An intelligent optimized shared energy storage system based on artificial intelligence algorithms

Abstract

The present invention discloses an intelligent optimized shared energy storage system based on artificial intelligence algorithms, which relates to the technical field of power system management. It includes a power central control module for collecting and preprocessing historical data of electricity-consuming entities; an electricity consumption prediction module for predicting future electricity consumption demands and evaluating electricity consumption capacity by training a long short-term memory neural network model; a charge and discharge control module for optimizing the charge and discharge strategies of energy storage devices according to the predicted electricity consumption data and electricity price data, and adjusting the energy storage output ratio using a genetic algorithm; a data encryption module for encrypting and uploading power transaction data to the blockchain using blockchain technology to ensure data security; and an anomaly diagnosis module for real-time monitoring and early warning of system anomalies through blockchain data analysis. It realizes the efficient optimized allocation and utilization of power resources, enhances data security and privacy protection, has efficient anomaly detection and fault diagnosis capabilities, and improves the dynamic response and flexibility of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of power system management, and particularly to an intelligent optimized shared energy storage system based on artificial intelligence algorithms. Background Art

[0002] With the rapid growth of social electricity demand, the development and utilization of new energy have rapidly expanded globally, and the construction of smart grids and distributed energy storage systems has increasingly become an important development direction in the power industry. As an emerging power management method, the shared energy storage system can integrate the energy storage resources of multiple electricity consumers to achieve more efficient electricity utilization. However, there are still some key technical problems in the management and optimization of existing shared energy storage systems.

[0003] Traditional shared energy storage systems mainly use preset rules or simple control algorithms to manage charge and discharge. These methods usually rely on fixed regulation strategies and are difficult to dynamically respond to complex market conditions and changing load demands. In practical applications, this static regulation method will lead to resource waste and low energy storage efficiency, and cannot fully realize the optimal allocation of power resources. In addition, traditional systems lack the ability to intelligently analyze the electricity consumption behaviors of different electricity consumers and are difficult to predict future electricity demands based on historical data and environmental conditions.

[0004] In the shared energy storage system, the electricity consumption data of different electricity consumers need to be transmitted, shared, and stored. In the prior art, many systems lack an effective encryption protection mechanism during data transmission, which easily leads to user data leakage and security risks.

[0005] The shared energy storage system may face various abnormal situations during actual operation, such as equipment failures and abnormal fluctuations in power loads. The abnormal diagnosis and fault detection of existing systems usually rely on manual monitoring or simple threshold alarms and cannot identify and locate abnormal problems in a timely and accurate manner. Summary of the Invention

[0006] Based on the above-mentioned disadvantages of the prior art, the purpose of the present invention is to provide an intelligent optimized shared energy storage system based on artificial intelligence algorithms to solve the above technical problems.

[0007] To achieve the above purpose, the present invention provides the following technical solution: An intelligent optimized shared energy storage system based on artificial intelligence algorithms, comprising:

[0008] A power central control module, configured to collect and sort out the historical data of electricity consumers, access it to the platform end of the shared energy storage system, and preprocess the historical electricity consumption data of electricity consumers, including feature transformation, feature screening, and dimensionality reduction processing;

[0009] An electricity consumption prediction module, which is used to train a long short-term memory neural network algorithm model through preprocessed historical electricity consumption data, predict the future electricity consumption data of electricity consumers, and evaluate the electricity consumption capacity on the demand side;

[0010] A charge and discharge control module, which is used to perform refined control on the charging and discharging of shared energy storage devices according to the predicted electricity consumption data and electricity price data of electricity consumers, determine the output strategy of shared energy storage devices through time-sharing load, balance the insufficient part through grid power, and optimize the actual output ratio of energy storage monomers through genetic algorithms;

[0011] A data encryption module, which is used to encrypt and store data using blockchain technology to ensure the security and effectiveness of data. When an electricity consumer conducts a power transaction through a shared energy storage system, the transaction data and the current energy storage operation status are uploaded to the blockchain to form a block with real-time information, and the power transaction within the shared energy storage system is realized through a consensus mechanism to ensure the security and effectiveness of data;

[0012] An abnormal diagnosis module, which is used to obtain blockchain data within the scope of shared energy storage, analyze it, ensure the data security of power generation units and electricity consumption units, realize abnormal monitoring of the electricity output of power generation units through an abnormal diagnosis algorithm, and give early warnings of potential risks.

