect does not meet the preset requirements, the next priority scheduling unit is scheduled, and the charge and discharge plan is adjusted and the scheduling effect is evaluated, until the priority scheduling unit that meets the scheduling effect is obtained for scheduling. Specifically, during scheduling, the energy storage unit with the highest priority in the priority scheduling unit is selected, and the artificial intelligence algorithm is used for optimized scheduling, the charge and discharge plan is adjusted in real time, and the scheduling effect is evaluated; if the effect is not good, the energy storage unit with the second highest priority is used to execute the scheduling strategy and effect evaluation, and the cycle is repeated in sequence, and the optimal energy storage unit is used to execute the scheduling strategy. Among them, the artificial intelligence algorithm can be an intensity chemistry algorithm, and the artificial intelligence algorithm can be used to dynamically adjust the charge and discharge strategy according to the real-time operating data of the energy storage power station and the power grid demand to maximize the energy storage efficiency and meet the power grid demand.

[0035] The AI-based intelligent scheduling method for energy storage power stations provided in embodiments of the present invention achieves efficient operation of energy storage power stations and precise matching of power grid demand through the screening and sorting of energy storage units, calculation of optimal charging and discharging plans, and implementation of real-time optimized scheduling. Furthermore, during scheduling, the introduction of AI technology enables efficient and intelligent sorting and scheduling of energy storage units. For example, AI algorithms can dynamically optimize and adjust charging and discharging plans. This method not only improves the operating efficiency of energy storage power stations and reduces energy loss, but also enhances the stability and economic efficiency of the power grid.

[0036] In this embodiment, an intelligent scheduling method for energy storage power stations based on artificial intelligence is provided. Figure 2 As shown, the process includes the following steps:

[0037] Step S201, based on the operation plan of the energy storage power station and the grid demand, the energy storage units participating in the scheduling of the energy storage power station are screened. Specifically, the energy storage units participating in the scheduling of the energy storage power station selected include multiple energy storage unit combinations that meet the operation plan and grid demand, and each energy storage unit combination includes multiple energy storage units; the multiple energy storage unit combinations are determined using an optimization algorithm.

[0038] The search for energy storage unit combinations can be implemented using optimization algorithms such as genetic algorithms, particle swarm optimization, or other heuristic algorithms. These algorithms can identify a variety of energy storage unit combinations while meeting grid demand and the energy storage plant operation plan. When using optimization algorithms to screen energy storage unit combinations, evaluation metrics can be determined based on the operation plan and grid demand. The grid demand and energy storage plant operation constraints are then transformed into an optimization problem, and a mathematical model is established. Optimization algorithms such as genetic algorithms and particle swarm optimization can then be used to process the mathematical model, mapping the energy storage unit combinations to individual representations within the algorithm. An iterative process is then performed to determine the selected energy storage plant combinations.

[0039] At the same time, during the search process, the search strategy can be dynamically adjusted based on the historical operating data of the energy storage units and the real-time demand changes of the power grid to improve the accuracy and adaptability of the search. Furthermore, in addition to basic optimization algorithm search, more advanced optimization techniques such as simulated annealing or taboo search can be introduced to improve search efficiency and solution quality.

[0040] Step S202 : sorting the selected energy storage units based on their efficiency and status, and selecting a preset number of energy storage units after sorting as priority scheduling units.

[0041] Specifically, the above step S202 includes:

[0042] Step S2021 , weighting and assigning scores to the importance of each energy storage unit in each energy storage unit combination to obtain a first score matrix reflecting the importance of the energy storage unit.

[0043] Specifically, the first score matrix can be determined by the following steps:

[0044] Step a1 ranks the energy storage units in each energy storage unit combination according to their importance and assigns a score. Specifically, the importance of each energy storage unit can be determined based on factors such as its capacity, charge / discharge efficiency, charge / discharge speed, response time, and geographic location, and the corresponding score can be assigned accordingly. These factors can also be adjusted based on the type, scale, and historical performance of the energy storage unit. Furthermore, when determining importance, a multi-objective optimization approach can be employed, simultaneously considering multiple factors of the energy storage unit.

