A Method, Device, Equipment, and Medium for Optimizing the Charging and Discharging Energy of Cloud Energy Storage on the User Side

Abstract

The present application discloses a method, device, equipment and medium for optimizing the charging and discharging of user-side cloud energy storage, which relates to the field of optimizing the operation of user-side energy storage. The method includes obtaining real-time meteorological data of sunlight and real-time meteorological data of wind speed; predicting photovoltaic output data and wind power output data respectively according to the real-time meteorological data of sunlight and the real-time meteorological data of wind speed; establishing a price-based demand response model and an alternative demand response model; establishing a user-side charging and discharging decision-making behavior model according to the price-based demand response model, the alternative demand response model, the photovoltaic output data and the wind power output data; solving the user-side charging and discharging decision-making behavior model to obtain an optimization scheme for the charging and discharging of user-side cloud energy storage; the optimization scheme for the charging and discharging of user-side cloud energy storage includes the actual power purchased by each user from the power grid, the heat network and the gas network. The present application improves the utilization efficiency of the energy storage system, balances the power grid load, and achieves a better energy storage scheduling effect.

Description

Technical Field

[0001] The present application relates to the field of optimal operation of user-side energy storage, and particularly to a method, device, equipment and medium for optimizing the charging and discharging of user-side cloud energy storage. Background Art

[0002] In the current energy structure transformation, new energy sources (such as wind energy and solar energy) have gradually become an important part of the power system due to their advantages of cleanliness, renewability, etc. However, new energy has obvious uncertainties and fluctuations. Especially under different weather, time periods and regional conditions, the power generation output is difficult to predict, which brings challenges to the balanced dispatching and operation stability of the power system. At the same time, with the gradual opening of the power market and the development of smart grid technology, the user-side demand response (DR) technology has emerged, enabling users to participate in the regulation of the power system by adjusting their electricity consumption behaviors, so as to improve electricity consumption efficiency and reduce costs. Therefore, there is an urgent need for a method for optimizing the charging and discharging of user-side cloud energy storage that can improve the utilization efficiency of the energy storage system, balance the grid load, and achieve a better energy storage dispatching effect. Summary of the Invention

[0003] The purpose of the present application is to provide a method, device, equipment and medium for optimizing the charging and discharging of user-side cloud energy storage, which realizes the maximization of energy efficiency and the minimization of operating costs, improves the utilization efficiency of the energy storage system, balances the grid load, and achieves a better energy storage dispatching effect.

[0004] To achieve the above purpose, the present application provides the following solutions.

[0005] In the first aspect, the present application provides a method for optimizing the charging and discharging of user-side cloud energy storage, including the following steps.

[0006] Obtain real-time meteorological data of sunlight and real-time meteorological data of wind speed.

[0007] Respectively predict photovoltaic output data and wind power output data according to the real-time meteorological data of sunlight and the real-time meteorological data of wind speed.

[0008] Establish a price-based demand response model and a substitution-based demand response model.

[0009] Establish a user-side charging and discharging decision behavior model according to the price-based demand response model, the substitution-based demand response model, the photovoltaic output data and the wind power output data; the user-side charging and discharging decision behavior model includes an objective function and constraint conditions; the objective function is a function with the minimum equal annual value cost of the user as the objective.

[0010] Solve the user-side energy storage charging and discharging decision-making behavior model to obtain an optimized user-side cloud energy storage charging and discharging plan; the optimized user-side cloud energy storage charging and discharging plan includes the actual power purchased by each user from the power grid, the heat grid, and the gas grid.

[0011] In a second aspect, the present application provides a user-side cloud energy storage charging and discharging optimization device, including the following modules.

[0012] A meteorological data acquisition module, configured to: acquire real-time illumination meteorological data and real-time wind speed meteorological data.

[0013] An output data prediction module, configured to: predict photovoltaic output data and wind power output data respectively according to the real-time illumination meteorological data and the real-time wind speed meteorological data.

[0014] A demand response model establishment module, configured to: establish a price-based demand response model and an alternative demand response model.

[0015] A user-side energy storage charging and discharging decision-making behavior model establishment module, configured to: establish a user-side energy storage charging and discharging decision-making behavior model according to the price-based demand response model, the alternative demand response model, the photovoltaic output data, and the wind power output data; the user-side energy storage charging and discharging decision-making behavior model includes an objective function and constraint conditions; the objective function is a function with the minimum equal annual value cost of the user as the objective.

[0016] A user-side cloud energy storage charging and discharging optimization module, configured to: solve the user-side energy storage charging and discharging decision-making behavior model to obtain an optimized user-side cloud energy storage charging and discharging plan; the optimized user-side cloud energy storage charging and discharging plan includes the actual power purchased by each user from the power grid, the heat grid, and the gas grid.

[0017] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the above-mentioned user-side cloud energy storage charging and discharging optimization method.

[0018] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned user-side cloud energy storage charging and discharging optimization method is implemented.

