Method, device, equipment, medium and program product for scheduling mobile energy storage system

Abstract

The application relates to a mobile energy storage system scheduling method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring demand prediction data corresponding to a plurality of target moments in a preset time period, wherein the demand prediction data comprises an electric load power demand prediction value, a thermal load power demand prediction value and a mobile energy storage system position transfer time prediction value; acquiring a constraint condition and a scheduling model corresponding to the mobile energy storage system, wherein the constraint condition at least comprises a power supply operation constraint condition and a heat supply operation constraint condition of the mobile energy storage system, and the scheduling model is used for representing a scheduling target of the mobile energy storage system in the preset time period; and in the case that the demand prediction data and the constraint condition both satisfy the scheduling target, determining supply data corresponding to the demand prediction data according to the demand prediction data and the scheduling model. The method can reduce the energy supply cost.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of energy storage systems, and in particular, to a scheduling method and device for a mobile energy storage system, a computer device, a storage medium, and a computer program product. BACKGROUND

[0002] In remote areas, in order to meet the living requirements of local residents, the power demand and heat demand of local residents need to be met.

[0003] In the prior art, a diesel generator system is usually configured to meet the power demand of local residents. Meanwhile, an air conditioning system is usually configured to provide heat for the heat demand of residents, and the diesel generator system is also needed to provide power to ensure the operation of the air conditioning system.

[0004] However, the above-mentioned use of diesel generators to support the power demand of users and the normal operation of air conditioners to meet the heat demand has a high energy supply cost. SUMMARY

[0005] Therefore, it is necessary to provide a scheduling method and device for a mobile energy storage system, a computer device, a computer readable storage medium, and a computer program product, which can reduce the energy supply cost.

[0006] In a first aspect, the present application provides a scheduling method for a mobile energy storage system. The method comprises:

[0007] obtaining demand prediction data corresponding to a plurality of target time points in a preset time period, the demand prediction data comprising an electric load power demand prediction value, a heat load power demand prediction value, and a position transfer time prediction value of the mobile energy storage system;

[0008] obtaining a constraint condition and a scheduling model corresponding to the mobile energy storage system, the constraint condition comprising at least a power supply operation constraint condition and a heat supply operation constraint condition of the mobile energy storage system, and the scheduling model being used to represent a scheduling target of the mobile energy storage system in the preset time period;

[0009] in a case where the demand prediction data and the constraint condition both satisfy the scheduling target, determining supply data corresponding to the demand prediction data according to the demand prediction data and the scheduling model.

[0010] In an embodiment, obtaining the demand prediction data corresponding to the plurality of target time points in the preset time period comprises:

[0011] obtaining historical demand data corresponding to a plurality of historical time points in a historical period, the historical demand data comprising a historical electric load power demand value, a historical heat load power demand value, and a historical position transfer time of the mobile energy storage system;

[0012] According to the historical demand data corresponding to each historical moment and the prediction model, the demand prediction data corresponding to each target moment is obtained.

[0013] In one of the embodiments, according to the historical demand data corresponding to each historical moment and the prediction model, the demand prediction data corresponding to each target moment is obtained, including:

[0014] The historical demand data corresponding to each historical moment is input into the prediction model to obtain the demand prediction initial data corresponding to each target moment;

[0015] For each target moment, a Monte Carlo sampling model is used to obtain a plurality of demand prediction data corresponding to the demand prediction initial data.

[0016] In one of the embodiments, the Monte Carlo sampling method is used to obtain a plurality of demand prediction data corresponding to the demand prediction initial data, including:

[0017] A normal distribution function satisfied by the demand prediction initial data is obtained.

[0018] The normal distribution function and the demand prediction initial data are input into the Monte Carlo sampling model to obtain a plurality of demand prediction data corresponding to the demand prediction initial data.

[0019] In one of the embodiments, the scheduling model includes a cost control condition, and the method further includes:

[0020] If the demand prediction data and the constraint condition both satisfy the cost control condition, it is determined that the demand prediction data and the constraint condition both satisfy the scheduling target.

