User side cloud energy storage charging and discharging optimization method, device and equipment and medium

Abstract

The invention discloses a user side cloud energy storage energy charging and discharging optimization method and device, equipment and a medium, and relates to the field of user side energy storage optimization operation, and the method comprises the steps: obtaining illumination real-time meteorological data and wind speed real-time meteorological data; according to the illumination real-time meteorological data and the wind speed real-time meteorological data, photovoltaic output data and wind power output data are predicted; establishing a price type demand response model and an alternative type demand response model; according to the price type demand response model, the substitution type demand response model, the photovoltaic output data and the wind power output data, establishing a user side energy charging and discharging decision behavior model; solving the user side energy charging and discharging decision behavior model to obtain a user side cloud energy storage energy charging and discharging optimization scheme; the user side cloud energy storage charging and discharging optimization scheme comprises actual power purchased by each user from a power grid, a heat supply network and a gas network, the utilization efficiency of an energy storage system is improved, the load of the power grid is balanced, and a better energy storage scheduling effect is achieved.

Description

Technical Field

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

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

[0003] The purpose of this application is to provide a user-side cloud energy storage charging and discharging optimization method, device, equipment and medium, which maximizes energy efficiency and minimizes operating costs, improves the utilization efficiency of the energy storage system, balances the grid load, and achieves a better energy storage scheduling effect.

[0004] To achieve the above objectives, this application provides the following solutions.

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

[0006] Get real-time meteorological data of light intensity and wind speed.

[0007] The photovoltaic output data and the wind power output data are predicted according to the real-time meteorological data of illumination and the real-time meteorological data of wind speed respectively.

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

[0009] A user-side charging and discharging decision-making behavior model is established based on the price-type demand response model, the alternative demand response model, the photovoltaic output data and the wind power output data; the user-side charging and discharging decision-making behavior model includes an objective function and constraints; the objective function is a function that aims to minimize the user's equal annual cost.

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

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

[0012] The meteorological data acquisition module is used to obtain real-time meteorological data of light intensity and wind speed.

[0013] The output data prediction module is used to predict photovoltaic output data and wind power output data according to the real-time meteorological data of light intensity and the real-time meteorological data of wind speed, respectively.

[0014] The demand response model establishment module is used to establish a price-based demand response model and an alternative demand response model.

[0015] The user-side charging and discharging decision-making behavior model establishment module is used to: establish a user-side charging and discharging decision-making behavior model according to the price-type demand response model, the alternative demand response model, the photovoltaic output data and the wind power output data; the user-side charging and discharging decision-making behavior model includes an objective function and constraints; the objective function is a function that aims to minimize the user's equal annual cost.

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

[0017] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein 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 having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned user-side cloud energy storage charging and discharging optimization method.

[0019] According to the specific embodiments provided in this application, this application discloses the following technical effects: The present application provides a user-side cloud energy storage charging and discharging optimization method, device, equipment and medium. Through real-time meteorological data of light and wind speed, photovoltaic output data and wind power output data are predicted, and a price-type demand response model and an alternative demand response model are established. According to the price-type demand response model, the alternative demand response model, the photovoltaic output data and the wind power output data, a user-side charging and discharging decision-making behavior model is established. At the same time, considering the uncertainty of new energy output and demand response, the charging and discharging strategy of the user-side energy storage system is optimized, and energy efficiency is maximized and operating cost is minimized. By fully considering the volatility of new energy power generation and the flexibility of user-side load demand response in 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