[0019] According to the specific embodiments provided by the present application, the following technical effects are disclosed in the present application:

[0020] The present application provides a method, device, equipment and medium for optimizing the charging and discharging of user-side cloud energy storage. By using real-time meteorological data of sunlight and wind speed, the photovoltaic output data and wind power output data are predicted. A price-based demand response model and an alternative demand response model are established. According to the price-based demand response model, the alternative demand response model, the photovoltaic output data and the wind power output data, a decision-making behavior model for user-side charging and discharging is established. Considering the uncertainty of new energy output and demand response, the charging and discharging strategies of the user-side energy storage system are optimized, achieving maximum energy efficiency and minimum operating cost. By fully considering the volatility of new energy generation and the flexibility of user-side load demand response during the energy storage optimization process, the utilization efficiency of the energy storage system is improved, the grid load is balanced, and a better energy storage scheduling effect is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1 It is an application environment diagram of a method for optimizing the charging and discharging of user-side cloud energy storage in an embodiment of the present application;

[0023] Figure 2 It is a flowchart of a method for optimizing the charging and discharging of user-side cloud energy storage provided in an embodiment of the present application;

[0024] Figure 3 It is a schematic diagram of the specific process of a method for optimizing the charging and discharging of user-side cloud energy storage provided in an embodiment of the present application;

[0025] Figure 4 It is a schematic diagram of the structure of a new energy output prediction model provided in an embodiment of the present application;

[0026] Figure 5 It is a neural network block diagram of a long short-term memory network provided in an embodiment of the present application;

[0027] Figure 6 It is a schematic diagram of the functional modules of a device for optimizing the charging and discharging of user-side cloud energy storage provided in another embodiment of the present application;

[0028] Figure 7 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts belong to the scope of protection of the present application.

[0030] Cloud energy storage technology has gradually become an important solution. Cloud energy storage can not only centrally manage dispersed energy storage resources, but also improve the overall efficiency of the energy storage system through intelligent scheduling and optimization algorithms. The research framework and basic model of cloud energy storage in the power system introduce the research framework of cloud energy storage from three perspectives: operation, object, and market, establish a two-agent basic mathematical model of cloud energy storage, and give a decision-making method on the side of cloud energy storage providers for the uncertainty of user charging and discharging behaviors. The robust optimal configuration model of cloud energy storage based on cooperative game takes into account the uncertainty of renewable energy. The optimized design of the power system based on the smart grid proposes a P2P sharing mode for selling the right to use redundant energy storage capacity while meeting the electricity load for shared energy storage on the user side, so as to optimize the benefits of energy storage providers, consumers, and platforms. However, the utilization efficiency of the above-mentioned energy storage system is relatively low. Traditional cloud energy storage scheduling optimization methods usually only rely on fixed load models, ignoring the volatility and uncertainty of new energy sources (such as wind energy, solar energy, etc.) in actual output. In addition, demand response strategies are not fully integrated with the energy storage system in traditional methods, resulting in the inability to flexibly respond to electricity price fluctuations and dynamic changes in user loads. To address the above problems, the present application proposes an optimization method for charging and discharging of cloud energy storage on the user side.

[0031] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0032] The optimization method for charging and discharging of cloud energy storage on the user side provided by the embodiments of the present application can be applied to, for example Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set separately, integrated on the server 104, placed on the cloud or other servers. The terminal 102 can send the real-time illumination meteorological data and the real-time wind speed meteorological data to the server 104. After receiving the real-time illumination meteorological data and the real-time wind speed meteorological data, for the real-time illumination meteorological data and the real-time wind speed meteorological data, the server 104 respectively predicts the photovoltaic power output data and the wind power output data according to the real-time illumination meteorological data and the real-time wind speed meteorological data, establishes a price-based demand response model and an alternative demand response model, and according to the price-based demand response model, the alternative demand response model, the photovoltaic power output data and the wind power output data, establishes a user-side energy storage charging and discharging decision-making behavior model, solves the user-side energy storage charging and discharging decision-making behavior model, and obtains an optimized solution for the user-side cloud energy storage charging and discharging. The server 104 can feedback the obtained optimized solution for the user-side cloud energy storage charging and discharging to the terminal 102. In addition, in some embodiments, the user-side cloud energy storage charging and discharging optimization method can also be implemented separately by the server 104 or the terminal 102. For example, the terminal 102 can directly perform energy storage charging and discharging optimization processing on the real-time illumination meteorological data and the real-time wind speed meteorological data, or the server 104 can obtain the real-time illumination meteorological data and the real-time wind speed meteorological data from the data storage system and perform energy storage charging and discharging optimization processing on the real-time illumination meteorological data and the real-time wind speed meteorological data.

[0033] Among them, the terminal 102 can be, but is not limited to, various desktop computers and laptop computers. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers, and can also be a cloud server.

[0034] In an exemplary embodiment, such as Figure 2 and Figure 3 shown, a user-side cloud energy storage charging and discharging optimization method is provided. This method is executed by a computer device, and can be specifically executed separately by a computer device such as a terminal or a server, or jointly executed by a terminal and a server. In the embodiments of the present application, taking this method applied to Figure 1 the server 104 in

[0035] Step 201: Obtain the real-time illumination meteorological data and the real-time wind speed meteorological data.

[0036] Step 202: Respectively predict the photovoltaic power output data and the wind power output data according to the real-time illumination meteorological data and the real-time wind speed meteorological data.

[0037] Step 203: Establish a price-based demand response model and an alternative demand response model.

[0038] Step 204: Based on the price-based demand response model, the alternative demand response model, the photovoltaic output data, and the wind power output data, establish a user-side energy storage charging and discharging decision-making behavior model; the user-side energy storage charging and discharging decision-making behavior model includes an objective function and constraint conditions; the objective function is a function with the minimum equivalent annual cost of the user as the goal.