[0021] In one of the embodiments, the mobile energy storage system includes a mobile electric energy storage subsystem and a mobile phase change energy storage subsystem, and the constraint condition corresponding to the mobile energy storage system is obtained, including:

[0022] The power supply operation constraint condition corresponding to the mobile electric energy storage subsystem, the heat supply operation constraint condition corresponding to the mobile phase change energy storage subsystem, and the electric-thermal conversion constraint condition corresponding to the mobile electric energy storage subsystem and the mobile phase change energy storage subsystem are obtained.

[0023] In a second aspect, the application further provides a scheduling device of a mobile energy storage system. The device includes:

[0024] The obtaining module is configured to obtain demand prediction data corresponding to a plurality of target moments in a preset time period, the demand prediction data including an electric load power demand prediction value, a thermal load power demand prediction value, and a position transfer time prediction value of the mobile energy storage system.

[0025] The scheduling module is configured to obtain a constraint condition and a scheduling model corresponding to the mobile energy storage system, the constraint condition at least including a power supply operation constraint condition and a heat supply operation constraint condition of the mobile energy storage system, and the scheduling model being used to represent a scheduling target of the mobile energy storage system in a preset time period.

[0026] The determining module is configured to, in a case where the demand prediction data and the constraint condition both satisfy the scheduling target, determine, according to the demand prediction data and the scheduling model, supply data corresponding to the demand prediction data.

[0027] In one of the embodiments, the obtaining module is specifically configured to:

[0028] obtain historical demand data corresponding to a plurality of historical time points in a historical time period, the historical demand data including a historical electric load power demand value, a historical heat load power demand value, and a historical position transfer time of the mobile energy storage system;

[0029] obtain, according to the historical demand data corresponding to each historical time point and the prediction model, demand prediction data corresponding to each target time point.

[0030] In one of the embodiments, the determining module is specifically configured to:

[0031] input the historical demand data corresponding to each historical time point into the prediction model to obtain demand prediction initial data corresponding to each target time point;

[0032] for each target time point, obtain a plurality of demand prediction data corresponding to the demand prediction initial data by using a Monte Carlo sampling model.

[0033] In one of the embodiments, the determining module is further specifically configured to:

[0034] obtain a normal distribution function satisfied by the demand prediction initial data;

[0035] input the normal distribution function and the demand prediction initial data into the Monte Carlo sampling model to obtain the plurality of demand prediction data corresponding to the demand prediction initial data.

[0036] In one of the embodiments, the scheduling model includes a cost control condition, and the device further includes:

[0037] if the demand prediction data and the constraint condition both satisfy the cost control condition, it is determined that the demand prediction data and the constraint condition both satisfy the scheduling target.

[0038] In one of the embodiments, the mobile energy storage system includes a mobile electric energy storage subsystem and a mobile phase change energy storage subsystem, and the constraint condition corresponding to the mobile energy storage system is obtained by:

[0039] obtain a power supply operation constraint condition corresponding to the mobile electric energy storage subsystem, a heat supply operation constraint condition corresponding to the mobile phase change energy storage subsystem, and an electricity-heat conversion constraint condition corresponding to the mobile electric energy storage subsystem and the mobile phase change energy storage subsystem.

[0040] In a third aspect, the present application also provides a computer device. The computer device comprises a memory and a processor. The memory stores a computer program. The processor implements the scheduling method of the mobile energy storage system according to any one of the first aspect when executing the computer program.

[0041] In a fourth aspect, the present application also provides a computer readable storage medium. The computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the scheduling method of the mobile energy storage system according to any one of the first aspect.

[0042] In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program. The computer program is executed by a processor to implement the scheduling method of the mobile energy storage system according to any one of the first aspect.

[0043] The scheduling method, device, computer device, storage medium and computer program product of the mobile energy storage system obtain demand prediction data corresponding to a plurality of target time points, respectively, and constraint conditions and a scheduling model corresponding to the mobile energy storage system. In the case that the demand prediction data and the constraint conditions meet the scheduling target, the supply data corresponding to the demand prediction data is determined according to the demand prediction data and the scheduling model. The demand prediction data comprises an electric load power demand prediction value, a thermal load power demand prediction value and a position transfer time prediction value of the mobile energy storage system. The constraint conditions at least comprise a power supply operation constraint condition and a heat supply operation constraint condition of the mobile energy storage system. The mobile energy storage system is used to meet the electric demand and the thermal demand of residents. Compared with a diesel generator, the mobile energy storage system has a lower consumption cost, thereby reducing the cost consumed for meeting the energy supply. Moreover, the supply data corresponding to the final demand prediction data is determined based on the electric load power demand prediction value, the thermal load power demand prediction value, the electric load power demand prediction value and the thermal load power demand prediction value. The electric demand and the thermal demand of users are considered, the joint scheduling of the power supply and the heat supply of the mobile energy storage system is realized, the reasonable scheduling of the mobile energy storage system is realized, and the operation cost is greatly reduced. The position transfer time prediction value of the mobile energy storage system is used when the supply data corresponding to the final demand prediction data is determined. The spatial transfer uncertainty of the mobile energy storage system is fully considered, and the reliability and accuracy of the scheduling result are improved. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1A flowchart of a scheduling method of a mobile energy storage system in an embodiment;