[0045] Step a2 accumulates the scores of each energy storage unit in each combination to form a score reflecting the importance of each energy storage unit. Specifically, the scores of each energy storage unit in different combinations can be added together to obtain a score reflecting its overall importance. The scores of the energy storage units in different combinations can be processed using a weighted average or other mathematical method to more accurately reflect their overall importance. Weighted scoring also fully considers the diversity and complementarity of the energy storage units, making the determined scores more objective.

[0046] In step a3, the scores of each energy storage unit are mapped to the unit number to form a first score matrix. Specifically, the first score matrix is ​​constructed by mapping the scores of each energy storage unit to the unit number, forming a matrix that can be quantitatively compared. Furthermore, the first score matrix can be displayed using data visualization techniques to make the results more intuitive and understandable.

[0047] Step S2022 : obtaining an efficiency status index reflecting the energy storage unit based on the first parameter characteristic of the energy storage unit and a pre-built efficiency status index prediction model.

[0048] Specifically, the above step S2022 includes:

[0049] Step b1, selects the first parameter feature of the energy storage unit as the model input for the first machine learning model that calculates the efficiency status index of the energy storage unit; specifically, the first parameter feature can use feature selection techniques such as correlation coefficient, information gain and chi-square test to determine the parameter feature with the most predictive power, that is, the feature that is most critical to the efficiency evaluation index of the energy storage unit, to reduce the complexity of the model and improve the calculation efficiency. For example, the first parameter feature may include the capacity, charge and discharge efficiency, current state, historical operation data and environmental factors of the energy storage unit. Among them, the capacity can be the rated energy or actual available energy of the energy storage unit; the charge and discharge efficiency involves the energy conversion efficiency of the energy storage unit during the charge and discharge process; the current state includes the power level, temperature, health of the energy storage unit, etc.; the historical operation data covers the past charge and discharge records, fault records, etc. of the energy storage unit; and the environmental factors include external conditions such as temperature, humidity, and load changes. These parameters can be obtained in real time through sensors or a preset data acquisition system.

[0050] After obtaining these features, they can be processed through necessary data cleaning and data preprocessing techniques such as normalization and standardization to convert feature values ​​of different dimensions and ranges to a unified scale to ensure data quality and consistency, while improving the convergence speed and prediction accuracy of the model.

[0051] The first machine learning model can be a support vector machine (SVM), decision tree, neural network, random forest, etc. These models can effectively process and analyze the multi-dimensional data of the energy storage unit. At the same time, the first machine learning model can be trained to calculate efficiency status indicators, such as the charge and discharge efficiency and response time of the energy storage unit in different states.

[0052] Step b2 is to train and adjust the parameters of the first machine learning model; specifically, when training the first machine learning model, the first parameter feature can be used as input, and the efficiency and status indicators can be used as output, that is, the input data of the first machine learning model is a multi-dimensional feature including the capacity, charge and discharge efficiency, current state, historical operation data and environmental factors of the energy storage unit, and the output is the efficiency status indicator. At the same time, during the training and parameter adjustment process, optimization algorithms such as batch gradient descent and stochastic gradient descent can be used to adjust the model parameters, and the performance of the model can be evaluated through cross-validation and other techniques. Regularization techniques such as L1 or L2 regularization can also be introduced to prevent model overfitting and improve the model's predictive ability on unknown data. In addition, it is also possible to consider introducing ensemble learning methods, such as random forests or gradient boosting machines, to improve the overall predictive ability by combining multiple weak prediction models. In practical applications, the weights of the input features can also be dynamically adjusted according to the specific needs of the energy storage power station and the real-time status of the power grid to adapt to different scheduling strategies and optimization objectives.

[0053] In step b3, the parameter characteristics of the energy storage unit are input into the trained model to calculate the efficiency and status indicators. Specifically, in practical applications, a multi-task learning method can be used to simultaneously predict multiple efficiency status indicators of the energy storage unit to improve the practicality of the model.

[0054] Step S2023: construct a second score matrix reflecting the efficiency and status of the energy storage unit based on the scoring of the efficiency status index.