[0013] The present invention is further configured that the dimensions of the historical data of electricity consumers include: electricity consumption data, time data, electricity price data, urban electricity load, shared energy storage system load, and environmental temperature;

[0014] Feature transformation includes: transforming the time data into time features, where the time features include season features, week features, and hour features; transforming the electricity price data, urban electricity load, shared energy storage system load, and environmental temperature into electricity price features, urban electricity load features, shared energy storage system load features, and environmental temperature features; transforming the electricity consumption data into electricity consumption features; standardizing the time features, electricity price features, urban electricity load features, shared energy storage system load features, and environmental temperature features to form a feature set;

[0015] Feature screening includes: setting the electricity consumption feature as the target feature, and setting the feature set as the feature set to be screened; calculating the resonance index and linear connection degree between the target feature and the features in the feature set to be screened, calculating the comprehensive correlation index according to the resonance index and linear connection degree, and selecting the features with a comprehensive correlation index greater than the set comprehensive correlation index threshold as the first screened feature set;

[0016] Dimensionality reduction processing includes: performing principal component analysis on the first screened feature set to obtain a second screened feature set after dimensionality reduction.

[0017] The present invention is further configured such that the calculation logic of the resonance index is as follows: , where is the resonance index of the th feature and the target feature . is the probability that the target variable takes the value of . is the probability that the target variable takes the value of under the condition of the given feature .

[0018] The calculation logic of the linear connection degree is as follows: , where is the linear connection degree of the th feature and the target feature . is the number of data. is the weighted average value of the th feature, and the calculation logic is: , , is the value of the th data for the th feature. is the weight of the th data, and the calculation logic is: , is the median of the th feature . is a constant. is the value of the th data for the th feature. is the value of the target feature of the th data. is the weighted average value of the target variable , and the calculation logic is: .

[0019] The present invention is further configured to normalize the resonance index and the linear connection degree, and calculate the comprehensive correlation index according to the normalized resonance index and linear connection degree. The calculation logic is: , where is the comprehensive correlation index of the th feature . and are weight coefficients, both greater than or equal to 0, and .

[0020] The present invention is further configured to train a long short - term memory neural network algorithm model through the pre - processed historical power consumption data, and predict the future power consumption data of the power consumption entity to evaluate the power consumption capacity on the demand side, including:

[0021] Combine the second screening feature set with the target feature to form a data set, where each sample contains a feature value and a corresponding target value, and organize the data into a time - series format according to the requirements of power consumption prediction;

[0022] Divide the data set into a training set and a test set, use the second screening feature set as the input, and the target feature as the output to train the long short - term memory neural network algorithm model;

[0023] Adopt the mean square error as the loss function, and train until the loss function converges or reaches the maximum preset number of training rounds;

[0024] Make predictions on the test set, calculate the performance metrics. When the performance metrics meet the requirements, predict the future power consumption data of the power consumption entity, and sum up the future power consumption data of all power consumption entities to obtain the power consumption capacity on the demand side.

[0025] The present invention is further configured that the charge - discharge control module includes:

[0026] A data integration unit for integrating the predicted power consumption data and the electricity price data into a data set and format the data set into a time - series form to support time - series analysis, where is the number of records at different time points;

[0027] A time - sharing load analysis unit for defining the time - sharing load as the power consumption demand at time and estimating it through interpolation, , where is the unit impulse function;

[0028] When the electricity price data is greater than the electricity price threshold, discharge, and the discharge amount is: ; when the electricity price data is greater than the electricity price threshold, charge, and the charge amount is: , where is the energy storage state of the current energy storage device. When discharging, when , balance it through grid power, and the balance amount is: .

[0029] The present invention is further configured such that when the shared energy storage device performs charging and discharging, a genetic algorithm is used to optimize the output ratio of the energy storage monomers.

[0030] Define the set of charging and discharging output ratios of all energy storage monomers as: , is the number of energy storage monomers, is the output ratio of the -th energy storage monomer, and the sum is one, and;

[0031] Define the charging fitness function: , where is the charging output ratio of the -th energy storage monomer, the -th charging electricity price of the energy storage monomer;

[0032] Define the discharging fitness function: , the -th discharging output ratio of the energy storage monomer, the -th discharging electricity price of the energy storage monomer;

[0033] Randomly generate multiple sets of charging and discharging output ratios, calculate the charging fitness function and the discharging fitness function. Among them, when charging, minimize the charging fitness function, and when discharging, maximize the discharging fitness function;

[0034] Select a preset number of parents from the minimum charging fitness function or the maximum discharging fitness function for crossover to generate the next generation of individuals. Until the maximum number of iterations or the target fitness function, select the set of charging and discharging output ratios with the maximum fitness and set it as the output ratio of the energy storage monomers.