[0045] Figure 2 A flowchart of step 101 in an embodiment;

[0046] Figure 3 A flowchart of step 202 in an embodiment;

[0047] Figure 4 A flowchart of step 302 in an embodiment;

[0048] Figure 5 A flowchart of a scheduling method of a mobile energy storage system in another embodiment;

[0049] Figure 6 A distribution map of power grid electricity price in an embodiment;

[0050] Figure 7 A graph of experimental results in an embodiment;

[0051] Figure 8 A graph of experimental results in an embodiment;

[0052] Figure 9 A graph of experimental results in an embodiment.

[0053] Figure 10 A block diagram of a scheduling device of a mobile energy storage system in an embodiment;

[0054] Figure 11 An internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application is further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0056] In remote areas, in order to meet the living requirements of local residents, the electricity demand and heat demand of local residents need to be met.

[0057] Considering the small electricity demand, large investment cost of laying lines and other problems, some remote areas (such as grasslands or plateaus) in China are not connected to the large power grid. The local villages will use diesel generators to generate electricity, but the cost of power generation is relatively high.

[0058] For the heat demand of residents, an air conditioning system is usually configured to provide heat, and a diesel generator system is also needed to provide power to ensure the operation of the air conditioning system.

[0059] However, the above-mentioned use of diesel engine power generation to support the user's electricity demand and the normal operation of the air conditioner has high energy supply consumption cost.

[0060] Therefore, the embodiment of the present application provides a mobile energy storage system scheduling method, which can reduce the energy supply consumption cost.

[0061] It should be noted that the mobile energy storage system scheduling method provided by the embodiment of the present application can be a mobile energy storage system scheduling device, which can be implemented by software, hardware or a combination of software and hardware to become part or all of the terminal.

[0062] In the following method embodiment, the terminal is taken as an example to be executed, wherein the terminal can be a personal computer, a notebook computer, a media player, a smart television, a smart phone, a tablet computer and a portable wearable device, etc. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is realized through the interaction of the terminal and the server.

[0063] Please refer to Figure 1 which shows a flowchart of a mobile energy storage system scheduling method provided by the embodiment of the present application. As Figure 1 shown, the mobile energy storage system scheduling method can include the following steps:

[0064] Step 101, obtaining demand prediction data corresponding to a plurality of target time points in a preset time period respectively.

[0065] The demand prediction data includes an electric load power demand prediction value, a thermal load power demand prediction value and a mobile energy storage system position transfer time prediction value.

[0066] The mobile energy storage system needs to complete the round trip between the grid side and the village site in the preset time period. The position transfer time prediction value corresponding to a target time point refers to the driving time required from the starting site to the target site starting from the target time point. Optionally, the position transfer time prediction value of the mobile energy storage system includes the driving time prediction value from the grid side site to the village site and the driving time prediction value from the village site to the grid side site.

[0067] Optionally, the length of the preset time period is 1 day or 1 week. The preset time period is divided into a plurality of target time points according to a preset time length, wherein the preset time length can be 1 hour, several hours, several minutes or several tens of minutes, etc. For example, when the length of the preset time period is 1 day, the preset time period is divided into 24 target time points according to 1 hour as the preset time length.

[0068] Optionally, the demand prediction data D is represented as follows:

[0069]

[0070] wherein T is a preset time period, i.e., a scheduling period, and is 24 hours; and respectively represent an electric load power demand prediction value and a thermal load power demand prediction value at a tth target moment, wherein t = 1, 2, … T; and respectively represent a position transition time prediction value of the mobile energy storage system from the power distribution network to the village and from the village to the power distribution network at the tth target moment.