[0039] Step 205: Solve the user-side energy storage charging and discharging decision-making behavior model to obtain an optimized user-side cloud energy storage charging and discharging plan; the optimized user-side cloud energy storage charging and discharging plan includes the actual power purchased by each user from the power grid, the heat grid, and the gas grid.

[0040] Implementing the above Steps 201 to 205 can, by evaluating the volatility and uncertainty of new energy in real time, ensure that the energy storage system can fully absorb new energy; at the same time, introducing a demand response mechanism into energy storage scheduling can flexibly adjust the energy storage charging and discharging strategy according to the real-time changes in electricity prices and user loads. Ultimately, the economy and operation efficiency of the user-side cloud energy storage are significantly improved.

[0041] In another exemplary embodiment of this application, the above Step 202 may include the following Steps 301 to 302.

[0042] Step 301: Preprocess the real-time meteorological data of sunlight and the real-time meteorological data of wind speed to obtain preprocessed sunlight data and preprocessed wind data.

[0043] Step 302: Input the preprocessed sunlight data and the preprocessed wind data into the trained new energy output prediction model respectively, and predict the photovoltaic output data and the wind power output data.

[0044] By introducing a new energy output prediction model, the volatility and uncertainty of new energy can be evaluated in real time, ensuring that the energy storage system can fully absorb new energy.

[0045] The structure of the new energy output prediction model is as Figure 4As shown in the figure, in this embodiment, the new energy output prediction model is named CNN-SimLSTM. The trained new energy output prediction model includes an initial feature extraction module, a temporal feature extraction module, and an output prediction module that are connected in sequence. The initial feature extraction module is used to extract features from the preprocessed optical data and preprocessed wind data respectively to obtain illumination features and wind speed features; the temporal feature extraction module is used to extract temporal features from the illumination features and wind speed features respectively to obtain an illumination final temporal feature vector and a wind speed final temporal feature vector; the output prediction module is used to predict photovoltaic output data and wind power output data respectively based on the illumination final temporal feature vector and the wind speed final temporal feature vector.

[0046] First, the sensor of the user-side energy storage device and the monitoring system obtain real-time illumination meteorological data and real-time wind speed meteorological data. The real-time illumination meteorological data includes various meteorological factors such as illumination intensity and temperature and humidity, and the real-time wind speed meteorological data includes various meteorological factors such as wind speed and temperature and humidity, which are the input data of the new energy output prediction model. Then, the input data is preprocessed. The preprocessing in step 301 includes meteorological factor analysis, data normalization, and outlier removal, etc.; then, a convolutional neural network is used to extract high-dimensional features of the input data; next, a long short-term memory network optimized based on SimAM is used to extract temporal features through historical typical day distributed energy output data; finally, combining meteorological and temporal features, a fully connected layer is used to predict the energy output probability distribution of the distributed energy storage and perform sampling.

[0047] Perform normalization and outlier removal operations on the real-time illumination meteorological data and real-time wind speed meteorological data. Secondly, perform correlation analysis and feature screening on the meteorological factors affecting photovoltaic output. Suppose there are moments of a total of types of meteorological factor data, and the th moment of the th type of meteorological factor data is , and the photovoltaic output data is . Calculate the direct correlation coefficient between the th type of meteorological factor and the photovoltaic output, which is expressed in the form shown in Equation (1).

[0048] (1).

[0049] (2).

[0050] In the formula, , represents the mean value of the meteorological factor data; , represents the mean value of the photovoltaic output data; is the partial regression coefficient.

[0051] The category of meteorological factors passes through the category of meteorological factors, and the indirect correlation coefficient with the photovoltaic output is as shown in the following formula.

[0052] (3).

[0053] (4).

[0054] In the formula, is the correlation coefficient between the category and the category of numerical meteorological data. The correlation coefficient between the category of meteorological factors and the photovoltaic output is as shown in the following formula.

[0055] (5).

[0056] Perform a correlation analysis using the photovoltaic output and meteorological data of a certain place, and select the factors with a correlation coefficient greater than 0.2. Finally, for photovoltaic, the selected meteorological factors from the real-time meteorological data of light include light radiation intensity, temperature, humidity, etc.; for wind power, the selected factors from the real-time meteorological data of wind speed include wind speed, temperature, humidity, etc.). Suppose a total of factors are selected, and the vector composed of these meteorological factor data is the meteorological feature vector at the

[0057] The initial feature extraction module uses a convolutional neural network to perform deep feature extraction on meteorological data. Specifically, a one-dimensional CNN network model is adopted, which consists of a convolutional layer, a batch normalization layer, an activation layer, and a pooling layer. Among them, the convolutional layer is the main operation unit, and it completes the convolution operation through the filter and stride structure inside the module. The operation process of the convolutional layer is as shown in formula (6).

[0058] (6).

[0059] In the formula, is the convolutional kernel size; is the th weight of the convolutional kernel; is the bias term. Then, batch normalization (BN) is used to normalize the output data of the convolutional layer, as shown in the following formula.

[0060] (7).

[0061] In the formula, is the output data of the convolutional layer; is the mean value of , is the variance of ; and are the scaling factor and the offset factor respectively.

[0062] After that, the data is activated through the ReLU activation function, which is defined as , where represents the output of the ReLU activation function. When the data passes through the pooling layer, spatial merging is performed through the pooling window, reducing the feature size while maintaining the feature information. The pooling layer in the convolutional neural network uses the max-pooling layer, which is defined as , where, is the output of the pooling layer, is the set of all data within the pooling region.