[0035] The present invention is further configured such that the data encryption module includes:

[0036] A data encryption unit for encrypting the transaction data and the current energy storage operation status. Among them, the encryption algorithm includes a symmetric encryption algorithm or an asymmetric encryption algorithm;

[0037] An organization block unit that organizes the encrypted data into blocks. Among them, the block header includes a timestamp, the hash value of the previous block, and a Nonce value, and the block body includes the encrypted transaction data and the energy storage status data;

[0038] A blockchain processing unit for broadcasting the block to all nodes in the blockchain network to ensure that all nodes receive the new block, and realizing power transactions within the shared energy storage system through a consensus mechanism to ensure the security and effectiveness of the data.

[0039] The present invention is further configured such that the abnormal diagnosis module includes:

[0040] Obtain blockchain data within the scope of shared energy storage, decrypt it to obtain a data set;

[0041] Perform quartile analysis on the numerical data in the data set to obtain the first quartile, the second quartile, the third quartile, and the interquartile range. Among them, the first quartile is the value at the 25% position in the data set, the second quartile is the median of the data set, the third quartile is the value at the 75% position in the data, and the interquartile range is the value obtained by subtracting the first quartile from the third quartile;

[0042] When the numerical data in the data set is greater than the sum of the third quartile and 1.5 times the interquartile range, or when the numerical data in the data set is less than the difference between the first quartile and 1.5 times the interquartile range, mark the corresponding data, generate abnormal monitoring, and give an early warning.

[0043] The present invention is further configured such that the shared energy storage system supports virtual power plants and spot market transactions in the power market, and is used to provide a local consumption and surplus grid connection mode to reduce the impact on the power grid system.

[0044] The present invention provides an intelligent optimized shared energy storage system based on artificial intelligence algorithms. Through a power control center module, it is used to collect and organize the historical data of electricity-consuming entities, access it to the platform side of the shared energy storage system, and preprocess the historical electricity consumption data of electricity-consuming entities, including feature transformation, feature screening, and dimensionality reduction processing; an electricity consumption prediction module, which is used to train a long short-term memory neural network algorithm model through the preprocessed historical electricity consumption data and predict the future electricity consumption data of electricity-consuming entities to evaluate the electricity consumption capacity on the demand side; a charge and discharge control module, which is used to finely control the charging and discharging of shared energy storage devices according to the predicted electricity consumption data and electricity price data of electricity-consuming entities, determine the output strategy of shared energy storage devices through time-sharing loads, balance the insufficient part through grid power, and optimize the actual output ratio of energy storage monomers through genetic algorithms; a data encryption module, which is used to encrypt and store data using blockchain technology to ensure the safety and effectiveness of data. When an electricity-consuming entity conducts a power transaction through the shared energy storage system, the transaction data and the current energy storage operation status are uploaded to the blockchain to form a block with real-time information, and power transactions within the shared energy storage system are realized through a consensus mechanism to ensure the safety and effectiveness of data; an abnormal diagnosis module, which is used to obtain blockchain data within the scope of shared energy storage, analyze it to ensure the data security of the power generation unit and the electricity consumption unit, realize abnormal monitoring of the electricity output of the power generation unit through an abnormal diagnosis algorithm, and give an early warning of potential risks. The beneficial effects generated include:

[0045] 1. Improve the optimal allocation and utilization efficiency of power resources: Through the current prediction module and the power central control module, the present invention can deeply analyze the historical power consumption data of power-consuming entities, predict future power consumption demands, and dynamically adjust the energy storage strategy in combination with real-time electricity prices and market conditions, improving the utilization efficiency of power resources, reducing power consumption costs, and avoiding the problem of resource waste caused by static regulation in traditional shared energy storage systems;

[0046] 2. Enhance data security and privacy protection: Through the data encryption module, sensitive information such as transaction data and power consumption data in the energy storage system is encrypted, effectively preventing data from being stolen or tampered with during transmission and storage. In addition, the blockchain encryption storage mechanism is adopted to ensure the immutability and traceability of data, further improving the security of the system and user privacy protection. Through the design of the data encryption module, the present invention provides multi-level security guarantees in the data transmission and storage links of the shared energy storage system, effectively reducing the risks of data leakage and privacy infringement, and ensuring the security and credibility of the system in a multi-user environment;

[0047] 3. Achieve efficient anomaly detection and fault diagnosis: Through the anomaly diagnosis module, the data in the shared energy storage system can be monitored and analyzed in real time. Once abnormal fluctuations or fault signals are detected, the system can automatically identify and trigger the warning mechanism. Compared with the traditional alarm methods relying on manual monitoring or simple thresholds, the intelligent anomaly detection function of the present invention can quickly and accurately identify potential problems, helping to maintain and optimize the system operation status in a timely manner, thus improving the reliability and stability of the energy storage system;

[0048] 4. Improve the dynamic response ability and flexibility of the system: The present invention optimizes the energy storage strategy according to real-time market conditions and environmental factors through dynamic feature screening and dimensionality reduction processing technologies, thereby enhancing the response ability of the system. In the case of large electricity price fluctuations or drastic changes in power consumption demands, the system can quickly adjust the charge and discharge modes of the energy storage units to achieve the optimal allocation of power resources. This efficient and flexible dynamic response mechanism enables the present invention to achieve the optimal operation effect in various complex power market environments and has strong adaptability.