[0071] In step 102, the constraint condition and the scheduling model corresponding to the mobile energy storage system are obtained.

[0072] The constraint condition at least includes a power supply operation constraint condition and a heat supply operation constraint condition of the mobile energy storage system, and the scheduling model is used to represent a scheduling target of the mobile energy storage system in the preset time period.

[0073] Optionally, the power supply operation constraint condition at least includes a charging constraint condition and a discharging constraint condition, etc. The heat supply operation constraint condition at least includes a heat storage constraint condition and a heat release constraint condition, etc.

[0074] Optionally, the scheduling target of the scheduling model is to minimize the length of time for which the diesel engine power generation system is used to generate power in the preset time period. The scheduling model includes an objective function and a constraint condition corresponding to the objective function, and correspondingly, the objective function is a function corresponding to the minimum length of time for which the diesel engine power generation system is used to generate power in the preset time period.

[0075] In step 103, when the demand prediction data and the constraint condition both satisfy the scheduling target, the supply data corresponding to the demand prediction data is determined according to the demand prediction data and the scheduling model.

[0076] The supply data includes the power generation power of the diesel engine corresponding to each target moment, the actual discharging power and the actual charging power of the mobile energy storage system, and the actual heat storage power and the actual heat release power of the mobile energy storage system, etc.

[0077] Optionally, the terminal inputs the demand prediction data and the constraint condition into the scheduling model, solves the calling model, and obtains the supply data. For example, the terminal calls a Gurobi solver to solve the calling model.

[0078] In the aforementioned method for dispatching the mobile energy storage system, demand forecast data corresponding to multiple preset target times, along with the corresponding constraints and dispatch model of the mobile energy storage system, are acquired. When both the demand forecast data and constraints meet the dispatch objectives, the supply data corresponding to the demand forecast data is determined based on the demand forecast data and dispatch model. The demand forecast data includes predicted values ​​for electrical load power demand, thermal load power demand, and the predicted location transfer time of the mobile energy storage system. The constraints include at least power supply and heating operation constraints for the mobile energy storage system. Since a mobile energy storage system is used to meet residents' electricity and heating needs, its consumption cost is lower than that of diesel generators, reducing the cost of meeting energy supply requirements. By determining the final supply data corresponding to the demand forecast data based on the predicted values ​​for electrical load power demand, thermal load power demand, and thermal load power demand, and considering both user electricity and heating needs, the joint dispatch of power supply and heating from the mobile energy storage system is achieved, realizing reasonable dispatch of the mobile energy storage system and significantly reducing operating costs. In addition, the location transfer time prediction value of the mobile energy storage system was also used when determining the supply data corresponding to the final demand forecast data. This fully takes into account the spatial transfer uncertainty of the mobile energy storage system and improves the reliability and accuracy of the scheduling results.

[0079] In one embodiment, based on Figure 1 The illustrated embodiment can be found in [reference]. Figure 2 This embodiment relates to the process of obtaining demand prediction data corresponding to multiple target times within a preset time period in step 101.

[0080] like Figure 2 As shown, the implementation process includes steps 201 and 202:

[0081] Step 201: Obtain historical demand data corresponding to multiple historical moments within the historical period.

[0082] The historical demand data includes historical electrical load power demand values, historical thermal load power demand values, and historical location transfer times of mobile energy storage systems.

[0083] Optionally, the length of this historical time period is the same as the length of a preset time period. The historical time period is divided according to the preset time period to obtain multiple historical moments. This historical time period is any time period preceding the preset time period in chronological order. For example, this historical time period is a time period whose end point is the start time of the preset time period in chronological order.

[0084] Optionally, a large amount of historical demand data samples are stored in the terminal, and the data samples include historical demand data and time information corresponding to the historical demand data. The historical demand data samples are processed according to the time information corresponding to the historical demand data, and historical demand data corresponding to each historical time in a historical time period is obtained.

[0085] In step 202, demand prediction data corresponding to each target time is obtained according to the historical demand data corresponding to each historical time and a prediction model.

[0086] Optionally, the prediction model includes one of a long short-term memory (LSTM) model, a temporal convolutional network (TCN) model, and a time graph network (TGNs) model.