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 This is an application environment diagram of a user-side cloud energy storage charging and discharging optimization method in one embodiment of the present application; Figure 2 A flowchart of a method for optimizing charging and discharging of cloud energy storage at a user side provided in one embodiment of the present application; Figure 3 A schematic diagram of a specific process of a user-side cloud energy storage charging and discharging optimization method provided in an embodiment of the present application; Figure 4 A schematic diagram of a new energy output prediction model structure provided in one embodiment of the present application; Figure 5 A neural network block diagram of a long short-term memory network provided in one embodiment of the present application; Figure 6 A schematic diagram of functional modules of a user-side cloud energy storage charging and discharging optimization device provided in another embodiment of the present application; Figure 7 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0023] Cloud energy storage technology has gradually become an important solution. Cloud energy storage can not only centrally manage decentralized energy storage resources, but also improve the overall efficiency of energy storage systems through intelligent scheduling and optimization algorithms. The research framework and basic model of cloud energy storage in power systems introduces the research framework of cloud energy storage from the three perspectives of operation, object and market, establishes a basic mathematical model of cloud energy storage, and gives a decision-making method for cloud energy storage providers based on the uncertainty of user charging and discharging behavior. The robust optimal configuration model of cloud energy storage based on cooperative game takes into account the uncertainty of renewable energy. The optimization design of power systems based on smart grids proposes a P2P sharing model for user-side shared energy storage, which sells the right to use excess energy storage capacity when the power load is met, so as to optimize the benefits of energy storage providers, consumers and platforms. However, the utilization efficiency of energy storage systems in the above methods is low. Traditional cloud energy storage scheduling optimization methods are usually based only on fixed load modes, ignoring the volatility and uncertainty of new energy (such as wind energy, solar energy, etc.) in actual output. In addition, the demand response strategy is not fully integrated with the energy storage system in traditional methods, resulting in the inability to flexibly respond to fluctuations in electricity prices and dynamic changes in user loads. In response to the above problems, this application proposes a user-side cloud energy storage charging and discharging optimization method.

[0024] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0025] The user-side cloud energy storage charging and discharging optimization method provided in the embodiment of the present application can be applied to 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 up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the real-time meteorological data of light and wind speed to the server 104. After the server 104 receives the real-time meteorological data of light and wind speed, for the real-time meteorological data of light and wind speed, the server 104 predicts the photovoltaic output data and wind power output data according to the real-time meteorological data of light and wind speed, respectively, and establishes a price-type demand response model and an alternative demand response model. According to the price-type demand response model, the alternative demand response model, the photovoltaic output data and the wind power output data, a user-side charging and discharging decision-making behavior model is established, 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 plan. The server 104 can feedback the obtained user-side cloud energy storage charging and discharging optimization plan to the terminal 102. In addition, in some embodiments, the user-side cloud energy storage charging and discharging optimization method can also be implemented independently 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 meteorological data of light and the real-time meteorological data of wind speed, or the server 104 can obtain the real-time meteorological data of light and the real-time meteorological data of wind speed from the data storage system, and perform energy storage charging and discharging optimization processing on the real-time meteorological data of light and the real-time meteorological data of wind speed.

[0026] The terminal 102 may be, but is not limited to, various desktop computers and laptop computers. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0027] In an exemplary embodiment, Figure 2 and Figure 3 As shown, a method for optimizing the charging and discharging of cloud energy storage at the user side is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or can be executed by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used for explanation, and the steps include the following steps 201 to 205.

[0028] Step 201: Acquire real-time meteorological data of light intensity and real-time meteorological data of wind speed.

[0029] Step 202: predicting photovoltaic power output data and wind power output data according to the real-time meteorological data of light intensity and the real-time meteorological data of wind speed, respectively.

[0030] Step 203: Establish a price-based demand response model and a substitution-based demand response model.

[0031] Step 204: Establish a user-side charging and discharging decision-making behavior model based on 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 decision-making behavior model includes an objective function and constraints; the objective function is a function that aims to minimize the user's equal annual cost.

[0032] Step 205: Solve the user-side charging and discharging decision-making behavior model to obtain a user-side cloud energy storage charging and discharging optimization plan; the user-side cloud energy storage charging and discharging optimization plan includes the actual power purchased by each user from the power grid, heat grid, and gas grid.

[0033] By implementing the above steps 201 to 205, the volatility and uncertainty of new energy are evaluated in real time to ensure that the energy storage system can fully absorb new energy. At the same time, the demand response mechanism is introduced into the energy storage dispatch to flexibly adjust the energy storage charging and discharging strategy according to the real-time changes in electricity prices and user loads. Ultimately, the economic efficiency and operating efficiency of user-side cloud energy storage are significantly improved.

[0034] In another exemplary embodiment of the present application, the above step 202 may include the following steps 301 to 302.

[0035] Step 301: preprocessing the real-time meteorological data of illumination and the real-time meteorological data of wind speed to obtain preprocessed light data and preprocessed wind data.

[0036] Step 302: respectively input the pre-processed light data and the pre-processed wind data into the trained new energy output prediction model to predict photovoltaic output data and wind power output data.

