A charging and discharging control method for mobile energy storage equipment based on electricity price and electricity quantity

Abstract

The present invention discloses a mobile energy storage device charge and discharge control method based on electricity price and electricity quantity, the method comprising S1, adjusting the charge and discharge power distribution of each mobile energy storage device in real time based on load prediction data when multiple users access, S2, determining the optimal charge and discharge strategy of each mobile energy storage device according to the current power grid electricity price and electricity demand, S3, predicting the user load change trend in the next time period, S4, dynamically optimizing the charge and discharge plan of each mobile energy storage device according to the prediction result, S5, monitoring the actual operation state of each mobile energy storage device, and feedback adjusting the charge and discharge instructions to ensure uniform power distribution; the mobile energy storage device charge and discharge control method based on electricity price and electricity quantity solves the problem that the prior art cannot fully adapt to the variable electricity price and user demand environment in practical applications, which has an adverse effect on the economy and reliability of the energy storage system.

Description

Technical Field

[0001] The present invention relates to the technical field of power system automation, and in particular to a method for controlling charging and discharging of a mobile energy storage device based on electricity price and electricity quantity. Background Art

[0002] In existing mobile energy storage systems, the main purpose of the charge and discharge control method is to optimize the energy efficiency and cost-effectiveness of energy storage equipment by adjusting the charge and discharge strategy in real time under the condition of electricity price fluctuations. This type of system usually uses an optimization algorithm to dynamically decide whether to charge or discharge according to the real-time changes in electricity prices and the power state of the energy storage device to maximize economic benefits. However, in practical applications, this method faces many challenges.

[0003] First, in the scenario where multiple users are connected at the same time, power needs to be allocated according to the load demand of each user. However, the large error in load prediction often leads to deviations between actual power demand and expectations. This inconsistent power demand not only increases the imbalance of power distribution, but also causes load fluctuations in the energy storage system, affecting the stability of the entire system. In addition, when power allocation cannot meet the needs of all users, the electricity experience of some users is reduced, thereby reducing the service quality of the system. Secondly, the existing technology has limitations in the response speed of power allocation, especially when electricity prices change frequently, the optimization algorithm cannot respond in time, resulting in delays in charging and discharging decisions. Therefore, this method cannot fully adapt to the changing electricity prices and user demand environment in actual applications, which has an adverse impact on the economy and reliability of the energy storage system. Summary of the invention

[0004] The purpose of the present invention is to provide a mobile energy storage device charging and discharging control method based on electricity price and electricity quantity, so as to solve the problem that the large error of load prediction in the prior art often leads to deviation between actual power demand and expectation. This inconsistent power demand not only increases the imbalance of power distribution, but also causes load fluctuation of the energy storage system, affecting the stability of the entire system. In addition, when the power distribution cannot meet the needs of all users, the electricity consumption experience of some users is reduced, thereby reducing the service quality of the system. The prior art has limitations in the response speed of power distribution, especially when the electricity price changes frequently, the optimization algorithm cannot respond in time, resulting in delays in charging and discharging decisions. Therefore, this method cannot fully adapt to the changing electricity price and user demand environment in actual applications, which has an adverse effect on the economy and reliability of the energy storage system.

[0005] To achieve the above object, the present invention provides the following technical solution: a method for controlling charging and discharging of a mobile energy storage device based on electricity price and electricity quantity, the method comprising:

[0006] S1. Based on the load forecast data when multiple users access, the charging and discharging power distribution of each mobile energy storage device is adjusted in real time;

[0007] S2. According to the current power grid electricity price and power demand, determine the optimal charging and discharging strategy for each mobile energy storage device, specifically: the charging and discharging operations of all energy storage devices are divided into various strategy spaces, and the benefits of each device are constructed by setting the benefit function and the operation cost function. Solve to find the balanced charging and discharging strategy combination of all devices under the current electricity price, and use the obtained solution to guide each device to perform charging and discharging operations to minimize the overall system cost;

[0008] S3, predicting the user load change trend in the next time period;

[0009] S4. Dynamically optimize the charging and discharging plans of each mobile energy storage device based on the prediction results, specifically: encode each round of decision-making of the charging and discharging plan into genes, randomly generate a group of individuals to form an initial population, each individual represents a potential charging and discharging strategy, define a fitness function to evaluate the pros and cons of each charging and discharging strategy, select the individual with the highest fitness from the current population to enter the next generation, perform crossover operations on the selected individuals to generate the next generation of individuals, and the generated new individuals replace the previous generation of population to form a new population, recalculate the fitness of each individual in the new generation of population, iterate multiple rounds, and finally select the individual with the highest fitness as the current optimal charging and discharging strategy;

[0010] S5. Monitor the actual operating status of each mobile energy storage device, and provide feedback to adjust the charging and discharging instructions to ensure uniform power distribution.