[0087] The prediction model can be trained by the terminal itself, or the prediction model can be trained by a server and sent to the terminal after training, so as to save the computing resources of the terminal. The terminal inputs the historical demand data corresponding to each historical time into the trained prediction model, and obtains the demand prediction data corresponding to each target time.

[0088] In this embodiment, the demand prediction data corresponding to each target time is obtained according to the historical demand data corresponding to each historical time and the prediction model, and the demand prediction data corresponding to each target time is obtained by prediction based on historical data, thereby improving the accuracy of the demand prediction data.

[0089] In one embodiment, based on Figure 2 As shown in the embodiment shown in Figure 3 The embodiment relates to step 202, in which demand prediction data corresponding to each target time is obtained according to historical demand data corresponding to each historical time and a prediction model, and includes steps 301 and 302.

[0090] In step 301, the historical demand data corresponding to each historical time is input into the prediction model, and demand prediction initial data corresponding to each target time is obtained.

[0091] The demand prediction initial data includes an electrical load power demand prediction initial value, a thermal load power demand prediction initial value, and a mobile energy storage system position transfer time prediction initial value.

[0092] Optionally, the prediction model is a long short-term memory (LSTM) model. The length of the preset time period is one day, and the historical time period is one day before the preset time period.

[0093] In step 302, for each target time, a Monte Carlo sampling model is used to obtain a plurality of demand prediction data corresponding to the demand prediction initial data.

[0094] Optionally, the demand prediction initial data is predicted according to a demand, an interval to which the demand prediction data belongs is determined, and a plurality of data is determined from the interval as the demand prediction data by using a Monte Carlo sampling model.

[0095] The embodiment acquires a plurality of demand prediction data corresponding to the demand prediction initial data by using the Monte Carlo sampling model, determines a plurality of possible demand prediction data by using a statistical analysis method, and improves the accuracy of the dispatching method.

[0096] In one embodiment, as shown in Figure 4 based on the embodiment shown in Figure 3 The embodiment relates to an implementation process of acquiring a plurality of demand prediction data corresponding to the demand prediction initial data by using the Monte Carlo sampling model in step 302, and includes steps 401 and 402.

[0097] In step 401, a normal distribution function satisfied by the demand prediction initial data is acquired.

[0098] Optionally, a formula of the normal distribution function satisfied by the demand prediction initial data is as follows:

[0099]

[0100]

[0101]

[0102]

[0103] In the formula, μ EL and σ EL respectively represent a mean value and a standard deviation of a normal distribution satisfied by the demand prediction initial value of the electric load power μ CL and σ CL respectively represent a mean value and a standard deviation of a normal distribution satisfied by the demand prediction initial value of the thermal load power μ 01 and σ 01 respectively represent a mean value and a standard deviation of a normal distribution satisfied by the demand prediction initial value of the transfer time of the mobile energy storage system from the power distribution network to the corresponding position of the remote village μ 10 and σ 10 respectively represent a mean value and a standard deviation of a normal distribution satisfied by the demand prediction initial value of the transfer time of the mobile energy storage system from the remote village to the corresponding position of the power distribution network.

[0104] ​At step 402, the normal distribution function and the demand prediction initial data are input into the Monte Carlo sampling model to obtain a plurality of demand prediction data corresponding to the demand prediction initial data.

[0105] Optionally, according to the normal distribution function and the demand prediction initial data, the Monte Carlo sampling model is used to generate a plurality of demand prediction data for each demand prediction initial data. The number of the demand prediction data can be set according to actual conditions. That is, a plurality of scenarios are generated by using the Monte Carlo sampling method to simulate the demand prediction data that can occur.

[0106] Suppose that the number of data set is S, that is, S scenarios are generated by using the Monte Carlo sampling method, and the initial value of the power demand prediction of the electrical load is The obtained power demand prediction value of the electrical load is The initial value of the power demand prediction of the thermal load is The obtained power demand prediction value of the thermal load is The initial value of the position transfer time prediction of the mobile energy storage system from the distribution network to the corresponding position of the remote village is The obtained position transfer time prediction value is The initial value of the position transfer time prediction of the mobile energy storage system from the remote village to the corresponding position of the distribution network is The obtained position transfer time prediction value is

[0107] In this embodiment, according to the Monte Carlo sampling model and the distribution function satisfied by the demand prediction initial data, a plurality of demand prediction data corresponding to the demand prediction initial data are obtained, and the statistical analysis method is used to determine a plurality of possible demand prediction data, thereby improving the accuracy of the dispatching method.