[0037] By introducing a new energy output prediction model, the volatility and uncertainty of new energy can be evaluated in real time to ensure that the energy storage system can fully absorb new energy.

[0038] The structure of the new energy output prediction model is as follows: Figure 4As shown, 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 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 light features and wind speed features; the time series feature extraction module is used to extract time series features from the light features and wind speed features, respectively, to obtain the final time series feature vector of light and the final time series feature vector of wind speed; the output prediction module is used to predict the photovoltaic output data and the wind power output data according to the final time series feature vector of light and the final time series feature vector of wind speed.

[0039] First, the real-time meteorological data of light and wind speed are obtained from the sensors and monitoring systems of the energy storage equipment on the user side. The real-time meteorological data of light includes multiple meteorological factors such as light intensity and temperature and humidity. The real-time meteorological data of wind speed includes multiple meteorological factors such as wind speed and temperature and humidity. They 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 removal of outliers. Then, a convolutional neural network is used to extract high-dimensional features of the input data. Then, a long short-term memory network based on SimAM optimization is used to extract time series features through historical typical daily distributed energy output data. Finally, the meteorological and time series features are integrated, and the fully connected layer is used to predict the energy output probability distribution of distributed energy storage and perform sampling.

[0040] Normalize the real-time meteorological data of light and wind speed and remove outliers. Secondly, conduct correlation analysis and feature screening on meteorological factors affecting photovoltaic output. The total time Meteorological factor data, The moment The meteorological factor data are , the photovoltaic output data is Calculate the Meteorological factors Direct correlation coefficient with photovoltaic output , expressed as the form shown in formula (1).

[0041] (1).

[0042] (2).

[0043] In the formula, , represents the mean value of meteorological factor data; , represents the mean value of photovoltaic output data; is the partial regression coefficient.

[0044] No. Type I meteorological factors Indirect correlation coefficient between meteorological factors and photovoltaic output As shown in the following formula.

[0045] (3).

[0046] (4).

[0047] In the formula, For the Class and The correlation coefficient between these numerical meteorological data. Correlation coefficient between meteorological factors and photovoltaic output As shown in the following formula.

[0048] (5).

[0049] The photovoltaic output and meteorological data of a certain place are used for correlation analysis, and the factors with correlation coefficient greater than 0.2 are selected. Finally, for photovoltaic, the meteorological factors selected for real-time meteorological data of light include light radiation intensity, temperature, humidity, etc.; for wind power, the factors selected for real-time meteorological data of wind speed include wind speed, temperature, humidity, etc.). Assume that a total of factors, the vector composed of these meteorological factor data That is The meteorological feature vector at the time.

[0050] 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 used, which consists of a convolution layer, a batch normalization layer, an activation layer, and a pooling layer. Among them, the convolution layer is the main operation unit, which completes the convolution operation through the filter and step structure inside the module. The operation process of the convolution layer is shown in formula (6).

[0051] (6).

[0052] In the formula, is the convolution kernel size; is the convolution kernel weights; 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.

[0053] (7).

[0054] In the formula, Output data for the convolution layer; for The mean of for The variance of and are the scaling factor and offset factor respectively.

[0055] The data is then activated by 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, it is spatially merged through the pooling window to reduce the feature size while maintaining the feature information. The pooling layer in the convolutional neural network uses the maximum pooling layer, which is defined as , where is the output of the pooling layer, is the set of all data in the pooling area.

[0056] The time series feature extraction module uses the long short-term memory (LSTM) network based on SimAM optimization to extract time series features. LSTM processes time series data. However, when processing input data, the traditional LSTM module cannot adaptively adjust its weight according to the importance of the feature, resulting in information dispersion and loss of important information. The time series feature extraction module is named SimLSTM module. The SimLSTM module finds key nodes by measuring the linear separability of neurons without adding additional parameters. Neuron energy is the key parameter of this mechanism to distinguish the importance of different neurons. The calculation method is shown in the following formula.

[0057] (8).

[0058] In the formula, and Represent the target neuron and other neurons in the same channel respectively. is the index of the neuron in the channel, and is the linear transformation of the corresponding neuron. The lower the target neuron energy is, the better it reflects the neuron The greater the linear separation from other neurons, the more the minimum value of equation (8) needs to be solved. In order to simplify the optimization calculation process, , Binary labeling is adopted, and a regularization term is added to the objective function. The final energy expression is shown in the following formula.