[0049] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the specific embodiments of this application are hereinafter specifically exemplified. Brief Description of the Drawings

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. In the drawings:

[0051] Figure 1 It is a schematic structural diagram of an intelligent optimized shared energy storage system based on an artificial intelligence algorithm shown in an exemplary embodiment of the present invention. Detailed implementation manners

[0052] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation manners. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for explaining the present invention, rather than for limiting the protection scope of the present invention.

[0053] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner. Therefore, only the components related to the present invention are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and proportion of each component in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0054] In the following description, a large number of details are explored to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0055] An intelligent optimized shared energy storage system based on an artificial intelligence algorithm, as Figure 1 shown, includes:

[0056] A power central control module, configured to collect and organize the historical data of electricity-consuming entities, access it to the platform side of the shared energy storage system, and preprocess the historical electricity consumption data of electricity-consuming entities, including feature transformation, feature screening, and dimensionality reduction processing;

[0057] An electricity consumption prediction module, configured to train a long short-term memory neural network algorithm model through the preprocessed historical electricity consumption data, and predict the future electricity consumption data of electricity-consuming entities to evaluate the electricity consumption capacity on the demand side;

[0058] A charge and discharge control module is used to conduct refined control over the charge and discharge of a shared energy storage device based on the predicted electricity consumption data and electricity price data of the electricity-consuming entity, determine the output strategy of the shared energy storage device through time-sharing load, balance the insufficient part through grid power, and optimize the actual output ratio of energy storage monomers through a genetic algorithm;

[0059] A data encryption module is used to encrypt and store data using blockchain technology to ensure the security and effectiveness of the data. When the electricity-consuming entity conducts a power transaction through the shared energy storage system, the transaction data and the current energy storage operation status are uploaded to the blockchain to form a block with real-time information, and the power transaction within the shared energy storage system is realized through a consensus mechanism to ensure the security and effectiveness of the data;

[0060] An anomaly diagnosis module is used to obtain blockchain data within the scope of the shared energy storage, conduct analysis to ensure the data security of the power generation unit and the electricity-consuming unit, realize anomaly monitoring of the electricity output of the power generation unit through an anomaly diagnosis algorithm, and give early warnings of potential risks.

[0061] The present invention is further configured such that the dimensions of the historical data of the electricity-consuming entity include: electricity consumption data, time data, electricity price data, urban electricity load, shared energy storage system load, and environmental temperature;

[0062] Feature transformation includes: converting the time data into time features, where the time features include season features, week features, and hour features; converting the electricity price data, urban electricity load, shared energy storage system load, and environmental temperature into electricity price features, urban electricity load features, shared energy storage system load features, and environmental temperature features; converting the electricity consumption data into electricity consumption features; and normalizing the time features, electricity price features, urban electricity load features, shared energy storage system load features, and environmental temperature features to form a feature set;

[0063] Feature screening includes: setting the electricity consumption feature as the target feature and setting the feature set as the feature set to be screened; calculating the resonance index and linear connection degree between the target feature and the features in the feature set to be screened, calculating the comprehensive correlation index based on the resonance index and linear connection degree, and selecting the features with a comprehensive correlation index greater than the set comprehensive correlation index threshold as the first screened feature set;

[0064] Dimensionality reduction processing includes: performing principal component analysis on the first screened feature set to obtain a second screened feature set after dimensionality reduction.

[0065] The present invention is further configured such that the calculation logic of the resonance index is: , where is the th feature and the target feature The resonance index, The target variable The value is The probability of For a given feature Under the condition that The value is Specifically, the above resonance index is used to measure the ability to distinguish between features, by calculating the target variable in each category In a given feature The joint probability of , measure the characteristics and the target variable The degree of correlation can effectively identify features with high correlation with the target variable, thereby helping to select the features that contribute most to the model effect and improve the performance of the model.