[0063] The time series feature extraction module uses the long short-term memory network (LSTM) based on SimAM optimization for time series feature extraction, and the LSTM processes time series data. However, when the traditional LSTM module processes the input data, it cannot adaptively adjust its weights according to the importance of the features, resulting in the dispersion of information and the loss of important information. The time series feature extraction module is named the SimLSTM module. The SimLSTM module finds the key nodes by measuring the linear separability of neurons without adding additional parameters. The neuron energy is the key parameter for this mechanism to distinguish the importance of different neurons, and the calculation method is shown in the following formula.

[0064] (8).

[0065] Where, and represent the target neuron and other neurons in the same channel respectively, is the index of the neurons within the channel, and are the linear transformations of the corresponding neurons. The lower the energy of the target neuron, the greater the linear separability between the neuron and other neurons. Therefore, the minimum value of formula (8) needs to be solved. To simplify the optimization calculation process, for , binary labeling is adopted, and a regularization term is added to the objective function. The final energy expression is shown in the following formula.

[0066] (9).

[0067] To reduce the computational burden of different neurons in different channels, in the above formula and It is obtained in the form of an analytical solution as shown in the following formula.

[0068] (10).

[0069] (11).

[0070] In the formula, and are the mean and variance of all neurons other than the target neuron q in a single channel. Since the neurons in the same channel are uniformly distributed, the calculation process of the mean and variance of the target neuron q can be simplified, that is, the statistical parameters are calculated based on all neurons in the channel.

[0071] (11).

[0072] The minimum energy function of the final target neuron q can be calculated by formula (12).

[0073] (12).

[0074] The smaller the minimum energy function value of the neuron, the more obvious its contained features. Therefore it can represent the importance of each neuron. At the same time, the weighted calculation of this attention mechanism is completed based on the importance of each neuron, and the process is as shown in the following formula.

[0075] (13).

[0076] In the formula, is the matrix representation of the minimum energy function values of all neurons, and the sigmoid activation function is used to prevent excessive values in the parameter matrix.

[0077] After obtaining the weighted feature , it is input into the forget gate , memory gate and cell state of the LSTM unit (LSTM Cell), and finally the output gate is obtained. The neural network block diagram of the LSTM unit is as shown in Figure 5 .

[0078] Suppose a total of L LSTM units are used to extract historical feature vectors. When the prediction time is time, the input of the th LSTM unit is the meteorological feature vector at the and PV output data The splicing is as shown in the following formula.

[0079] (14).

[0080] In the formula, represents the splicing operation.

[0081] Traverse Calculate the input gate of the th LSTM cell, forget gate, output gate and each unit state . Define , , then the calculation formula is as shown in the following formula.

[0082] (15).

[0083] (16).

[0084] (17).

[0085] (18).

[0086] (19).

[0087] In the formula, , , , are the weight matrices of the input gate, forget gate, output gate, and learnable unit state respectively; , , , are the bias constants of the above four respectively, is the sigmoid activation function. Take the unit state of the th long short-term memory network unit as the time series feature vector . Finally, send the output of the SimLSTM module to the output prediction module to obtain the new energy output sampling value at the th moment. The output prediction module is a fully connected layer, specifically represented in the form shown in the following formula.

[0088] (20).

[0089] In the formula, is the weight of the fully connected layer.

[0090] There are differences in the sensitivities of different types of loads to the same electricity price signal. Price-based demand response electrical loads are divided into curtailable loads (CL) and shiftable loads (SL). The following models these two types of loads separately. Then the price-based demand response model includes a curtailable load model and a shiftable load model.

[0091] CL selects whether to curtail its own load by comparing the electricity price changes in this period before and after DR. The price-demand elasticity matrix is used to describe the DR characteristics. The curtailable load model is expressed as shown in the following formula.

[0092] (21).

[0093] (22).

[0094] Among them, represents the elasticity coefficient of the curtailable load at time to the electricity price at time which is the element in the th row and th column of the price-demand elasticity matrix ; is the change in the curtailable load at time after demand response; is the change in the electricity price at time after demand response; is the initial electricity price at time ; is the initial curtailable load at time ; is the price-demand elasticity matrix of the curtailable load; is the electricity price at time

[0095] A shiftable load refers to a load whose users can flexibly adjust their working hours according to their own demand response to the electricity price. Taking the time-of-use electricity price of peak, valley, and flat periods as a signal, it can guide users to shift the load during peak periods to valley and flat periods. Similarly, the price-demand elasticity matrix is used to describe the DR characteristics. The shiftable load model is expressed as shown in the following formula.

[0096] (23).

[0097] In the formula, is the change in the shiftable load at time after demand response, is the initial shiftable load at time ; is the price-demand elasticity matrix of SL.

[0098] For a certain type of heat load that can be directly supplied by thermal energy or electrical energy, electrical energy can be consumed during low electricity price periods, and thermal energy can be directly consumed during high electricity price periods to meet its own needs, thus realizing the mutual substitution of electrical energy and thermal energy. The replaceable load (RL) model, that is, the alternative demand response model, is expressed as shown in the following formula.

[0099] (24).

[0100] (25).