[0059] (9).

[0060] In order to reduce the Computational burden, in the above formula and It is obtained through analytical solution as shown below.

[0061] (10).

[0062] (11).

[0063] In the formula, and is a single channel except for the target neuron q The mean and variance of all other neurons except the target neuron. Since the distribution of neurons in the same channel is consistent, the target neuron can be simplified q The mean and variance calculation process of , that is, the statistical parameters are calculated based on the overall neurons in the channel.

[0064] (11).

[0065] The minimum energy function of the final target neuron q can be calculated by formula (12).

[0066] (12).

[0067] The smaller the value of the neuron's minimum energy function is, the more obvious its implicit features are. It can represent the importance of each neuron. At the same time, the weighted calculation of the attention mechanism is completed according to the importance of each neuron, and the process is shown in the following formula.

[0068] (13).

[0069] In the formula, It is a matrix representation of the minimum energy function value of all neurons. The activation function sigmoid is used to prevent excessive values ​​from appearing in the parameter matrix.

[0070] In getting the weighted features After that, it is input into the forget gate in the LSTM cell. , Memory Gate and cell status , and finally get the output gate , the neural network block diagram of the LSTM unit is as follows Figure 5 shown.

[0071] Shared use L LSTM units extract historical feature vectors. When the prediction time is At the moment, The input of LSTM units For the The meteorological characteristic vector at each moment and photovoltaic output data The splicing process is shown in the following formula.

[0072] (14).

[0073] In the formula, Represents a concatenation operation.

[0074] Traversal Calculate the LSTM unit input gate , Forget Gate , output gate and the status of each unit , .definition , , the calculation formula is as follows.

[0075] (15).

[0076] (16).

[0077] (17).

[0078] (18).

[0079] (19).

[0080] In the formula, , , , They 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. The cell state of a LSTM network cell As a time series feature vector Finally, the output of the SimLSTM module is sent to the output prediction module to obtain the first The new energy output sampling value at the moment , the output prediction module is a fully connected layer, which is specifically expressed in the form shown in the following formula.

[0081] (20).

[0082] In the formula, is the weight of the fully connected layer.

[0083] Different types of loads have different sensitivities to the same electricity price signal. The price-based demand response load is divided into curtailable load (CL) and shiftable load (SL). The following models the two types of loads separately. The price-based demand response model includes a curtailable load model and a shiftable load model.

[0084] CL chooses whether to reduce its own load by comparing the changes in electricity prices before and after DR. The price demand elasticity matrix is ​​used to describe the DR characteristics, and the load reduction model is shown in the following formula.

[0085] (twenty one).

[0086] (twenty two).

[0087] in, express Time can reduce the load The elasticity coefficient of electricity price at the moment is the price demand elasticity matrix Middle Line Column elements; After demand response The amount of load variation that can be reduced at any time; for The load that can be reduced at any time; After demand response Changes in electricity prices at each moment; for Initial electricity price at the time; for The load can be reduced at the beginning of the time; is the price demand elasticity matrix for curtailable load; for Electricity price at any time.

[0088] Transferable load refers to the load that users can flexibly adjust their working hours by responding to electricity prices according to their own needs. With the peak, flat and valley time-of-use electricity prices as signals, users can be guided to transfer the load during peak hours to flat and valley hours. Similarly, the price demand elasticity matrix is ​​used to describe the DR characteristics, and the transferable load model is expressed as shown in the following formula.

[0089] (twenty three).

[0090] In the formula, After demand response The change in transferable load at a given moment, for The initial transferable load at time t; is the SL price demand elasticity matrix.

[0091] For a certain type of thermal load that can be directly supplied by thermal energy or electric energy, electric 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, thereby realizing the replaceable load (RL) model of mutual substitution of electric energy and thermal energy, that is, the alternative demand response model is expressed as shown in the following formula.

[0092] (twenty four).

[0093] (25).

[0094] in, , are the replaceable electrical load and the corresponding replaced thermal load respectively; is the electric heat substitution coefficient; , are the unit calorific values ​​of electrical energy and thermal energy respectively; , are the energy utilization rates of electrical energy and thermal energy respectively. In formula (24), “ " indicates that the reduction of replaceable electrical load corresponds to the increase of replaced thermal load. For this type of load, the maximum replaceable load constraint needs to be considered, as shown in the following formula.