[0108] In one embodiment, the mobile energy storage system includes a mobile electrical energy storage subsystem and a mobile phase change energy storage subsystem, and the mobile energy storage system is based on Figure 1 In the embodiment shown, the embodiment relates to the constraint conditions of the mobile energy storage system obtained at step 102, which includes:

[0109] The power supply operation constraint condition of the mobile electrical energy storage subsystem, the heat supply operation constraint condition of the mobile phase change energy storage subsystem, and the electrical-thermal conversion constraint condition of the mobile electrical energy storage subsystem and the mobile phase change energy storage subsystem are obtained.

[0110] Optionally, the mobile electrical energy storage subsystem is charged at the power distribution network and then travels to the remote village to discharge. The power supply operation constraints include: the spatial location uniqueness constraint of the mobile electrical energy storage subsystem (formula (1) below), the spatial transfer continuity constraint of the mobile electrical energy storage subsystem (formula (2)-(3) below), the travel time constraint of the mobile electrical energy storage subsystem (formula (4) below), the charging power constraint at the power distribution network node (formula (5) below), the discharging constraint at the remote village (formula (6) below), and the energy storage state constraint of the mobile electrical energy storage subsystem (formula (7)-(8) below), and the specific expressions are as follows:

[0111]

[0112]

[0113]

[0114]

[0115]

[0116]

[0117]

[0118]

[0119] wherein the Boolean variable equals 1 / 0 respectively indicating that the mobile electrical energy storage subsystem is / is not on the road from i to j at the tth moment under scenario s, and respectively represent the rated charging power and the rated discharging power of the mobile electrical energy storage subsystem, and equal to 1000 kW; and represent the actual discharging power and the actual charging power of the mobile electrical energy storage subsystem at the tth moment under scenario s; represents the rated energy storage capacity of the mobile electrical energy storage subsystem, and equals 5000 kWh; η P represents the charging and discharging efficiency, and equals 0.9; and respectively represent the actual energy storage state, the minimum energy storage state (taking the value of 0.1) and the maximum energy storage state (taking the value of 0.9) of the mobile electrical energy storage subsystem at the tth moment under scenario s.

[0120] The mobile phase change thermal storage subsystem increases the heat storage at the power distribution network and then releases the heat at the remote village. The heat supply operation constraints include: the spatial position uniqueness constraint condition of the mobile phase change thermal storage subsystem (equation (9) below), the spatial transfer continuity constraint condition of the mobile phase change thermal storage subsystem (equations (10)-(11) below), the travel time constraint condition of the mobile phase change thermal storage subsystem (equation (12) below), the heat storage power constraint condition at the power distribution network node (equation (13) below), the heat release power constraint condition at the remote village (equation (14) below), and the heat storage state constraint condition of the mobile phase change thermal storage subsystem (equations (15)-(16) below), and the specific expressions are as follows:

[0121]

[0122]

[0123] and i≠j (11)

[0124]

[0125]

[0126]

[0127]

[0128]

[0129] wherein the Boolean variable equals 1 / 0 respectively indicates that the mobile phase change thermal storage subsystem is on / off the road from site i to j at the tth moment under scenario s, and respectively represent the rated heat storage power and the rated heat release power of the mobile phase change thermal storage subsystem; and represent the actual heat storage power and the actual heat release power of the mobile phase change thermal storage subsystem at the tth moment under scenario s; represents the rated heat storage capacity of the mobile phase change thermal storage subsystem; η Q represents the charging and discharging efficiency; and respectively represent the actual heat storage state, the minimum heat storage state and the maximum heat storage state of the mobile phase change thermal storage subsystem at the tth moment under scenario s.

[0130] The heat storage of the mobile phase change thermal storage system is derived from the conversion of electricity, and the corresponding electrical-thermal conversion constraint condition of the mobile phase change thermal storage subsystem is as follows:

[0131]

[0132]

[0133] wherein, and η M respectively represent the actual working power and the electric-thermal conversion efficiency of the heat pump in the mobile phase change energy storage system at time t in scenario s; represents the maximum power (1400 kW) that the line can allow to inject at time t in scenario s; represents the actual discharging power of the mobile electric energy storage subsystem at time t in scenario s.