[0055] In an optional implementation, the above step S2023 includes:

[0056] Step b1: Arrange the efficiency status indicators in descending order to construct an indicator matrix.

[0057] Step b2: constructing a score matrix of efficiency status based on cluster analysis.

[0058] Step b3: multiply the indicator matrix and the score matrix, and combine them with the numbers of the energy storage units to obtain a second score matrix.

[0059] Specifically, when determining the score matrix, techniques such as cluster analysis can be used to classify the efficiency and status of the energy storage units in order to better understand and analyze the performance of the energy storage units. The efficiency status index column vectors of each energy storage unit arranged in descending order can then be multiplied by the score matrix to obtain a score reflecting the efficiency status of each energy storage unit; the scores of each energy storage unit are matched with the energy storage unit numbers to form a second score matrix. Furthermore, when calculating the scores, consideration can be given to introducing a weighted average or other comprehensive scoring mechanism so that the score matrix not only reflects the level of a single indicator, but also comprehensively considers the balance of multiple indicators, thereby more comprehensively evaluating the performance of the energy storage unit.

[0060] In step S2024, the selected energy storage units are sorted according to a third score matrix obtained by weightedly combining the first score matrix and the second score matrix, and a preset number of energy storage units after sorting are selected as priority scheduling units. Specifically, the number of priority scheduling units selected can be determined based on actual needs. This embodiment does not impose specific limitations on this.

[0061] Step S203: Calculate the optimal charge and discharge plan for each priority scheduling unit, and determine the scheduling order of the priority scheduling units based on the optimal discharge plan; see Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0062] Step S204: Based on the scheduling order, the priority scheduling unit with the highest priority is scheduled, and the artificial intelligence algorithm is used to adjust the charge and discharge plan of the scheduled priority scheduling unit, and the scheduling effect is evaluated. If the scheduling effect does not meet the preset requirements, the next priority scheduling unit is scheduled, and the charge and discharge plan is adjusted and the scheduling effect is evaluated until the priority scheduling unit that meets the scheduling effect is scheduled. For details, please refer to Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0063] In this embodiment, an artificial intelligence-based intelligent scheduling method for energy storage power stations is provided, which includes the following steps:

[0064] Step S301: Select the energy storage units that participate in the scheduling of the energy storage power station according to the operation plan of the energy storage power station and the grid demand; see Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0065] Step S302: sort the selected energy storage units based on their efficiency and status, and select a preset number of energy storage units as priority scheduling units. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0066] Step S303 , calculating the optimal charging and discharging plan of each priority scheduling unit, and determining the scheduling order of the priority scheduling units based on the optimal discharging plan.

[0067] Specifically, the above step S303 includes:

[0068] Step S3031: Training a machine learning model based on the second parameter characteristics of the energy storage unit and the optimal charging and discharging scheme to obtain a charging and discharging prediction model.

[0069] Specifically, the second parameter characteristics include the location, capacity, efficiency, current status and matching degree with the grid demand of the energy storage unit. Location information may affect the response speed and effect of the energy storage unit to different areas of the grid; capacity and efficiency are key indicators of the performance of the energy storage unit; the current status includes power level, health status, etc.; and the matching degree with the grid demand involves the ability of the energy storage unit to meet the grid demand. These parameters can be obtained through real-time monitoring and data acquisition systems, and necessary data preprocessing and feature engineering are carried out to meet the needs of the model. The optimal charging and discharging plan includes the time point, power size, duration, etc. of charging and discharging to achieve the best match between the energy storage unit and the grid demand.

[0070] The purpose of constructing a charge-discharge prediction model is to optimize the charging and discharging schedules for energy storage units during grid operation. Therefore, the machine learning model used for training can employ sequence models from deep learning, such as long short-term memory networks or recurrent neural networks, which are suitable for processing time series data and predicting charge-discharge strategies. For example, convolutional neural networks or recurrent neural networks from deep learning can be used to process grid demand data with time series characteristics, while graph neural networks can be used to consider the spatial relationships of energy storage units.