[0066] The calculation logic of the linear connection degree is: ,in, For the Features and target features The linear connection degree, is the number of data, For the Features The weighted average value is calculated as follows: , For the The data The value of the feature, For the The weight of each data is calculated as follows: , For the Features the median of is a constant, For the The data The value of the feature, For the The target characteristics of the data The value of The target variable The weighted average of is calculated as follows: ; Specifically, the linear connection degree is calculated by weighted average feature and the target variable The linear discreteness between them is used to evaluate the explanatory power of the feature on the target feature. First, the weighted mean and weighted standard deviation are calculated, and then the linear connection between the feature and the target is obtained through the linear coupling formula for feature selection and evaluation. The constant The value range is [0.1, 1]; by calculating the linear coupling degree between the feature and the target feature, features with high interpretability for the target feature can be effectively identified, thereby improving the accuracy and discriminative ability of the model. Using weighted average and combining with the median to calculate the weights can effectively reduce the influence of outliers on the calculation results, making the coupling degree calculation more robust.

[0067] The present invention is further configured to normalize the resonance index and the linear coupling degree, and calculate the comprehensive correlation index according to the normalized resonance index and linear coupling degree. The calculation logic is as follows: , where is the th feature 's comprehensive correlation index, and are weight coefficients, both greater than or equal to 0, and . Specifically, by simultaneously considering non-linear resonance and linear coupling, the comprehensive correlation index provides a more comprehensive feature evaluation method, making feature selection more accurate and comprehensive. The weights of the resonance index and the linear coupling degree can be controlled by adjusting and , so as to adapt to the characteristic requirements of different data sets and provide greater flexibility for feature selection.

[0068] The present invention is further configured to train a long short-term memory neural network algorithm model through the preprocessed historical electricity consumption data, and predict the future electricity consumption data of the electricity-consuming entity to evaluate the electricity consumption capacity on the demand side, including:

[0069] Combine the second screened feature set with the target feature to form a data set. Each sample contains a feature value and a corresponding target value. According to the requirements of electricity consumption prediction, the data is organized in a time series format;

[0070] Divide the data set into a training set and a test set. Use the second screened feature set as the input and the target feature as the output to train the long short-term memory neural network algorithm model;

[0071] Use the mean square error as the loss function and train until the loss function converges or reaches the maximum preset number of training rounds;

[0072] Predict on the test set, calculate performance metrics. When the performance metrics meet the requirements, predict the future electricity consumption data of electricity users, sum up the future electricity consumption data of all electricity users, and obtain the electricity consumption capacity on the demand side. Specifically, the Long Short-Term Memory (LSTM) neural network is a special type of recurrent neural network (RNN) that is good at processing time series data. Through the "memory gate" and "forget gate" mechanisms, LSTM can capture dependencies over long time spans and is suitable for dynamic prediction of electricity demand. It is a prior art and will not be elaborated here. Using the LSTM model can effectively capture the time dependence of electricity consumption data, thus accurately predicting future electricity demand and helping decision-makers allocate resources reasonably.

[0073] The present invention is further configured such that the charge and discharge control module includes:

[0074] A data integration unit for integrating the predicted electricity consumption data and electricity price data into a data set and formatting the data set into a time series form to support time series analysis, where is the number of records at different time points;

[0075] A time-sharing load analysis unit for defining the time-sharing load as the electricity demand at time estimated by the interpolation method, , where is the unit impulse function; specifically, the above calculation logic defines the calculation method of the time-sharing load to represent the electricity demand at a specific time . By the interpolation method, multiply the electricity consumption data at multiple time points by the unit impulse function and accumulate them to generate a load curve at any time, effectively converting discrete electricity consumption data points into continuous load demands, which is suitable for predicting and regulating the load distribution of the system; the unit impulse function is a function used to generate an instantaneous value at a specific time point. is equal to 1 at and 0 at other time points, and is used to selectively activate the electricity demand at the corresponding time point . Through the time-sharing load analysis unit, the present invention can estimate the electricity demand at any time point, improving the monitoring accuracy of load changes; the interpolation method converts discrete load data into a continuous load function, avoiding the possible mutation phenomenon in traditional discrete prediction, thus making the load prediction curve smoother and closer to the actual situation.

[0076] When the electricity price data is greater than the electricity price threshold, discharge is performed, and the discharge amount is: ; when the electricity price data is greater than the electricity price threshold, charging is performed, and the charging amount is: , where is the energy storage state of the current energy storage device. When discharging, when , it is balanced by grid power, and the balancing amount is: .