[0011] Preferably, the S1 comprises:

[0012] Collect historical load data and current load real-time data, and make predictions and updates on the current load status. Assuming that the prior probability of load demand comes from historical data, the posterior probability of load demand is calculated in combination with real-time observation data. The specific calculation formula is:

[0013] ;

[0014] in, represents the assumed future load demand, Represents the observed real-time data, Indicates that real-time data is observed In the case of future load demand The posterior probability of It means that under the assumption that the future load demand is Under the premise of observing real-time data The probability of Indicates future load demand The prior probability of Represents the observed data The marginal probability of .

[0015] Preferably, S2 further includes:

[0016] The specific calculation formula for building the benefits of each device is:

[0017] ;

[0018] in, Indicates The revenue function of an energy storage device is: Indicates the charging and discharging selection strategy of the device, Indicates the policy combination of other devices. Indicates income, Indicates cost.

[0019] Preferably, S3 includes:

[0020] Collect and standardize user load time series data, extract the characteristics of different frequency bands, decompose the load signal into low-frequency and high-frequency parts, use the low-frequency part as the basic data for long-term load forecasting, and combine the high-frequency part to make short-term fluctuation adjustments. The forecast results are used in the scheduling decision of the charging and discharging plan for the next time period. The specific public disclosure of the characteristics of different frequency bands is as follows:

[0021] ;

[0022] in, Represents the time signal, Indicates time, Indicates signal The size of the components at different scales and locations, Indicated in scale and location The basis functions on represents the scale parameter, Represents a positional parameter.

[0023] Preferably, S4 includes:

[0024] The fitness function is positioned as:

[0025] ;

[0026] in, represents the value of the fitness function, represents the total time period, Indicates at time The discharge gain, Indicates at time The charging cost, Indicates time.

[0027] Preferably, S5 includes:

[0028] Define power error, error change rate, charge and discharge instructions and their fuzzy membership functions, build a fuzzy reasoning rule base, map the errors and error changes under different states to the control strategy, use fuzzy reasoning to process the real-time monitored power distribution data, obtain the output charge and discharge instructions, implement fuzzy control feedback, convert the fuzzy output into specific instructions and send them to the energy storage device to achieve uniform power distribution.

[0029] Preferably, the S1 further comprises:

[0030] Obtain real-time load data when multiple users access;

[0031] Calculate the deviation between the current total load and the predicted load;

[0032] Adjust the charging and discharging power of each mobile energy storage device based on the deviation value;

[0033] Wherein, adjusting the charging and discharging power of each mobile energy storage device based on the deviation value includes:

[0034] Obtain the current state of charge SOC of each mobile energy storage device;

[0035] Calculate the ratio of the deviation value to the maximum deviation value R = deviation value / maximum deviation value, where R is the ratio, indicating the ratio of the deviation value to the maximum deviation value;

[0036] The charging and discharging power of each mobile energy storage device is adjusted based on the ratio R.

[0037] Preferably, adjusting the charging and discharging power of each mobile energy storage device based on the ratio R includes:

[0038] Determine the initial charge and discharge power of each mobile energy storage device;

[0039] Calculate the new charge and discharge power P of each device new =P initial × (1 + R × K), where P new is the new charge and discharge power, P initial is the initial charge and discharge power, K is the adjustment coefficient, and R is the ratio.

[0040] Preferably, the cost in S2 is Including the charging cost of energy storage equipment, equipment depreciation cost and power transmission loss cost.

[0041] Preferably, the S1 load forecast data includes temperature, weather and seasonal load changes.