[0101] Among them, and are the replaceable electrical load quantity and the corresponding replaced thermal load quantity respectively; is the electrical-thermal substitution coefficient; and are the unit calorific values of electrical energy and thermal energy respectively; and are the energy utilization rates of electrical energy and thermal energy respectively. In formula (24), " " indicates that the reduction of the replaceable electrical load corresponds to the increase of the replaced thermal load. For this type of load, the maximum replaceable load quantity constraint needs to be considered, as shown in the following formula.

[0102] (26).

[0103] In the formula, is the replaceable electrical load at time are the minimum and maximum substitution quantities of the replaceable electrical load respectively; is the replaceable thermal load at time are the minimum and maximum substitution quantities of the replaceable thermal load respectively.

[0104] For electrical load users, their new energy output mainly includes a part of the self-built photovoltaic (PV) and the shared regional wind turbine (WT) output; for thermal load users, their new energy output is the WT converted thermal output obtained through sharing; for gas load users, their new energy output is the WT converted gas output obtained through sharing. Therefore, in the rd season and the th moment (collectively referred to as moment), the electrical, thermal, and gas new energy outputs of user are as shown in the following formula.

[0105] (27).

[0106] (28).

[0107] (29).

[0108] In the formula, are respectively the new - energy output of electricity, heat, and gas supplied to users at time ; are respectively the self - built PV output and the allocated WT output of users at time ; are respectively the shunt coefficients of WT and P2G; are respectively the efficiencies of P2G and gas boiler (GB).

[0109] Define the operations 、 as shown in the following formula.

[0110] (30).

[0111] When there is no energy - storage device, users purchase power from the electricity, heat, and gas grids respectively. When the new - energy output is excessive, users send the excessive power back to the electricity, heat, and gas grids respectively. The power purchased and sent back by users is shown in the following formula respectively.

[0112] (31).

[0113] (32).

[0114] In the formula, are respectively the electricity, heat, and gas power purchased by users from the energy network due to insufficient new - energy output at time , respectively represent electricity, heat, and gas; , are respectively the electricity, heat, and gas power sent back by users to the energy network due to excessive new - energy output at time ; , are respectively the electricity, heat, and gas loads of users at time after considering DR .

[0115] Considering the rational charging and discharging behavior of cloud energy storage for a single - electricity - load user , set the critical charging electricity price and the critical discharging electricity price . When the electricity price is lower than the critical charging electricity price or the new energy output is excessive, the user controls the cloud energy storage to charge; when the electricity price is higher than the critical discharging electricity price and the new energy output is lower than the load demand, the user controls the cloud energy storage to discharge; when the electricity price is higher than the critical charging electricity price and lower than the critical discharging electricity price, the cloud energy storage does not discharge. In the latter two cases, only when the new energy power is excessive, the user controls the cloud energy storage to charge. Therefore, the charging and discharging behavior of the user during this period is expressed by the following formula.

[0116] When ,

[0117] (33).

[0118] In the formula, are respectively the cloud energy storage charging and discharging power demands of the user at time ; is the power of the user renting the cloud electricity storage service from the cloud energy storage provider; is the remaining capacity of the cloud electricity storage rented by the user at the end of time ; is the maximum limit of the cloud electricity storage capacity purchased by the user ; is the charging efficiency of the cloud electricity storage purchased by the user ; represents the time interval. In this application, time-of-use electricity price is adopted, and is taken as 1h.

[0119] When , the cloud energy storage charging and discharging power demands are expressed by the following formula.

[0120] (34).

[0121] When , the cloud energy storage charging and discharging power demands are expressed by the following formula.

[0122] (35).

[0123] In the formula, represents the electric power fed back to the energy network by the user at time due to the excess of new energy output, is the discharging efficiency of the cloud electricity storage purchased by the user , are respectively the electric power purchased by the user at time from the energy network due to the shortage of new energy output.

[0124] Considering the specific conditions of the thermal market and the natural gas market, the prices of heat and gas are fixed. Therefore, when the new energy output of a single heat user is greater than the heat demand, the heat storage tank is controlled to store heat; when the new energy output is insufficient to meet the heat demand of the load, the heat storage tank is controlled to release heat. At time the charging and discharging behavior of the user

[0125] is expressed by the following formula.

[0126] In the formula, are respectively at time the charging and discharging power demands of the cloud energy storage of the user is the power for the user to purchase cloud heat storage service from the cloud energy storage provider; is at the end of time the remaining capacity of the cloud heat storage purchased by the user is the maximum limit of the cloud heat storage capacity purchased by the user ; are respectively the charging and discharging efficiencies of the cloud energy storage purchased by the user ; represents at time the heat power fed back to the energy network by the user due to the excess new energy output; are respectively at time

[0127] the heat power purchased by the user from the energy network due to insufficient new energy output. At time the charging and discharging behavior of the user

[0128] is expressed by the following formula.

[0129] In the formula, are respectively at time the charging and discharging gas power demands of the cloud energy storage of the user is the power for the user to purchase cloud gas storage service from the cloud energy storage provider; is the maximum limit of the cloud gas storage capacity purchased by the user is at the end of time the remaining capacity of the cloud gas storage purchased by the user respectively for the user charging and discharging efficiency of the cloud energy storage purchased denote at the moment, the user gas power sent back to the energy network due to over - generation of new energy is at the moment, the user gas power purchased from the energy network due to insufficient generation of new energy

[0130] The purpose of introducing energy storage is to reduce the curtailment of wind and solar power, better absorb new energy, and thus reduce costs. Therefore, the user gives priority to using new energy for charging. For a single user the new - energy charging part in the charging, heat - charging, and gas - charging power is expressed by the following formula

[0131] (38).