[0077] The present invention is further configured such that when the shared energy storage device performs charge and discharge, a genetic algorithm is used to optimize the output ratio of the energy storage monomers;

[0078] Define the set of charge and discharge output ratios of all energy storage monomers as: , is the number of energy storage monomers, is the output ratio of the th energy storage monomer, and the sum is one, and;

[0079] Define the charging fitness function: , where is the charging output ratio of the th energy storage monomer, the th energy storage monomer's charging electricity price; define the discharging fitness function: , the th energy storage monomer's discharging output ratio, the th energy storage monomer's discharging electricity price; specifically, define the charging fitness function and the discharging fitness function are respectively used to evaluate the adaptability of the charging and discharging strategies of the energy storage system within a specific time period. These two functions calculate the fitness value by accumulating the product of the charging and discharging output ratios of the energy storage units and the electricity price, thereby reflecting the charging and discharging efficiency of the energy storage system under different electricity price conditions. This method can help optimize the charge and discharge scheduling of the energy storage units, enabling the system to perform energy management at the optimal cost in different time periods.

[0080] Randomly generate multiple sets of charge and discharge output ratios, calculate the charging fitness function and the discharging fitness function. Among them, when charging, minimize the charging fitness function, and when discharging, maximize the discharging fitness function;

[0081] Select a preset number of parents from the minimum charging fitness function or the maximum discharging fitness function for crossover to generate the next generation of individuals. Until the maximum number of iterations or the target fitness function is reached, select the set of charging and discharging output ratios with the maximum fitness and set it as the output ratio of the energy storage cell.

[0082] The present invention is further configured such that the data encryption module includes:

[0083] A data encryption unit for encrypting the transaction data and the current energy storage operation state. Among them, the encryption algorithm includes a symmetric encryption algorithm or an asymmetric encryption algorithm;

[0084] An organization block unit for organizing the encrypted data into blocks. Among them, the block header includes a timestamp, the hash value of the previous block, and a Nonce value, and the block body includes the encrypted transaction data and the energy storage state data;

[0085] A blockchain processing unit for broadcasting the block to all nodes in the blockchain network to ensure that all nodes receive the new block, and realizing the power transaction in the shared energy storage system through a consensus mechanism to ensure the security and effectiveness of the data. Specifically, the data encryption module adopts blockchain technology to ensure the security of the transaction data in the shared energy storage system through encryption and blockchain methods. The data encryption module consists of the following units, and each unit works together to achieve the secure storage and reliable transmission of data; Data encryption unit: responsible for encrypting the transaction data and the current energy storage operation state to ensure the security of sensitive information during transmission and storage. The encryption algorithm can be symmetric encryption or asymmetric encryption, and the most suitable encryption method is selected according to the security requirements; Organization block unit: packing the encrypted data into blocks. Each block includes a block header and a block body. The block header contains a timestamp, the hash value of the previous block, and a random number (Nonce value) to ensure the order and immutability of the block; the block body contains the actual encrypted transaction data and the energy storage state data; Blockchain processing unit: broadcasting the generated block to all nodes in the blockchain network. Through the consensus mechanism, all nodes can verify and receive the new block, thereby realizing the synchronization and verification of the data across the network. This mechanism ensures the authenticity and security of the power transaction data in the shared energy storage system.

[0086] The present invention is further configured such that the abnormal diagnosis module includes:

[0087] Obtain the blockchain data within the shared energy storage range, decrypt it to obtain a data set;

[0088] Perform quartiles on the numerical data in the dataset to obtain the first quartile, the second quartile, the third quartile, and the interquartile range. Among them, the first quartile is the value at the 25% position in the dataset, the second quartile is the median of the dataset, the third quartile is the value at the 75% position in the data, and the interquartile range is the value obtained by subtracting the first quartile from the third quartile;

[0089] When the numerical data in the dataset is greater than the sum of the third quartile and 1.5 times the interquartile range, or when the numerical data in the dataset is less than the difference between the first quartile and 1.5 times the interquartile range, mark the corresponding data, generate anomaly monitoring, and issue an early warning. Specifically, by calculating the quartiles and ranges of the data, a deeper understanding of the central tendency and dispersion of the data can be obtained, making the anomaly detection more robust and having a higher tolerance for extreme values; once data outside the normal range is detected, the system can immediately mark and generate a warning message, thereby discovering potential equipment failures or operation anomalies in advance and ensuring the stability and safety of the shared energy storage system.