[0042] It can be seen from the above technical solution that the present invention has the following beneficial effects:

[0043] The mobile energy storage device charge and discharge control method based on electricity price and electricity quantity adjusts the charge and discharge power distribution of each mobile energy storage device in real time based on the load forecast data when multiple users access, determines the optimal charge and discharge strategy of each mobile energy storage device according to the current power grid electricity price and electricity demand, predicts the user load change trend in the next time period, dynamically optimizes the charge and discharge plan of each mobile energy storage device according to the prediction result, monitors the actual operation status of each mobile energy storage device, and feedback adjusts the charge and discharge instructions to ensure uniform power distribution and reduce the power demand prediction error, thereby realizing accurate power distribution in multi-user scenarios, avoiding load fluctuations caused by unbalanced power distribution, and ensuring the stability of the system and the user's power experience. In addition, the present invention optimizes the real-time response capability of the charge and discharge control algorithm, can quickly adjust the charge and discharge strategy in the case of frequent changes in electricity prices, effectively shortens the decision delay time, and improves the system's adaptability to electricity price fluctuations, thereby achieving higher economic benefits and service quality, and solves the problem that the existing technology cannot fully adapt to the variable electricity price and user demand environment in practical applications, which has an adverse effect on the economy and reliability of the energy storage system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] like Figure 1 As shown, the present invention provides a technical solution: a method for controlling charging and discharging of a mobile energy storage device based on electricity price and electricity quantity, the method comprising:

[0047] S1. Based on the load forecast data when multiple users are connected, the charging and discharging power distribution of each mobile energy storage device is adjusted in real time. By monitoring the real-time load changes of the connected users, the system dynamically adjusts the charging and discharging power of each mobile energy storage device according to the current load demand, ensuring the reasonable power distribution of each device and improving the coordination of charging and discharging.

[0048] S2. Determine the optimal charging and discharging strategy for each mobile energy storage device based on the current grid electricity price and electricity demand. This step specifically includes treating the charging and discharging operations of all energy storage devices as an element in the strategy space, constructing a benefit function and an operating cost function, and thereby determining the benefits of each device under the current electricity price conditions. By solving the benefit function, find the charging and discharging equilibrium strategy combination for each device under the current electricity price, and use the solution obtained to guide the charging and discharging operations of each device to achieve the goal of minimizing the overall cost of the system.

[0049] S3. Predict the user load change trend in the next time period. Based on historical data and current power consumption, predict the load change in the next time period to provide data support for the optimization of subsequent charging and discharging plans.

[0050] S4. Dynamically optimize the charging and discharging plans of each mobile energy storage device based on the prediction results. The specific method is to encode each round of charging and discharging decisions into genes, randomly generate a group of individuals as the initial population, and each individual represents a potential charging and discharging strategy. Define the fitness function to evaluate the pros and cons of each charging and discharging strategy, select the individuals with the highest fitness from the current population to enter the next generation, and perform crossover operations on the selected individuals to generate the next generation of individuals. The generated new individuals will replace the previous generation population to form a new population, and recalculate the fitness of each individual in the new generation population. After multiple rounds of iterations, the individual with the highest fitness is finally selected as the current optimal charging and discharging strategy.

[0051] S5. Monitor the actual operating status of each mobile energy storage device, and adjust the charge and discharge instructions to ensure uniform power distribution. This step monitors the operating data of each energy storage device in real time, including parameters such as charge and discharge power and battery status, and adjusts the charge and discharge instructions according to the actual situation to avoid imbalance in power distribution and ensure the stability and safety of the operation of each device.

[0052] The core of the present invention is to dynamically adjust the charging and discharging plans of each mobile energy storage device through an optimization algorithm based on load forecasts, grid electricity prices and electricity demand, so as to minimize the overall system cost. Through the real-time adjustment of step S1 and the optimization of the electricity price-sensitive strategy in step S2, each device can make independent decisions and balance the charging and discharging operations. In the dynamic optimization process of step S4, the optimal individuals are gradually selected from the population through an evolutionary algorithm to adapt to grid demand and load fluctuations, thereby achieving dynamic response in a multi-user environment. Step S5 ensures balance and efficiency among energy storage devices through a feedback mechanism.