[0132] In the formula respectively are at the moment, the user electric, heat, and gas new - energy charging power

[0133] Combined with the above description of the user's energy - using behavior, the actual power purchased or sent back by a single user from the electric, heat, and gas networks is

[0134] (39).

[0135] In the formula respectively are at the moment, the user actual power purchased from the electric, heat, and gas networks

[0136] Cloud - energy - storage users lease the right to use a certain power and capacity of cloud energy storage from cloud - energy - storage providers according to their own load requirements. Therefore, the total cost of a single user includes the investment cost of leasing cloud - energy - storage services from cloud - energy - storage providers and the operating cost of purchasing energy from the electric, heat, and gas networks during actual operation when new - energy generation and cloud - energy - storage capacity are insufficient

[0137] Since cloud - energy - storage providers centrally manage physical energy storage, users save the fixed cost of maintaining physical energy storage. Taking the minimum equivalent annual cost of the user as the goal, the objective function is constructed as shown in the following formula

[0138] (40).

[0139] (41).

[0140] (42).

[0141] (43).

[0142] Wherein, is the objective function, is the equal annual value cost of the user, is the equal annual value coefficient; is the energy storage life cycle; is the annual interest rate; is the user 's investment cost; The energy storage equipment includes lithium batteries, thermal storage tanks, gas storage tanks, etc. are the unit power service fees of the lithium battery, thermal storage tank, and gas storage tank respectively; are the unit capacity service fees of the lithium battery, thermal storage tank, and gas storage tank respectively; is the user 's operating cost; is the number of days in a typical day for each season; respectively represent the prices of the user purchasing unit power energy from the electricity, heat, and gas grids, with the units being yuan / (kW·h), yuan / GJ, yuan / m 3 ; are the prices of the user selling back unit power energy to the electricity, heat, and gas grids respectively, with the units being yuan / (kW·h), yuan / GJ, yuan / m 3 ; are the calorific value coefficients of the heat grid and gas grid converted to unit power respectively, with the units being kW / GJ, kW / m 3 ; respectively are the actual power purchased by the user from the electricity, heat, and gas grids at the moment, respectively represent electricity, heat, and gas.

[0143] The constraint conditions of the user-side charging and discharging energy decision-making behavior model include the maximum replaceable load amount constraint; The maximum replaceable load amount constraint is shown in Equation (26). Taking the minimum equal annual value cost of the user as the objective function, the user-side charging and discharging energy decision-making behavior model is solved using the YALMIP toolbox in MATLAB to call the commercial solver CPLEX.

[0144] Taking a large industrial park in the southern region as the research object, the example selects the load data of 50 typical days in the region. The scheduling time for each typical day is 24 hours, and the scheduling interval time in this application is taken as 1 hour. The relevant parameters in the region are shown in Table 1. The peak, flat, and valley electricity prices under the time-of-use electricity price policy in this area are selected, and their prices and time periods are divided as shown in Table 2. Through investigation, it is obtained that the region uses heat metering and charges by GJ. The heat price for residential heating metering is 46 yuan / GJ, and the calorific value coefficient is taken as 0.0036 kW / GJ; the unified price of the natural gas network is 3.853 yuan / m3, and the calorific value coefficient is taken as 9.7 kW / m3. The specific conversion method is shown in Table 3.

[0145] Table 1 Relevant parameters in the region

[0146]

[0147] Table 2 Time-of-use electricity price and time period division

[0148]

[0149] Table 3 Heat-gas power conversion

[0150]

[0151] To verify the effectiveness of the user-side cloud energy storage charging and discharging optimization method proposed in this application, four different application scenarios are designed in the experimental part of this application, and the cost performance of users under the conditions of using cloud energy storage, considering new energy output prediction, and combining demand response is investigated respectively. The specific descriptions of these four scenarios are as follows: Scenario 1: Users only use cloud energy storage; Scenario 2: Users use cloud energy storage and consider the new energy output prediction method; Scenario 3: Users use cloud energy storage and consider demand response; Scenario 4: Users use cloud energy storage and consider the new energy output prediction method and demand response. The comparison of the equivalent annual value cost of users and the renewable energy consumption rate under different scenarios are shown in Table 4.

[0152] Table 4 Comparison of experimental results under different scenarios

[0153]

[0154] It can be seen from Table 4 that although Scenario 2 has a better performance in terms of new energy consumption rate, it is slightly inferior to Scenario 4 in terms of cost control. Although the demand response strategy in Scenario 3 can optimize power scheduling, without the support of new energy output prediction, its economic benefits and consumption rate are still inferior to Scenario 4. Scenario 4 shows the best results in terms of the equivalent annual value cost of users and the renewable energy consumption rate, verifying that the user-side cloud energy storage charging and discharging optimization method proposed in this application can maximize economic benefits and renewable energy utilization efficiency.