[0071] Among them, the training and parameter adjustment of the machine learning model can be achieved through an automated machine learning pipeline, which includes steps such as data cleaning, feature selection, and hyperparameter optimization. During the training process, the second parameter features and the charge and discharge records of the energy storage unit can be used as the training set, and the model can be trained through supervised learning to predict the optimal charge and discharge plan. At the same time, during the model training process, regularization terms can be introduced to prevent overfitting, and early stopping can be used to avoid excessive training time. Parameter adjustment can be completed through techniques such as grid search or Bayesian optimization to find the optimal model parameter configuration.

[0072] To improve the practicality and adaptability of the model, online learning and incremental learning methods can be used to enable the model to self-update and optimize based on real-time data from power grid operations. At the same time, model interpretability tools, such as feature importance analysis or Local Interpretable Model-agnostic Explanations (LIME), can be considered to improve model interpretability and help operators better understand the model's prediction results.

[0073] In practical applications, a multi-task learning framework can be used to simultaneously predict multiple output features related to charging and discharging scenarios to improve the model's predictive power and flexibility. Furthermore, reinforcement learning techniques can be considered to optimize the generation of charging and discharging scenarios. Within this framework, the model can act as an intelligent agent, learning optimal charging and discharging strategies through interaction with the grid environment. Furthermore, federated learning techniques can be used to process data from distributed energy storage units, allowing for model training and optimization while protecting data privacy. In practice, the model's input feature weights can be dynamically adjusted based on the actual operation of the grid and changes in the performance of the energy storage units to accommodate different scheduling requirements and optimization objectives.

[0074] In addition, after the model training is completed, the performance of the model can be evaluated through model evaluation indicators such as mean squared error or mean absolute error.

[0075] Step S3032: Based on the current second parameter characteristics of each priority scheduling unit and the charge-discharge prediction model, the optimal charge-discharge plan for each priority scheduling unit is predicted. Specifically, the obtained second parameter characteristics can be input into the charge-discharge prediction model to obtain the optimal charge-discharge plan for each priority scheduling unit. The calculated results of these plans will be used to schedule the actual energy storage units and guide the operation of the energy storage power station.

[0076] Step S304, based on the priority scheduling unit that is scheduled first in the scheduling order, uses an artificial intelligence algorithm to adjust the charging and discharging plan of the scheduled priority scheduling unit, and evaluates the scheduling effect. If the scheduling effect does not meet the preset requirements, schedule the next priority scheduling unit, adjust the charging and discharging plan and evaluate the scheduling effect until a priority scheduling unit that meets the scheduling effect is obtained for scheduling.

[0077] Specifically, the artificial intelligence algorithm is used to adjust the charging and discharging plan of the priority scheduling unit, including:

[0078] Step S3041: Based on the operational scenario data, the charge and discharge plans of the priority dispatch units are adjusted using a deep reinforcement learning algorithm based on a preset objective function. Specifically, the AI ​​algorithm is used to optimize scheduling, setting an objective function based on grid demand and the operational scenario of the energy storage power station. Intelligent scheduling is performed based on the real-time operational data of the energy storage power station to determine the charge and discharge plan. The current charge and discharge plan is evaluated and adjusted by collecting real-time operational data from the energy storage power station. Furthermore, during grid operation, online learning and updating of the intelligent scheduling are performed based on the real-time charge and discharge plan and the corresponding energy storage power station operational scenario.

[0079] The objective functions set by AI algorithms in optimized scheduling include minimizing charging and discharging costs, maximizing energy storage efficiency, and ensuring grid supply and demand balance. Real-time data collection involves operating parameters of energy storage power stations, such as charging and discharging status, power levels, and environmental conditions. This data can be accessed in real time via Internet of Things (IoT) devices. Online learning and updating in intelligent scheduling means that the algorithm can continuously adjust and optimize charging and discharging plans based on the latest operating data to adapt to changes in grid demand.

[0080] When setting the objective function, multi-objective optimization techniques can be used to simultaneously consider the balance of multiple objectives, such as economic efficiency, reliability, and environmental impact. Real-time data collection can be achieved by establishing a centralized data monitoring system capable of processing and analyzing data streams from individual energy storage units. Online learning and updating can be accomplished by introducing incremental learning or online learning algorithms, which are capable of updating model parameters based on new data without retraining the entire model.