[0053] By optimizing the charging and discharging strategy based on the benefit and cost function, the system can minimize the overall cost under the change of electricity price. By utilizing the dynamic optimization of the algorithm, the charging and discharging strategy is highly adaptable under the condition of load change and can respond to demand fluctuations in a timely manner. Through real-time monitoring and feedback adjustment, the uniformity of power distribution of each mobile energy storage device is ensured, and the stability and safety of the system are improved. This method can effectively coordinate the relationship between electricity price and electricity quantity, optimize the charging and discharging power distribution of each device, and achieve the effect of efficient energy utilization.

[0054] Step S1 includes:

[0055] Collect historical load data and current load real-time data, and make predictions and updates on the current load status. Assuming that the prior probability of load demand comes from historical data, the posterior probability of load demand is calculated in combination with real-time observation data. The specific calculation formula is:

[0056] ;

[0057] in, represents the assumed future load demand, Represents the observed real-time data, Indicates that real-time data is observed In the case of future load demand The posterior probability of It means that under the assumption that the future load demand is Under the premise of observing real-time data The probability of Indicates future load demand The prior probability of Represents the observed data The marginal probability of .

[0058] By combining real-time data with historical data, the posterior probability of future load demand is dynamically estimated to guide the charging and discharging scheduling of mobile energy storage equipment. This method can comprehensively consider historical load patterns and current load changes to achieve more accurate load forecasting. By calculating the posterior probability, the future load demand change trend can be better grasped, thereby improving the rationality and predictability of the charging and discharging strategy. The historical data can be organically combined with the real-time observation data to improve the accuracy of future load demand forecasting. The prediction model is dynamically updated using real-time data, so that the energy storage system can adapt to the fluctuation of load demand in time, avoid overcharging or discharging, and optimize the efficiency of the energy storage system. Accurate load forecasting can avoid unnecessary charging and discharging operations, reduce the frequency of charging and discharging, and thus extend the service life of energy storage equipment and reduce operating costs. This method effectively utilizes historical data and real-time data by calculating prior and posterior probabilities, making the operation of energy storage equipment more scientific and data-supported.

[0059] Step S2 also includes:

[0060] The specific calculation formula for building the benefits of each device is:

[0061] ;

[0062] in, Indicates The revenue function of an energy storage device is: Indicates the charging and discharging selection strategy of the device, Indicates the policy combination of other devices. Indicates income, Indicates cost.

[0063] The core of this implementation is to use the profit function To achieve the optimal charging and discharging strategy decision for each energy storage device. In the above formula, the construction of the benefit function and cost function enables each device to maximize its own benefits when making decisions. Specifically, the benefit Determined by the charging and discharging strategy of the device and the strategies of other devices, it represents the potential economic benefits of each energy storage device under the current electricity price and power demand. The cost function is only related to the strategy of the device itself, and usually includes the power consumption and equipment loss caused by the charging and discharging operation. By solving the benefit function of each energy storage device, the optimal charging and discharging strategy combination of all devices under the current electricity price and power demand conditions can be found, so as to achieve the goal of minimizing the overall cost of the system. This benefit calculation method allows each energy storage device to maximize its benefits under the conditions of changing electricity prices and demand by optimizing its charging and discharging strategy. By setting the cost function, the operating costs generated during the charging and discharging process can be reasonably controlled, thereby avoiding unnecessary charging and discharging operations and extending the life of the equipment. The structure of this method allows each device to autonomously adjust its strategy based on real-time electricity prices and load demands, and at the same time maintain the flexibility of the strategy under the coordination of multiple devices. This method achieves the overall efficiency improvement of the system under the conditions of electricity price and demand fluctuations through the trade-off between benefits and costs, so that the energy storage device can better respond to the grid load.

[0064] Step S3 includes:

[0065] Collect and standardize user load time series data, extract the characteristics of different frequency bands, decompose the load signal into low-frequency and high-frequency parts, use the low-frequency part as the basic data for long-term load forecasting, and combine the high-frequency part to make short-term fluctuation adjustments. The forecast results are used in the scheduling decision of the charging and discharging plan for the next time period. The specific public disclosure of the characteristics of different frequency bands is as follows:

[0066] ;

[0067] in, Represents the time signal, Indicates time, Indicates signal The size of the components at different scales and locations, Indicated in scale and location The basis functions on represents the scale parameter, Represents a positional parameter.