[0155] The present application also provides an application scenario, which applies the above-mentioned user-side cloud energy storage charging and discharging optimization method. Specifically: The user-side cloud energy storage charging and discharging optimization method provided in this embodiment can be applied to the user-side cloud energy storage charging and discharging optimization scenario. The user-side cloud energy storage charging and discharging optimization scenario includes a data collection link and an energy storage charging and discharging optimization link; the real-time illumination meteorological data and the real-time wind speed meteorological data enter the energy storage charging and discharging optimization link from the data collection link, and a corresponding user-side cloud energy storage charging and discharging optimization scheme is obtained. The user-side cloud energy storage charging and discharging optimization method provided in this embodiment belongs to the energy storage charging and discharging optimization link. Specifically, in the process of the energy storage charging and discharging optimization link for the real-time illumination meteorological data and the real-time wind speed meteorological data, the photovoltaic output data and the wind power output data can be predicted respectively according to the real-time illumination meteorological data and the real-time wind speed meteorological data, a price-based demand response model and a substitution-based demand response model are established, and a user-side charging and discharging decision-making behavior model is established according to the price-based demand response model, the substitution-based demand response model, the photovoltaic output data and the wind power output data, and the user-side charging and discharging decision-making behavior model is solved to obtain the user-side cloud energy storage charging and discharging optimization scheme.

[0156] Based on the same inventive concept, the embodiment of the present application also provides a user-side cloud energy storage charging and discharging optimization device for implementing the above-mentioned user-side cloud energy storage charging and discharging optimization method. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the user-side cloud energy storage charging and discharging optimization device provided below can refer to the limitations on the user-side cloud energy storage charging and discharging optimization method in the above text, and will not be repeated here.

[0157] In an exemplary embodiment, as Figure 6 shown, a user-side cloud energy storage charging and discharging optimization device is provided, which includes the following modules.

[0158] A meteorological data acquisition module T1, configured to: acquire real-time illumination meteorological data and real-time wind speed meteorological data.

[0159] An output data prediction module T2, configured to: predict photovoltaic output data and wind power output data respectively according to the real-time illumination meteorological data and the real-time wind speed meteorological data.

[0160] A demand response model establishment module T3, configured to: establish a price-based demand response model and a substitution-based demand response model.

[0161] The user-side charging and discharging energy decision-making behavior model establishment module T4 is used for: establishing a user-side charging and discharging energy decision-making behavior model according to the price-based demand response model, the alternative demand response model, the photovoltaic output data, and the wind power output data; the user-side charging and discharging energy decision-making behavior model includes an objective function and constraint conditions; the objective function is a function aiming at minimizing the equivalent annual cost of the user.

[0162] The user-side cloud energy storage charging and discharging energy optimization module T5 is used for: solving the user-side charging and discharging energy decision-making behavior model to obtain a user-side cloud energy storage charging and discharging energy optimization scheme; the user-side cloud energy storage charging and discharging energy optimization scheme includes the actual power purchased by each user from the power grid, the heat grid, and the gas grid.

[0163] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structure diagram can be as Figure 7 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store user-side cloud energy storage charging and discharging energy optimization data. The input / output interface of the computer device is used for the processor to exchange information with external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a user-side cloud energy storage charging and discharging energy optimization method.

[0164] Those skilled in the art can understand that Figure 7 the structure shown in

[0165] merely shows the block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0166] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which when executed by a processor implements the steps in the above method embodiments.

[0167] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0168] Those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0169] The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., and are not limited thereto.

[0170] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0171] In this text, specific examples are used to elaborate on the principles and implementation manners of the present application. The descriptions of the above embodiments are only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation on the present application.

Claims

1. A method for optimizing the charging and discharging of user-side cloud energy storage, characterized in that, The user-side cloud energy storage charging and discharging optimization method includes: Obtain real-time meteorological data of sunlight and real-time meteorological data of wind speed; Predict photovoltaic output data and wind power output data respectively according to the real-time meteorological data of sunlight and the real-time meteorological data of wind speed; Establish a price-based demand response model and an alternative demand response model; According to the price-based demand response model, the alternative demand response model, the photovoltaic output data and the wind power output data, establish a user-side charging and discharging decision-making behavior model; the user-side charging and discharging decision-making behavior model includes an objective function and constraint conditions; the objective function is a function with the minimum equal annual value cost of the user as the goal; the objective function is expressed as follows: ； ； ； ； In the formula, is the objective function, is the user's equivalent annual cost, is the equivalent annual value coefficient; is the energy storage life cycle; is the annual interest rate; is the user's investment cost; are the unit power service fees of the lithium battery, thermal storage tank, and gas storage tank respectively; are the unit capacity service fees of the lithium battery, thermal storage tank, and gas storage tank respectively; is the user's operation cost; is the number of days in a typical day of each season; respectively represent the prices at which the user purchases unit power energy from the electricity, heat, and gas grids; are the prices at which the user sells back unit power energy to the electricity, heat, and gas grids respectively; are the calorific value coefficients of the heat grid and gas grid converted to unit power respectively; are respectively the actual power purchased by the user from the electricity, heat, and gas grids at time respectively represent electricity, heat, and gas; is the power of the cloud storage electricity service leased by the user from the cloud energy storage provider; is the maximum limit of the cloud storage electricity capacity purchased by the user ; is the power of the cloud storage heat service purchased by the user from the cloud energy storage provider; is the maximum limit of the cloud storage heat capacity purchased by the user ; is the power of the cloud storage gas service purchased by the user from the cloud energy storage provider; is the maximum limit of the cloud storage gas capacity purchased by the user ; Solve the user-side charging and discharging decision-making behavior model to obtain a user-side cloud energy storage charging and discharging optimization scheme; the user-side cloud energy storage charging and discharging optimization scheme includes the actual power purchased by each user from the power grid, the heat network, and the gas network.