[0090] The present invention is further configured such that the shared energy storage system supports virtual power plants and spot market trading in the power market, and is used to provide local consumption and surplus grid connection modes to reduce the impact on the grid system. Specifically, the shared energy storage system further enhances its adaptability to the power market, supports the application of virtual power plants, and can participate in spot market trading in the power market, thereby realizing local power consumption and power surplus grid connection. This mechanism can optimize the economic benefits of the shared energy storage system and, to a certain extent, relieve the load pressure on the grid system. Virtual power plant support: A virtual power plant (VPP) is a distributed energy management method that can integrate dispersed energy storage devices and power generation units into a "virtual" power supply entity to uniformly dispatch and manage multiple energy storage units in the shared energy storage system. Through virtual power plant management, the shared energy storage system can respond to changes in power market demand in a clustered manner, balance supply and demand fluctuations, and improve the operating efficiency of the energy storage system; Spot market trading in the power market: Spot market trading is a real-time power trading mode. Through the trading platform, the energy storage system can perform charge and discharge operations according to real-time electricity prices. The shared energy storage system charges during low electricity price periods and discharges during high electricity price periods to maximize profits. At the same time, spot market trading provides a dynamic pricing mechanism for the energy storage system, enabling it to participate in market competition more flexibly. Local consumption and surplus grid connection: The local consumption mode enables the shared energy storage system to preferentially consume locally generated renewable energy electricity (such as solar and wind energy), reduce dependence on purchased electricity, and increase the energy self-sufficiency rate. The surplus grid connection mode allows the surplus electricity to be sold back to the grid when local power consumption is saturated, further realizing the profitability of the energy storage system.

[0091] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0092] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. Additionally, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood with reference to the context before and after.

[0093] In the present application, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0094] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not imply the order of execution. The order of execution of each process should be determined based on its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0095] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0096] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0097] In several embodiments provided in this application, it should be understood that the disclosed systems can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be electrical, mechanical, or other forms.

[0098] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0099] In addition, the functional units in each embodiment of this application can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0100] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0101] As described above, the above are only specific implementation manners of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. An intelligent optimization shared energy storage system based on artificial intelligence algorithm, characterized in that: include: The power central control module is used to collect and organize the historical data of the power users, connect to the shared energy storage system platform, and pre-process the historical power consumption data of the power users. It includes feature conversion, feature screening and dimensionality reduction processing. Feature screening includes: setting the power consumption feature as the target feature and setting the feature set as the feature set to be screened; calculating the resonance index and linear connection degree between the target feature and the features in the feature set to be screened, calculating the comprehensive correlation index according to the resonance index and the linear connection degree, selecting the features whose comprehensive correlation index is greater than the set comprehensive correlation index threshold, and setting them as the first screening feature set; The electricity consumption prediction module is used to train the long short-term memory neural network algorithm model through the pre-processed historical electricity consumption data, and predict the future electricity consumption data of the electricity users to evaluate the electricity consumption capacity on the demand side; The charging and discharging control module is used to finely control the charging and discharging of shared energy storage equipment according to the predicted power consumption data and electricity price data of the power users. The output strategy of the shared energy storage equipment is determined by the time-sharing load. The shortfall is balanced by the power of the grid. The actual output ratio of the energy storage unit is optimized by genetic algorithms. The data encryption module is used to encrypt and store data using blockchain technology to ensure data security and effectiveness. When the electricity user conducts electricity transactions through the shared energy storage system, the transaction data and the current energy storage operation status are uploaded to the chain to form a block with real-time information. The power transaction within the shared energy storage system is realized through the consensus mechanism to ensure data security and effectiveness. The abnormality diagnosis module is used to obtain blockchain data within the scope of shared energy storage, analyze it, ensure the data security of power generation units and power consumption units, monitor the abnormality of power output of power generation units through abnormality diagnosis algorithms, and provide early warning of potential risks; The calculation logic of the resonance index is: ,in, For the Features and target features The resonance index, The target variable The value is The probability of For a given feature Under the condition that The value is probability; The calculation logic of the linear connection degree is: ,in, For the Features and target features The linear connection degree, is the number of data, For the Features The weighted average value is calculated as follows: , For the The data The value of the feature, For the The weight of each data is calculated as follows: , For the Features the median of is a constant, For the The data The value of the feature, For the The target characteristics of the data The value of The target variable The weighted average of is calculated as follows: .

2. According to claim 1, an intelligent optimization shared energy storage system based on artificial intelligence algorithm is characterized in that: The dimensions of the historical data of electricity users include: electricity consumption data, time data, electricity price data, city power load, shared energy storage system load and ambient temperature; The feature conversion includes: converting the time data into time features, the time features include season features, week features and hour features; converting the electricity price data, city power load, shared energy storage system load and ambient temperature into electricity price features, city power load features, shared energy storage system load features and ambient temperature features; converting the power consumption data into power consumption features; standardizing the time features, electricity price features, city power load features, shared energy storage system load features and ambient temperature features to set them as feature sets; The dimensionality reduction process includes: performing principal component analysis on the first screening feature set to obtain a second screening feature set after dimensionality reduction.

3. According to claim 1, an intelligent optimization shared energy storage system based on artificial intelligence algorithm is characterized in that: The resonance index and linear connection degree are normalized, and the comprehensive correlation index is calculated based on the normalized resonance index and linear connection degree. The calculation logic is: ,in, For the Features The comprehensive correlation index of and are weight coefficients, all greater than or equal to 0, and .