[0068] The working principle of this implementation is to separate the different frequency band information in the load time series through signal processing technology, so as to accurately extract and predict the changing characteristics of the load demand. Specifically, the load signal is decomposed by wavelet, and the low-frequency part is used as the basis for long-term trend analysis, while the high-frequency part reflects short-term fluctuation information. This separation can make the load forecast more accurate in capturing long-term and short-term demand characteristics, thereby effectively guiding the charging and discharging scheduling of mobile energy storage equipment. Multi-scale analysis is performed to extract different characteristic components of the load signal. , providing support for subsequent charging and discharging strategy adjustments. By decomposing the load signal into low-frequency and high-frequency parts, long-term trend prediction and short-term fluctuation adjustment can be performed respectively, thereby improving the accuracy of load prediction. By utilizing the multi-scale characteristics of wavelet transform, the characteristics of load signals can be analyzed at different time scales, and load demand changes in different time ranges can be effectively responded to. This method enables the charging and discharging strategy of energy storage equipment to not only meet long-term needs, but also respond to short-term load fluctuations in a timely manner, thereby improving the flexibility and reliability of scheduling. Through more accurate load forecasting and strategy adjustment, unnecessary operations in the charging and discharging process are reduced, the service life of energy storage equipment is extended, and the stability of the system is improved.

[0069] Step S4 includes:

[0070] The fitness function is positioned as:

[0071] ;

[0072] in, represents the value of the fitness function, represents the total time period, Indicates at time The discharge gain, Indicates at time The charging cost, Indicates time.

[0073] The core of this implementation is to use the fitness function To evaluate the effectiveness of each charging and discharging strategy. In the above formula, the fitness function quantifies the overall benefit of the current charging and discharging strategy by summing the difference between the discharge benefit and the charging cost over the entire time period. Specifically, the higher the value of the fitness function, the greater the net benefit of the current strategy in this period, so the strategy is more superior. Through this fitness function, the system can gradually select the individuals with the highest fitness in multiple rounds of iterations as the optimal charging and discharging strategy, thereby maximizing benefits and minimizing costs. Through the quantitative evaluation of the fitness function, the charging and discharging strategy with the best balance between benefits and costs can be efficiently selected. The fitness function integrates the goals of maximizing discharge benefits and minimizing charging costs into a unified optimization index, thereby ensuring that each round of charging and discharging decisions has the highest net benefit. The definition of the fitness function is not limited to a fixed time period, and the total time period TTT can be adjusted according to actual needs to adapt to different scheduling strategy requirements. By dynamically updating the charging and discharging strategy and using the fitness function as the optimization criterion, the operating efficiency and economic benefits of the entire energy storage system are improved.

[0074] Step S5 includes:

[0075] Define power error, error change rate, charge and discharge instructions and their fuzzy membership functions, build a fuzzy reasoning rule base, map the errors and error changes under different states to the control strategy, use fuzzy reasoning to process the real-time monitored power distribution data, obtain the output charge and discharge instructions, implement fuzzy control feedback, convert the fuzzy output into specific instructions and send them to the energy storage device to achieve uniform power distribution.

[0076] This implementation method uses fuzzy control technology to map different situations of power error and error change rate into corresponding charging and discharging strategies through fuzzy membership functions and inference rules. Real-time monitoring of power data and calculation of errors, fuzzy output is obtained through the fuzzy reasoning process, and then defuzzified into specific charging and discharging instructions, thereby achieving precise control of charging and discharging. This method can realize dynamic adjustment of power distribution in a complex and highly uncertain environment, ensure uniform power distribution of energy storage equipment, use fuzzy control to realize real-time adjustment of charging and discharging instructions, adapt to complex power fluctuations, and realize uniform power distribution between devices through fuzzy reasoning and feedback control, thereby improving the stability of system operation. The control method responds quickly to errors and change rates, enabling the system to quickly adjust charging and discharging operations when power demand fluctuates, thereby improving the response speed.