[0081] More specifically, it is also possible to consider introducing adaptive control strategies to enhance the flexibility and robustness of intelligent scheduling. For example, the Adaptive Dynamic Programming (ADP) algorithm can be used to deal with uncertainty and changing grid conditions. In addition, the Deep Reinforcement Learning (DeepRL) algorithm can be used to learn the optimal charging and discharging strategy through interaction with the grid environment. During the implementation process, it is also possible to consider using edge computing technology to reduce data transmission delays and improve the real-time nature of scheduling decisions. At the same time, a feedback mechanism can be set up to evaluate and adjust the charging and discharging plan based on the feedback signal from the grid to ensure that the scheduling decision of the energy storage power station is always consistent with the actual needs of the grid.

[0082] In an optional embodiment, the deep reinforcement learning algorithm uses a policy network and a value network to adjust the charging and discharging plan; the policy network is used to obtain the charging and discharging plan based on the operating scenario data; the value network is used to obtain the operating scenario data and the charging and discharging plan, determine the matching degree between the energy storage power station and the grid demand and the operating efficiency of the energy storage unit as a reward, generate a reward function based on the reward, and use the reward function to optimize the policy network.

[0083] Specifically, the policy network generates and outputs a decision d based on the input scenario t. Scenario t is the current operating scenario of the energy storage plant, and decision d is the charging and discharging plan that guides the plant's next operational scenario. "Scenario" here refers to the state of the energy storage plant at a given moment, including but not limited to the power level, charging and discharging status, grid demand, storage unit capacity, charging and discharging efficiency, current status, and compatibility with grid demand. The "decision" is the charging and discharging plan formulated based on these scenarios. Before receiving these scenario data, normalization can be performed to eliminate dimensionality effects between different parameters. Normalization can use methods such as min-max normalization or Z-score normalization.

[0084] Based on the received energy storage plant operating scenario t, the value network evaluates the corresponding decision d, i.e., the charging and discharging plan, guiding the policy network in its optimization. The value network evaluates the effectiveness of these decisions and provides feedback to the policy network for optimization. In this process, deep learning techniques can be used to construct these two networks, training them with extensive historical data to enable them to learn and predict the optimal charging and discharging strategy.

[0085] Preferably, for example, in the policy network, a deep Q-network (DQN) can be used to learn the optimal decision-making in different scenarios. For example, the policy network can adopt a deep neural network, which contains multiple hidden layers to handle complex nonlinear relationships. In the value network, Monte Carlo Tree Search (MCTS) can be used to evaluate the potential value of the charging and discharging scheme. In addition, a reward function can be set that comprehensively considers the matching degree between the energy storage power station and the grid demand and the operating efficiency of the energy storage unit to guide the evaluation process of the value network. For example, the value network can adopt a criticism network to evaluate the decision quality of the policy network. In addition, an experience replay mechanism can be introduced to store historical scenarios and decisions for use in the training of the policy network and the value network to improve learning efficiency.

[0086] More specifically, the introduction of a multi-agent system can be considered to enhance the coordination and adaptability of intelligent scheduling. In such a system, each energy storage unit can be regarded as an intelligent agent, which communicate and collaborate to jointly optimize the charging and discharging strategies of the entire energy storage plant. In addition, federated learning techniques can be used to train the policy network and value network, allowing knowledge sharing while protecting the data privacy of each energy storage unit. In practical applications, the network's input parameters and reward function can be dynamically adjusted according to the real-time needs of the grid and the operating status of the energy storage plant, achieving more accurate and flexible intelligent scheduling.

[0087] During the charging and discharging plan evaluation process, the value network uses the matching degree between the energy storage power station and the grid demand and the operating efficiency of the energy storage unit after each round as a reward, and uses the cumulative reward from the starting round to the current round as the reward function of the charging and discharging plan of the current round.