4. According to claim 1, an intelligent optimization shared energy storage system based on artificial intelligence algorithm is characterized in that: The long short-term memory neural network algorithm model is trained through the pre-processed historical electricity consumption data, and the future electricity consumption data of the electricity users is predicted to evaluate the electricity consumption capacity on the demand side, including: The second screening feature set is combined with the target feature to form a data set, wherein each sample includes a feature value and a corresponding target value, and the data is organized into a time series format according to the needs of the electricity consumption forecast; The data set is divided into a training set and a test set, the second screening feature set is used as input, the target feature is used as output, and the long short-term memory neural network algorithm model is trained; Use mean square error as the loss function and train until the loss function converges or reaches the maximum preset training rounds; Predictions are made on the test set and performance indicators are calculated. When the performance indicators meet the requirements, the future electricity consumption data of the electricity users is predicted. The future electricity consumption data of all electricity users are added together to obtain the electricity consumption capacity on the demand side.

5. The intelligent optimization shared energy storage system based on artificial intelligence algorithm according to claim 1 is characterized in that: The charge and discharge control module includes: Data integration unit, used to integrate the predicted power consumption data and electricity price data Integrate into datasets , format the dataset into a time series format To support timing analysis, is the number of records at different time points; Time-sharing load analysis unit, used to define time-sharing load For in time The electricity demand is estimated by interpolation. , is the unit pulse function; When electricity price data When the power is greater than the electricity price threshold, discharge is performed, and the discharge amount is: When electricity price data When the electricity price is greater than the threshold, charging is performed, and the charging amount is: ,in, is the current energy storage state of the energy storage device. When discharging, When the power grid is used for balancing, the balancing amount is: .

6. The intelligent optimization shared energy storage system based on artificial intelligence algorithm according to claim 5 is characterized in that: When the shared energy storage device is charged and discharged, a genetic algorithm is used to optimize the output ratio of the energy storage unit; The charge and discharge output ratio set of all energy storage monomers is defined as: , is the number of energy storage units, For the The output ratio of each energy storage unit sums to one, and; Define the charging fitness function: ,in, For the The charging output ratio of each energy storage unit, No. The charging price of each energy storage unit; Define the discharge fitness function: , No. The discharge output ratio of each energy storage unit, No. The discharge electricity price of each energy storage unit; Randomly generate multiple charging and discharging output ratio sets, calculate the charging fitness function and the discharging fitness function, wherein when charging, the charging fitness function is minimized, and when discharging, the charging fitness function is maximized; Select a preset number of parents from the minimum charging fitness function or the maximum discharging fitness function for crossover to generate the next generation of individuals, until the maximum number of iterations or the target fitness function, select the charging and discharging output ratio set with the largest fitness and set it as the output ratio of the energy storage monomer.

7. The intelligent optimization shared energy storage system based on artificial intelligence algorithm according to claim 1 is characterized in that: The data encryption module comprises: A data encryption unit, used to encrypt the transaction data and the current energy storage operation status, wherein the encryption algorithm includes a symmetric encryption algorithm or an asymmetric encryption algorithm; Organizing block units, organizing the encrypted data into blocks, where the block header includes a timestamp, a hash value of the previous block and a Nonce value, and the block body includes encrypted transaction data and energy storage status data; The on-chain processing unit is used to broadcast the block to all nodes in the blockchain network, ensure that all nodes receive the new block, realize power trading in the shared energy storage system through the consensus mechanism, and ensure data security and effectiveness.

8. The intelligent optimization shared energy storage system based on artificial intelligence algorithm according to claim 1 is characterized in that: The abnormality diagnosis module comprises: Obtain blockchain data within the shared energy storage range, decrypt it, and obtain a data set; Quartile the numerical data in the data set to obtain the first quartile, second quartile, third quartile and interquartile range, where the first quartile is the value at the 25% position in the data set, the second quartile is the median of the data set, the third quartile is the value at the 75% position in the data, and the interquartile range is the value of the third quartile minus the first quartile; When the numerical data in the data set is greater than the sum of the third quartile and 1.5 times the interquartile range, or when the numerical data in the data set is less than the difference between the first quartile and 1.5 times the interquartile range, the corresponding data will be marked, abnormal monitoring will be generated, and early warning will be issued.

9. The intelligent optimization shared energy storage system based on artificial intelligence algorithm according to claim 1 is characterized in that: The shared energy storage system supports virtual power plants and spot market transactions with the electricity market to provide local consumption and surplus grid-connected modes, thereby reducing the impact on the power grid system.

Images