[0077] Step S1 also includes:

[0078] Obtain real-time load data when multiple users access;

[0079] Calculate the deviation between the current total load and the predicted load;

[0080] Adjust the charging and discharging power of each mobile energy storage device based on the deviation value;

[0081] Wherein, adjusting the charging and discharging power of each mobile energy storage device based on the deviation value includes:

[0082] Obtain the current state of charge SOC of each mobile energy storage device;

[0083] Calculate the ratio of the deviation value to the maximum deviation value R = deviation value / maximum deviation value, where R is the ratio, indicating the ratio of the deviation value to the maximum deviation value;

[0084] The charging and discharging power of each mobile energy storage device is adjusted based on the ratio R.

[0085] This implementation method dynamically adjusts the charging and discharging power of the energy storage device based on the real-time load data accessed by multiple users. By calculating the deviation between the total load and the predicted load and its ratio R relative to the maximum deviation, the charging and discharging operations of each energy storage device can be flexibly adjusted to ensure the stability of the overall load of the system and the rationality of scheduling. The charging and discharging adjustment is based on the load deviation ratio to achieve an accurate response to load fluctuations. The charging and discharging power of the energy storage device can be flexibly adjusted according to the real-time load data, improving the system's ability to adapt to a multi-user environment.

[0086] Adjusting the charging and discharging power of each mobile energy storage device based on the ratio R includes:

[0087] Determine the initial charge and discharge power of each mobile energy storage device;

[0088] Calculate the new charge and discharge power P of each device new =P initial × (1 + R × K), where P new is the new charge and discharge power, P initial is the initial charge and discharge power, K is the adjustment coefficient, and R is the ratio.

[0089] This implementation method dynamically adjusts the charge and discharge power of each device according to the ratio R and the adjustment coefficient K. By adjusting based on the initial power, it is possible to flexibly respond to load fluctuations and achieve refined control of the charge and discharge power of the energy storage device. By combining the ratio R and the adjustment coefficient K, dynamic adjustment of the charge and discharge power is achieved, which improves the flexibility of the system in responding to load changes, automatically adjusts power distribution under different load conditions, and ensures that the energy storage device can operate efficiently.

[0090] Cost in step S2 Including the charging cost of energy storage equipment, equipment depreciation cost and power transmission loss cost, this implementation method integrates the charging cost, equipment depreciation cost and power transmission loss cost into the cost function to optimize the charging and discharging strategy of energy storage equipment. The depreciation cost reflects the long-term operating cost of the equipment, while the transmission loss cost takes into account the actual loss in power transmission, making the charging and discharging strategy more economical and reasonable. The comprehensive consideration of multi-dimensional costs realizes the economic optimization of the operation of energy storage equipment, including the equipment depreciation cost, and ensures the long-term economic efficiency of the charging and discharging strategy.

[0091] Step S1: The load forecast data includes temperature, weather and seasonal load changes. This implementation optimizes the load forecast model by introducing factors such as temperature, weather and seasonal load changes to make the forecast more accurate. Temperature and weather factors directly affect electricity demand, while seasonal load changes reflect the characteristics of periodic loads, which helps to more accurately predict future loads. The accuracy of load forecasting is improved by combining multiple factors, and considering the impact of seasons and weather, so that energy storage equipment can better adapt to load demands in different environments.