2. The user-side cloud energy storage charging and discharging optimization method according to claim 1, characterized in that Respectively predicting photovoltaic output data and wind power output data according to the real-time meteorological data of sunlight and the real-time meteorological data of wind speed specifically includes: Preprocess the real-time meteorological data of sunlight and the real-time meteorological data of wind speed to obtain preprocessed light data and preprocessed wind data; Input the preprocessed light data and preprocessed wind data into the trained new energy output prediction model respectively to predict the photovoltaic output data and the wind power output data.

3. The user-side cloud energy storage charging and discharging optimization method according to claim 2, wherein The trained new energy output prediction model includes an initial feature extraction module, a time series feature extraction module, and an output prediction module connected in sequence; The initial feature extraction module is used to extract features from the preprocessed light data and the preprocessed wind data respectively to obtain sunlight features and wind speed features; The time series feature extraction module is used to extract time series features from the sunlight features and the wind speed features respectively to obtain a final sunlight time series feature vector and a final wind speed time series feature vector; The output prediction module is used to predict the photovoltaic output data and the wind power output data respectively according to the final sunlight time series feature vector and the final wind speed time series feature vector.

4. The user-side cloud energy storage charge and discharge energy optimization method according to claim 1, wherein The price-based demand response model includes a load curtailment model and a load transfer model; The load curtailment model is expressed as follows: ； ； Among them, represents the elasticity coefficient of the time-of-use price with respect to the load that can be curtailed at the moment; is the change in the load that can be curtailed at the moment after demand response; is the change in the time-of-use price at the moment after demand response; is the initial time-of-use price at is the initial load that can be curtailed at the price-demand elasticity matrix of the load that can be curtailed; is the time-of-use price at The load transfer model is expressed as follows: ； In the formula, is the change in transferable load after demand response at time ; is the initial transferable load at time ; and is the SL price demand elasticity matrix.

5. The user-side cloud energy storage charge and discharge energy optimization method according to claim 1, wherein The alternative demand response model is expressed as follows: ； ； Wherein, and are respectively the replaceable electric load and the corresponding replaced heat load; is the electric-heat substitution coefficient; and are respectively the unit calorific values of electric energy and heat energy; and are respectively the energy utilization rates of electric energy and heat energy.

6. The user-side cloud energy storage charge and discharge energy optimization method according to claim 1, characterized in that The constraint condition includes a maximum alternative load quantity constraint; the maximum alternative load quantity constraint is expressed as follows: ； In the formula, is the replaceable electrical load at time The minimum and maximum replacement amounts of the replaceable electrical load, respectively; is the replaceable heat load at time The minimum and maximum replacement amounts of the replaceable heat load, respectively.

7. A user-side cloud energy storage charge and discharge optimization device, characterized in that, The user-side cloud energy storage charging and discharging optimization device includes: A meteorological data acquisition module, which is used to: obtain real-time meteorological data of sunlight and real-time meteorological data of wind speed; An output data prediction module, which is used to: predict photovoltaic output data and wind power output data respectively according to the real-time meteorological data of sunlight and the real-time meteorological data of wind speed; A demand response model establishment module, which is used to: establish a price-based demand response model and an alternative demand response model; The user-side charging and discharging energy decision-making behavior model establishment module is used for: establishing a user-side charging and discharging energy decision-making behavior model according to the price-based demand response model, the alternative demand response model, the photovoltaic output data, and the wind power output data; the user-side charging and discharging energy decision-making behavior model includes an objective function and constraint conditions; the objective function is a function with the minimum equivalent annual cost of the user as the goal; the objective function is expressed as follows: ； ； ； ； In the formula, is the objective function, is the equal annual value cost of the user, is the equal annual value coefficient; is the energy storage life cycle; is the annual interest rate; is the investment cost of the user ; are the unit power service fees of the lithium battery, heat storage tank, and gas storage tank respectively; are the unit capacity service fees of the lithium battery, heat storage tank, and gas storage tank respectively; is the operating cost of the user ; is the number of days in a typical day of each season; respectively represent the prices at which the user purchases unit power energy from the electricity, heat, and gas grids; are the prices at which the user sells back unit power energy to the electricity, heat, and gas grids respectively; are the calorific value coefficients of the heat grid and gas grid converted to unit power respectively; are respectively the actual power purchased by the user from the electricity, heat, and gas grids at time respectively representing electricity, heat, and gas; is the power of the user renting cloud electricity storage services from the cloud energy storage provider; is the maximum limit of the cloud electricity storage capacity purchased by the user ; is the power of the user purchasing cloud heat storage services from the cloud energy storage provider; is the maximum limit of the cloud heat storage capacity purchased by the user ; is the power of the user purchasing cloud gas storage services from the cloud energy storage provider; is the maximum limit of the cloud gas storage capacity purchased by the user ; The user-side cloud energy storage charging and discharging energy optimization module is used for: solving the user-side charging and discharging energy decision-making behavior model to obtain a user-side cloud energy storage charging and discharging energy optimization plan; the user-side cloud energy storage charging and discharging energy optimization plan includes the actual power purchased by each user from the power grid, the heat network, and the gas network.

8. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the user-side cloud energy storage charging and discharging energy optimization method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the user-side cloud energy storage charging and discharging energy optimization method according to any one of claims 1-6.

Images