[0095] (26).

[0096] In the formula, for Can replace electrical load at any time; are the minimum and maximum replacement amounts of replaceable electric loads respectively; for The heat load can be replaced at any time; are the minimum and maximum replacement amounts of the replaceable heat load respectively.

[0097] For electricity load users, their renewable energy output mainly includes self-built photovoltaic (PV) and part of the regional wind turbine (WT) output obtained through sharing; for heat load users, their renewable energy output is the shared WT-heat output; for gas load users, their renewable energy output is the shared WT-gas output. Season, moments (collectively referred to as time), user The output of new energy sources such as electricity, heat and gas is shown in the following formula.

[0098] (27).

[0099] (28).

[0100] (29).

[0101] In the formula, They are Provide users with The new energy output of electricity, heat and gas loads; They are Moment User Self-built PV output and shared WT output; are the split coefficients of WT and P2G, respectively; are the efficiencies of P2G and gas boiler (GB), respectively.

[0102] Defining Operations , As shown in the following formula.

[0103] (30).

[0104] When there is no energy storage device, users Purchase power from the electricity, heat and gas grids respectively. When the output of new energy is in excess, users The excess power is fed back to the electricity, heat and gas grids respectively, and users The power purchased and sent back are shown in the following formulas respectively.

[0105] (31).

[0106] (32).

[0107] In the formula, They are Moment User The electricity, heat and gas power purchased from the energy grid due to insufficient output of new energy sources, They represent electricity, heat, and gas respectively; , They are Moment User The electricity, heat and gas power fed back to the energy grid due to excess output of new energy sources; , After considering DR Moment User Electricity, heat and gas loads.

[0108] Consider a single electricity load user Rational cloud energy storage charging and discharging behavior, setting critical charging electricity prices Critical discharge price In electricity prices When the electricity price is lower than the critical charging price or when the output of renewable energy is in excess, the user controls the cloud energy storage to charge; when the electricity price is higher than the critical discharge price and the output of renewable energy 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 price and lower than the critical discharge price, the cloud energy storage does not discharge. In the latter two cases, the user controls the cloud energy storage to charge only when the renewable energy power is in excess. Therefore, the user in this period The charge and discharge behavior is expressed as follows.

[0109] when ,hour, (33).

[0110] In the formula, They are Moment User The charging and discharging power requirements of cloud energy storage; For users Lease the power of cloud storage services from cloud energy storage providers; for At the end of the time, the user The remaining capacity of leased cloud storage; For users The maximum limit of the cloud storage capacity purchased; For users The charging efficiency of the purchased cloud storage; Indicates the time interval. This application adopts the time-of-use electricity price. Take it as 1h.

[0111] when When , the cloud energy storage charging and discharging power demand is expressed as follows.

[0112] (34).

[0113] when When , the cloud energy storage charging and discharging power demand is expressed as follows.

[0114] (35).

[0115] In the formula, express Moment User The electric power sent back to the energy grid due to excess output of new energy. For users The discharge efficiency of the purchased cloud storage, They are Moment User Electric power purchased from the energy grid due to insufficient output of renewable energy.

[0116] Taking into account the specific conditions of the heat market and the natural gas market, the prices of heat and gas are fixed. Therefore, when a single heat user's own renewable energy output is greater than the heat demand, the heat storage tank is controlled to store heat. When the renewable energy output is not enough to meet the load heat demand, the heat storage tank is controlled to release heat. moment, user The charging and discharging heat behavior is expressed as follows.

[0117] (36).

[0118] In the formula, They are Moment User The power demand for charging and discharging of cloud energy storage; For users Purchase power of cloud thermal storage services from cloud energy storage providers; for At the end of the time, the user The remaining capacity of purchased cloud thermal storage; For users The maximum value of the cloud thermal storage capacity purchased; For users The charging and discharging efficiency of the purchased cloud energy storage; express Moment User Thermal power fed back to the energy grid due to excess output of renewable energy; They are Moment User Thermal power purchased from the energy grid due to insufficient output from renewable energy sources.

[0119] When a single gas user's own renewable energy output is greater than the gas demand, the gas storage tank is controlled to store gas. When the renewable energy output is not enough to meet the load gas demand, the gas storage tank is controlled to release gas. Moment User The inflation and deflation behavior is expressed as follows.