[0088] Furthermore, it is possible to consider introducing multi-step rewards to evaluate the long-term effects of charging and discharging schemes, rather than just single-step rewards. This can be achieved by setting a reward discount factor, encouraging the model to consider the cumulative effects of multiple future time steps. Furthermore, policy gradient methods can be used to optimize the policy network. This method allows the network to directly learn the policy gradient information, thereby more efficiently updating the network weights. In practical applications, the normalization method and reward function design can be dynamically adjusted according to the specific operating conditions of the energy storage power station and changes in grid demand to adapt to different scheduling scenarios and optimization objectives.

[0089] The AI-based intelligent scheduling method for energy storage power stations provided by the embodiments of the present invention utilizes AI technology to achieve efficient and intelligent sorting and scheduling of energy storage units. This method first performs a comprehensive assessment based on the capacity, efficiency, and status of energy storage units, selecting priority units for scheduling through weighted sorting, thereby ensuring the scientific and rationality of the scheduling plan. Secondly, by building and training a machine learning model, the efficiency and status of energy storage units are accurately calculated, further improving the accuracy and reliability of scheduling. Furthermore, this method utilizes an optimization algorithm to search and score energy storage unit combinations, enhancing the flexibility and adaptability of the scheduling plan. Furthermore, the intelligent scheduling method of the present invention can respond to changes in grid demand in real time, dynamically optimizing and adjusting charging and discharging plans through AI algorithms. This method not only improves the operating efficiency of energy storage power stations and reduces energy loss, but also enhances the stability and economic efficiency of the grid. Through online learning and update mechanisms, the system can continuously improve itself and adapt to increasingly complex grid operating environments. Overall, the intelligent scheduling method of the present invention provides strong technical support for the efficient and stable operation of energy storage power stations.

[0090] The artificial intelligence-based intelligent scheduling method for energy storage power stations provided in an embodiment of the present invention can achieve efficient management of energy storage units and precise response to grid demand. First, by weighted ranking and optimized scheduling of energy storage units through intelligent algorithms, the operating efficiency and response speed of the energy storage power station can be significantly improved. Second, by using machine learning models to evaluate the efficiency and status of energy storage units, the accuracy and reliability of scheduling decisions can be further improved. In addition, real-time data acquisition and online learning update mechanisms enable the system to flexibly adapt to changes in grid demand, ensuring the real-time and effectiveness of scheduling plans. Furthermore, the intelligent scheduling method of the present invention also has the ability to self-learn and self-optimize. Through the collaborative work of the policy network and the value network, dynamic adjustment and optimization of the charging and discharging plans of energy storage units can be achieved. This method can not only improve the economy and environmental friendliness of energy storage power stations, but also enhance the stability and resilience of the power grid. Through continuous technical iteration and optimization, the present invention provides strong technical support for the intelligent management of energy storage power stations and the sustainable development of the power grid, and has important practical value and social significance.

[0091] This embodiment also provides an artificial intelligence-based intelligent dispatching device for energy storage power stations. This device is used to implement the above-mentioned embodiments and preferred implementations, and the details that have been described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0092] This embodiment provides an intelligent dispatching device for energy storage power station based on artificial intelligence, such as Figure 3 Shown, including:

[0093] A screening module 31 is used to screen the energy storage units participating in the scheduling of the energy storage power station according to the operation plan of the energy storage power station and the grid demand;

[0094] A priority scheduling determination module 32 is configured to sort the selected energy storage units based on their efficiency and status, and select a preset number of energy storage units after sorting as priority scheduling units;

[0095] The scheduling and sorting module 33 is used to calculate the optimal charging and discharging plan of each priority scheduling unit and determine the scheduling order of the priority scheduling unit based on the optimal discharging plan;

[0096] The sorting module 34 is used to schedule the priority scheduling unit at the top of the scheduling order, use the artificial intelligence algorithm to adjust the charging and discharging plan of the scheduled priority scheduling unit, and evaluate the scheduling effect. If the scheduling effect does not meet the preset requirements, the next priority scheduling unit is scheduled, the charging and discharging plan is adjusted, and the scheduling effect is evaluated until the priority scheduling unit that meets the scheduling effect is scheduled.