[0092] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for controlling charging and discharging of a mobile energy storage device based on electricity price and electricity quantity, characterized in that: The method comprises: S1. Based on the load forecast data when multiple users access, the charging and discharging power distribution of each mobile energy storage device is adjusted in real time; S2. According to the current power grid electricity price and power demand, determine the optimal charging and discharging strategy for each mobile energy storage device, specifically: the charging and discharging operations of all energy storage devices are divided into various strategy spaces, and the benefits of each device are constructed by setting the benefit function and the operation cost function. Solve to find the balanced charging and discharging strategy combination of all devices under the current electricity price, and use the obtained solution to guide each device to perform charging and discharging operations to minimize the overall system cost; S3, predicting the user load change trend in the next time period; S4. Dynamically optimize the charging and discharging plans of each mobile energy storage device based on the prediction results, specifically: encode each round of decision-making of the charging and discharging plan into genes, randomly generate a group of individuals to form an initial population, each individual represents a potential charging and discharging strategy, define a fitness function to evaluate the pros and cons of each charging and discharging strategy, select the individual with the highest fitness from the current population to enter the next generation, perform crossover operations on the selected individuals to generate the next generation of individuals, and the generated new individuals replace the previous generation of population to form a new population, recalculate the fitness of each individual in the new generation of population, iterate multiple rounds, and finally select the individual with the highest fitness as the current optimal charging and discharging strategy; S5, monitor the actual operating status of each mobile energy storage device, and provide feedback to adjust the charging and discharging instructions to ensure uniform power distribution; The S1 further comprises: Obtain real-time load data when multiple users access; Calculate the deviation between the current total load and the predicted load; Adjust the charging and discharging power of each mobile energy storage device based on the deviation value; Wherein, adjusting the charging and discharging power of each mobile energy storage device based on the deviation value includes: Obtain the current state of charge SOC of each mobile energy storage device; Calculate the ratio of the deviation value to the maximum deviation value R = deviation value / maximum deviation value, where R is the ratio, indicating the ratio of the deviation value to the maximum deviation value; Adjust the charging and discharging power of each mobile energy storage device based on the ratio R; The method of adjusting the charging and discharging power of each mobile energy storage device based on the ratio R includes: Determine the initial charge and discharge power of each mobile energy storage device; Calculate the new charge and discharge power P of each device new =P initial × (1 + R × K), where P new is the new charge and discharge power, P initial is the initial charge and discharge power, K is the adjustment coefficient, and R is the ratio.

2. According to claim 1, a mobile energy storage device charging and discharging control method based on electricity price and electricity quantity is characterized in that: The S1 includes: Collect historical load data and current load real-time data, and make predictions and updates on the current load status. Assuming that the prior probability of load demand comes from historical data, the posterior probability of load demand is calculated in combination with real-time observation data. The specific calculation formula is: ； in, represents the assumed future load demand, Represents the observed real-time data, Indicates that real-time data is observed In the case of future load demand The posterior probability of It means that under the assumption that the future load demand is Under the premise of observing real-time data The probability of Indicates future load demand The prior probability of Represents the observed data The marginal probability of .

3. According to claim 1, a mobile energy storage device charging and discharging control method based on electricity price and electricity quantity is characterized in that: The S2 further includes: The specific calculation formula for building the benefits of each device is: ； in, Indicates The revenue function of an energy storage device is: Indicates the charging and discharging selection strategy of the device, Indicates the policy combination of other devices. Indicates income, Indicates cost.

4. According to claim 1, a mobile energy storage device charging and discharging control method based on electricity price and electricity quantity is characterized in that: The S3 includes: Collect and standardize user load time series data, extract the characteristics of different frequency bands, decompose the load signal into low-frequency and high-frequency parts, use the low-frequency part as the basic data for long-term load forecasting, and combine the high-frequency part to make short-term fluctuation adjustments. The forecast results are used in the scheduling decision of the charging and discharging plan for the next time period. The specific public disclosure of the characteristics of different frequency bands is as follows: ； in, Represents the time signal, Indicates time, Indicates signal The size of the components at different scales and locations, Indicated in scale and location The basis functions on represents the scale parameter, Represents a positional parameter.

5. A mobile energy storage device charging and discharging control method based on electricity price and electricity quantity according to claim 1, characterized in that: The S4 includes: The fitness function is positioned as: ； in, represents the value of the fitness function, represents the total time period, Indicates at time The discharge gain, Indicates at time The charging cost, Indicates time.

6. A mobile energy storage device charging and discharging control method based on electricity price and electricity quantity according to claim 1, characterized in that: The S5 includes: Define power error, error change rate, charge and discharge instructions and their fuzzy membership functions, build a fuzzy reasoning rule base, map the errors and error changes under different states to the control strategy, use fuzzy reasoning to process the real-time monitored power distribution data, obtain the output charge and discharge instructions, implement fuzzy control feedback, convert the fuzzy output into specific instructions and send them to the energy storage device to achieve uniform power distribution.

7. A mobile energy storage device charging and discharging control method based on electricity price and electricity quantity according to claim 3, characterized in that: The cost of S2 Including the charging cost of energy storage equipment, equipment depreciation cost and power transmission loss cost.

8. The method for controlling charging and discharging of a mobile energy storage device based on electricity price and electricity quantity according to claim 1, characterized in that: The S1 load forecast data includes temperature, weather and seasonal load changes.

Images