[0120] (37).

[0121] In the formula, They are Moment User The power demand for charging and discharging of cloud energy storage; For users Purchase power of cloud gas storage services from cloud energy storage providers; For users The maximum limit of the cloud storage capacity purchased; for At the end of the time, the user The remaining capacity of purchased cloud gas storage; For users The charging and discharging efficiency of the purchased cloud energy storage; express Moment User The gas power fed back to the energy grid due to excess output of new energy; for Moment User Gas power purchased from the energy grid due to insufficient output from renewable energy sources.

[0122] The purpose of introducing energy storage is to reduce wind and solar power abandonment, better absorb new energy, and thus reduce costs. Prioritize the use of new energy sources for charging. Single user The new energy charging part of the charging, heating and gas charging power is expressed as the following formula.

[0123] (38).

[0124] In the formula, They are Moment User The charging power of new energy sources such as electricity, heat and gas.

[0125] Combined with the above description of user energy usage behavior, a single user The actual power purchased or returned from the electricity, heat and gas grid is (39).

[0126] In the formula, They are Moment User The actual power purchased from the electricity, heat and gas grid.

[0127] Cloud energy storage users lease the right to use cloud energy storage of a certain power and capacity from cloud energy storage providers according to their own load needs. 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 costs incurred by purchasing energy from the electricity, heat and gas networks when the output of new energy and cloud energy storage capacity are insufficient during actual operation.

[0128] Since cloud energy storage providers centrally manage physical energy storage, users save the fixed costs of operating and maintaining physical energy storage. The minimum is the goal, and the objective function is constructed as shown in the following formula.

[0129] (40).

[0130] (41).

[0131] (42).

[0132] (43).

[0133] In the formula, is the objective function, For users, the annual cost is equal to the cost of is the coefficient of equal annual value; is the energy storage life cycle; is the annual interest rate; For users The investment cost of energy storage equipment includes lithium batteries, heat storage tanks and gas storage tanks, etc. They are the unit power service fees for lithium batteries, heat storage tanks, and gas storage tanks; They are the unit capacity service fees for lithium batteries, thermal storage tanks, and gas storage tanks; For users operating costs; The number of typical days for each season; Respectively represent the price of unit power energy purchased between users and electricity, heat and gas grids, in units of RMB / (kW·h), RMB / GJ and RMB / m 3 ; are the prices of unit power energy sent back between users and the electricity, heat and gas grids, in units of RMB / (kW·h), RMB / GJ and RMB / m 3 ; They are the heating value coefficients of the heat network and gas network converted to unit power, in units of kW / GJ and kW / m 3 ; They are Moment User The actual power purchased from the electricity, heat and gas grids, They represent electricity, heat and gas respectively.

[0134] The constraints of the user-side charging and discharging decision-making behavior model include the maximum replaceable load constraint; the maximum replaceable load constraint is shown in formula (26). Taking the minimum annual cost of the user as the objective function, the YALMIP toolbox in MATLAB is used to call the commercial solver CPLEX to solve the user-side charging and discharging decision-making behavior model.

[0135] A large industrial park in the southern region is taken as the research object. The example selects 50 typical daily load data in the region. The dispatch time of each typical day is 24h. The dispatch interval time in this application is 1h. 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 the region are selected, and their prices and time period divisions are shown in Table 2. The survey found that the heat metering in this area is charged by GJ, the residential heating metering heat price is 46 yuan / GJ, and the calorific value coefficient is 0.0036kW / GJ; the unified pricing of the natural gas network is 3.853 yuan / m3, and the calorific value coefficient is 9.7kW / m3. The specific conversion method is shown in Table 3.

[0136] Table 1. Related parameters in the region Table 2 Time-of-use electricity prices and time period division Table 3 Heat-gas power conversion

[0137] In order to verify the effectiveness of the user-side cloud energy storage charging and discharging optimization method proposed in this application, this application designed four different application scenarios in the experimental part, respectively examining the cost performance of users when using cloud energy storage, considering new energy output forecasting, and combining demand response. These four scenarios are specifically described as follows: Scenario 1: Users only use cloud energy storage; Scenario 2: Users use cloud energy storage and consider new energy output forecasting methods; Scenario 3: Users use cloud energy storage and consider demand response; Scenario 4: Users use cloud energy storage and consider new energy output forecasting methods and demand response. The comparison of user equivalent annual cost and renewable energy consumption rate under different scenarios is shown in Table 4.