[0097] In an optional embodiment, the energy storage units participating in the scheduling of the screened energy storage power station include a variety of energy storage unit combinations that meet the operation plan and grid demand, and each energy storage unit combination includes multiple energy storage units; the priority scheduling determination module includes: a first score matrix determination module, which is used to weight the importance of each energy storage unit in each energy storage unit combination to obtain a first score matrix reflecting the importance of the energy storage unit; an efficiency status index determination module, which is used to obtain an efficiency status index reflecting the energy storage unit based on the first parameter characteristics of the energy storage unit and a pre-constructed efficiency status index prediction model; a second score matrix determination module, which is used to construct a second score matrix reflecting the efficiency and status of the energy storage unit based on the score of the efficiency status index; a priority scheduling determination submodule, which is used to sort the screened energy storage units according to a third score matrix obtained by weighted merging of the first score matrix and the second score matrix, and select a preset number of energy storage units after sorting as priority scheduling units.

[0098] In an optional embodiment, a combination of multiple energy storage units is determined using an optimization algorithm, and the efficiency status indicators include charging and discharging efficiency and response time; the second score matrix determination module is specifically used to: arrange the efficiency status indicators in descending order to construct an indicator matrix; construct an efficiency status score matrix based on cluster analysis; multiply the indicator matrix and the score matrix, and combine them with the number of the energy storage unit to obtain a second score matrix.

[0099] In an optional embodiment, the scheduling sorting module is specifically used to: train a machine learning model based on the second parameter characteristics of the energy storage unit and the optimal charging and discharging plan to obtain a charging and discharging prediction model; and predict the optimal charging and discharging plan of each priority scheduling unit based on the current second parameter characteristics of each priority scheduling unit and the charging and discharging prediction model.

[0100] In an optional embodiment, the second parameter characteristics include the location, capacity, efficiency, current state of the energy storage unit and the degree of matching with the grid demand, and the optimal charging and discharging plan includes the time point, power size and duration of charging and discharging.

[0101] In an optional embodiment, the sorting module is specifically used to: adjust the charging and discharging plan of the priority scheduling unit based on the operating scenario data, based on a preset objective function and using a deep reinforcement learning algorithm.

[0102] In an optional embodiment, the deep reinforcement learning algorithm uses a policy network and a value network to adjust the charging and discharging plan; the policy network is used to obtain the charging and discharging plan based on the operating scenario data; the value network is used to obtain the operating scenario data and the charging and discharging plan, determine the matching degree between the energy storage power station and the grid demand and the operating efficiency of the energy storage unit as a reward, generate a reward function based on the reward, and use the reward function to optimize the policy network.

[0103] The further functional description of each of the above modules is the same as that of the above corresponding embodiments and will not be repeated here.

[0104] The embodiment of the present invention also provides a computer device having the above Figure 3 The artificial intelligence-based intelligent dispatching device for energy storage power stations shown.

[0105] See also Figure 4 , Figure 4 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 4 As shown, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in the memory or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 4 A processor 10 is taken as an example.

[0106] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0107] The memory 20 stores instructions that can be executed by at least one processor 10, so as to enable at least one processor 10 to execute the method shown in the above embodiment.

[0108] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created based on the use of a computer device for displaying a small program landing page, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0109] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0110] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0111] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0112] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0113] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. An intelligent scheduling method for energy storage power stations based on artificial intelligence, characterized in that: The method comprises: Select the energy storage units that will be dispatched in the energy storage power station based on the power station's operation plan and grid demand; Sort the selected energy storage units based on their efficiency and status, and select a preset number of energy storage units after sorting as priority scheduling units; Calculating the optimal charging and discharging plan for each priority scheduling unit, and determining the scheduling order of the priority scheduling units based on the optimal discharging plan; Based on the scheduling order, the priority scheduling unit that is scheduled first is scheduled, and the artificial intelligence algorithm is used to adjust the charging and discharging plan of the scheduled priority scheduling unit, and the scheduling effect is evaluated. If the scheduling effect does not meet the preset requirements, the next priority scheduling unit is scheduled, and the charging and discharging plan is adjusted and the scheduling effect is evaluated until the priority scheduling unit that meets the scheduling effect is scheduled.