[0138] Table 4 Comparison of experimental results in different scenarios

[0139] As shown in Table 4, although scenario 2 has a good 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 of scenario 3 can optimize power dispatch, its economic benefits and consumption rate are still not as good as scenario 4 without the support of new energy output forecast. Scenario 4 shows the best results in terms of user equivalent annual cost and renewable energy consumption rate, which verifies 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.

[0140] 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 in 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 meteorological data of light and wind speed enter the energy storage charging and discharging optimization link from the data collection link to obtain the corresponding user-side cloud energy storage charging and discharging optimization solution. 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 optimizing the energy storage charging and discharging link based on the real-time meteorological data of light and wind speed, the photovoltaic output data and the wind power output data can be predicted according to the real-time meteorological data of light and wind speed respectively, and a price-type demand response model and an alternative demand response model can be established. According to the price-type demand response model, the alternative demand response model, the photovoltaic output data and the wind power output data, a user-side charging and discharging decision-making behavior model is established, and the user-side charging and discharging decision-making behavior model is solved to obtain a user-side cloud energy storage charging and discharging optimization plan.

[0141] 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 implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more user-side cloud energy storage charging and discharging optimization device embodiments provided below can refer to the above limitations on the user-side cloud energy storage charging and discharging optimization method, and will not be repeated here.

[0142] In an exemplary embodiment, Figure 6 As shown, a user-side cloud energy storage charging and discharging optimization device is provided, including the following modules.

[0143] The meteorological data acquisition module T1 is used to obtain real-time meteorological data of light intensity and wind speed.

[0144] The output data prediction module T2 is used to predict photovoltaic output data and wind power output data according to the real-time meteorological data of light intensity and the real-time meteorological data of wind speed, respectively.

[0145] The demand response model establishment module T3 is used to establish a price-based demand response model and an alternative demand response model.

[0146] The user-side charging and discharging decision-making behavior model establishment module T4 is used to: establish a user-side charging and discharging decision-making behavior model according to the price-type demand response model, the alternative demand response model, the photovoltaic output data and the wind power output data; the user-side charging and discharging decision-making behavior model includes an objective function and constraints; the objective function is a function that aims to minimize the user's equal annual value cost.

[0147] The user-side cloud energy storage charging and discharging optimization module T5 is used to solve the user-side charging and discharging decision-making behavior model to obtain the user-side cloud energy storage charging and discharging optimization plan; the user-side cloud energy storage charging and discharging optimization plan includes the actual power purchased by each user from the power grid, heat network, and gas network.

[0148] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to 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 optimization data. The input / output interface of the computer device is used to exchange information between the processor and an external device. 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, a user-side cloud energy storage charging and discharging optimization method is implemented.

[0149] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure 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 certain components, or have a different arrangement of components.

[0150] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0151] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0152] 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 used 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 must comply with relevant regulations.

[0153] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and 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 embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. 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 may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0154] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0155] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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, they should be considered to be within the scope of this specification.

[0156] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A user-side cloud energy storage charging and discharging optimization method, characterized in that: The user-side cloud energy storage charging and discharging optimization method includes: Obtain real-time meteorological data of light intensity and wind speed; Predicting photovoltaic power output data and wind power output data according to the real-time meteorological data of light intensity and the real-time meteorological data of wind speed respectively; Establish price-based demand response model and substitution-based demand response model; A user-side charging and discharging decision-making behavior model is established 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 decision-making behavior model includes an objective function and constraint conditions; the objective function is a function that takes the minimization of the user's equal annual cost as the goal; The user-side charging and discharging decision-making behavior model is solved to obtain a user-side cloud energy storage charging and discharging optimization plan; the user-side cloud energy storage charging and discharging optimization plan includes the actual power purchased by each user from the power grid, heat grid, and gas grid.

2. The user-side cloud energy storage charging and discharging optimization method according to claim 1 is characterized in that: The photovoltaic output data and the wind power output data are predicted according to the real-time meteorological data of light intensity and the real-time meteorological data of wind speed, respectively, including: Preprocessing the real-time meteorological data of illumination and the real-time meteorological data of wind speed to obtain preprocessed light data and preprocessed wind data; The preprocessed light data and preprocessed wind data are respectively input into the trained new energy output prediction model to predict photovoltaic output data and wind power output data.

3. The user-side cloud energy storage charging and discharging optimization method according to claim 2 is characterized in that: 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 pre-processed light data and the pre-processed wind data to obtain light features and wind speed features; The time series feature extraction module is used to extract the time series features of the illumination feature and the wind speed feature respectively to obtain the final time series feature vector of the illumination and the final time series feature vector of the wind speed; The output prediction module is used to predict photovoltaic output data and wind power output data according to the final time series characteristic vector of light and the final time series characteristic vector of wind speed respectively.

4. The user-side cloud energy storage charging and discharging optimization method according to claim 1 is characterized in that: The price-based demand response model includes a curtailable load model and a transferable load model; The curtailable load model is expressed as follows: ； ； in, express Time can reduce the load The elasticity coefficient of electricity price at each time; After demand response The amount of load variation that can be reduced at any time; for The load that can be reduced at any time; After demand response Changes in electricity prices at each moment; for Initial electricity price at the time; for The load can be reduced at the beginning of the time; is the price demand elasticity matrix for curtailable load; for Electricity price at any time; The transferable load model is expressed as follows: ； In the formula, After demand response The change in transferable load at a given moment, for The initial transferable load at time t; is the SL price demand elasticity matrix.

5. The user-side cloud energy storage charging and discharging optimization method according to claim 1 is characterized in that: The alternative demand response model is expressed as follows: ； ； in, , are the replaceable electrical load and the corresponding replaced thermal load respectively; is the electric heat substitution coefficient; , are the unit calorific values ​​of electrical energy and thermal energy respectively; , are the energy utilization rates of electrical energy and thermal energy, respectively.

6. The user-side cloud energy storage charging and discharging optimization method according to claim 1 is characterized in that: The objective function is expressed as follows: ； ； ； ； In the formula, is the objective function, For users, the annual cost is equal to the cost of is the coefficient of equal annual value; is the energy storage life cycle; is the annual interest rate; For users investment costs; They are the unit power service fees for lithium batteries, heat storage tanks, and gas storage tanks; They are the unit capacity service fees for lithium batteries, heat storage tanks, and gas storage tanks; For users operating costs; The number of typical days for each season; Respectively represent the price of unit power energy purchased between users and electricity, heat and gas grids; They are the prices of unit power energy sent back between users and the electricity, heat and gas grids respectively; They are the heating value coefficients of the heat network and gas network converted to unit power respectively; They are Moment User The actual power purchased from the electricity, heat and gas grids, They represent electricity, heat and gas respectively.

7. The user-side cloud energy storage charging and discharging optimization method according to claim 1 is characterized in that: The constraint condition includes a maximum replaceable load constraint; the maximum replaceable load constraint is expressed as follows: ； In the formula, for Can replace electrical load at any time; are the minimum and maximum replacement amounts of replaceable electric loads respectively; for The heat load can be replaced at any time; are the minimum and maximum replacement amounts of the replaceable heat load respectively.

8. A user-side cloud energy storage charging and discharging optimization device, characterized in that: The user-side cloud energy storage charging and discharging optimization device comprises: The meteorological data acquisition module is used to obtain real-time meteorological data of light intensity and wind speed; An output data prediction module is used to predict photovoltaic output data and wind power output data according to the real-time meteorological data of light intensity and the real-time meteorological data of wind speed, respectively; The demand response model establishment module is used to establish a price-based demand response model and an alternative demand response model; A user-side charging and discharging decision-making behavior model establishment module is used to establish a user-side charging and discharging decision-making behavior model according to the price-type demand response model, the alternative demand response model, the photovoltaic output data, and the wind power output data; 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 annual cost of the user as the goal; The user-side cloud energy storage charging and discharging optimization module is used to solve the user-side charging and discharging decision-making behavior model to obtain the user-side cloud energy storage charging and discharging optimization plan; the user-side cloud energy storage charging and discharging optimization plan includes the actual power purchased by each user from the power grid, heat grid, and gas grid.

9. A computer device comprising: A memory, a processor, and a computer program stored in 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 optimization method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the user-side cloud energy storage charging and discharging optimization method described in any one of claims 1 to 7 is implemented.

Images