2. The method according to claim 1, characterized in that The energy storage units participating in the scheduling of the selected energy storage power station include a variety of energy storage unit combinations that meet the operation plan and grid demand, and each energy storage unit combination includes multiple energy storage units; The selected energy storage units are sorted based on their efficiency and status, and a preset number of energy storage units are selected as priority scheduling units, including: Weighting and assigning scores to the importance of each energy storage unit in each energy storage unit combination to obtain a first score matrix reflecting the importance of the energy storage unit; Based on the first parameter characteristic of the energy storage unit and a pre-built efficiency status index prediction model, an efficiency status index reflecting the energy storage unit is obtained; Constructing a second score matrix reflecting the efficiency and status of the energy storage unit based on the scoring of the efficiency status indicator; The screened energy storage units are sorted according to a third score matrix obtained by weighted combination of the first score matrix and the second score matrix, and a preset number of energy storage units after sorting are selected as priority scheduling units.

3. The method according to claim 2, characterized in that The combination of multiple energy storage units is determined using an optimization algorithm, and efficiency status indicators include charge and discharge efficiency and response time; Based on the scoring of the efficiency status indicators, a second score matrix reflecting the efficiency and status of the energy storage unit is constructed, including: Arrange the efficiency status indicators in descending order to construct an indicator matrix; Constructing a score matrix of efficiency status based on cluster analysis; The indicator matrix and the score matrix are multiplied together, and combined with the numbers of the energy storage units to obtain a second score matrix.

4. The method according to claim 1, wherein Calculate the optimal charging and discharging plan for each priority dispatch unit, including: The machine learning model is trained based on the second parameter characteristics of the energy storage unit and the optimal charging and discharging scheme to obtain a charging and discharging prediction model; Based on the current second parameter characteristics of each priority scheduling unit and the charge and discharge prediction model, the optimal charge and discharge plan of each priority scheduling unit is predicted.

5. The method according to claim 4, characterized in that The second parameter characteristics include the location, capacity, efficiency, current state of the energy storage unit and the matching degree with the grid demand, and the optimal charging and discharging plan includes the time point, power size and duration of charging and discharging.

6. The method according to claim 1, characterized in that The artificial intelligence algorithm is used to adjust the charging and discharging plan of the priority scheduling unit, including: According to the operating scenario data, the charging and discharging plans of the priority scheduling units are adjusted based on the preset objective function and the deep reinforcement learning algorithm.

7. The method according to claim 6, characterized in that The deep reinforcement learning algorithm uses a policy network and a value network to adjust the charging and discharging plan; The strategy network is used to obtain a charging and discharging plan based on the operating scenario data; The value network is used to obtain the operating scenario data and charging and discharging plans, determine the matching degree between the energy storage power station and the grid demand and the operating efficiency of the energy storage unit as a reward, generate a reward function based on the reward, and use the reward function to optimize the strategy network.

8. An intelligent dispatching device for energy storage power station based on artificial intelligence, characterized in that: The device comprises: A screening module is used to screen the energy storage units participating in the scheduling of the energy storage power station based on the operation plan of the energy storage power station and the grid demand; A priority scheduling determination module is used to sort the screened energy storage units based on their efficiency and status, and select a preset number of energy storage units after sorting as priority scheduling units; A scheduling and sorting module is used to calculate the optimal charging and discharging plan of each priority scheduling unit, and determine the scheduling order of the priority scheduling unit based on the optimal discharge plan; The sorting module is used to schedule the priority scheduling unit at the top of the scheduling order, use artificial intelligence algorithm to adjust the charging and discharging plan of the scheduled priority scheduling unit, and evaluate the scheduling effect. If the scheduling effect does not meet the preset requirements, the next priority scheduling unit will be scheduled, the charging and discharging plan will be adjusted, and the scheduling effect will be evaluated until the priority scheduling unit that meets the scheduling effect is scheduled.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the artificial intelligence-based intelligent scheduling method for energy storage power stations according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, which are used to enable a computer to execute the artificial intelligence-based intelligent scheduling method for energy storage power stations according to any one of claims 1 to 7.

Images