[0134] The embodiment realizes the spatial flexible movement and the energy flexible charging and discharging of the mobile energy storage system by obtaining the power supply operation constraint condition corresponding to the mobile electric energy storage subsystem, the heat supply operation constraint condition corresponding to the mobile phase change energy storage subsystem, and the electric-thermal conversion constraint condition corresponding to the mobile electric energy storage subsystem and the mobile phase change energy storage subsystem, which is closer to the operation condition of the mobile energy storage system, and further improves the reliability of the scheduling method.

[0135] In one embodiment, the scheduling model includes a cost control condition, based on Figure 1 As shown in the embodiment, the scheduling method of the mobile energy storage system further includes:

[0136] If the demand prediction data and the constraint condition both satisfy the cost control condition, it is determined that the demand prediction data and the constraint condition both satisfy the scheduling target.

[0137] Optionally, the cost control condition is the minimization of the energy supply cost in a preset time period. Specifically, the expression of the scheduling model is as follows:

[0138]

[0139]

[0140]

[0141]

[0142]

[0143]

[0144]

[0145] wherein, represents the electricity price of the power distribution network at the tth time; p P represents the hourly driving cost of the mobile electric energy storage, which is set to 150 yuan; p Qp represents the hourly travel cost of the mobile phase change energy storage system, equal to 120 yuan; p G is the power generation cost per unit power of the diesel engine, which is 2 yuan / kWh; represents the power generation of the diesel engine at the tth moment in the scene s.

[0146] Optionally, according to the refined scheduling step, the Gurobi solver is called to solve the calling model. In order to refine the scheduling step of the scheduling model, the initial scheduling period, i.e. the time length of the preset time period, is divided into multiple time periods according to the preset scheduling step (for example, 10 minutes), and the scheduling model is executed according to the preset scheduling step. After refining the scheduling step, the values of the corresponding demand prediction data are:

[0147]

[0148] For example, when the scheduling step is per hour, the corresponding values are obtained Then, after taking 10 minutes as the scheduling step, the corresponding values are

[0149] This embodiment determines whether the demand prediction data and the constraint condition meet the scheduling target by determining whether the demand prediction data and the constraint condition meet the cost control condition, realizes the cost control of the mobile energy storage system, and reduces the diesel engine power generation and the operation cost of the mobile energy storage system.

[0150] In the examples of the present application, as shown in Figure 5 a scheduling method of a mobile energy storage system is provided, which comprises the following steps:

[0151] Step 501, obtaining historical demand data corresponding to a plurality of historical moments in a historical period.

[0152] The historical demand data includes historical electric load power demand values, historical thermal load power demand values, and historical position transfer times of the mobile energy storage system.

[0153] Step 502, inputting the historical demand data corresponding to each historical moment into a prediction model to obtain demand prediction initial data corresponding to each target moment.

[0154] The prediction model is a long short-term memory (LSTM) model.

[0155] Step 503, for each target moment, a Monte Carlo sampling model is used to obtain a plurality of demand prediction data corresponding to the demand prediction initial data.

[0156] The demand prediction data includes electric load power demand prediction values, thermal load power demand prediction values, and position transfer time prediction values of the mobile energy storage system.

[0157] Step 504: Obtain the power supply operation constraints of the mobile electric energy storage subsystem, the heating operation constraints of the mobile phase change energy storage subsystem, and the electrothermal conversion constraints of the mobile electric energy storage subsystem and the mobile phase change energy storage subsystem.

[0158] Step 505: Obtain the scheduling model corresponding to the mobile energy storage system, which includes cost control conditions.

[0159] This scheduling model is used to characterize the scheduling objectives of mobile energy storage systems within a preset time period.

[0160] Step 506: If both the demand forecast data and the constraints meet the cost control conditions, then it is determined that both the demand forecast data and the constraints meet the scheduling objective.

[0161] Step 507: According to the scheduling step size of the refined scheduling model, call the Gurobi solver to solve the calling model.

[0162] Step 508: If both the demand forecast data and the constraints meet the scheduling objective, determine the supply data corresponding to the demand forecast data based on the demand forecast data and the scheduling model.

[0163] This embodiment realizes the joint scheduling of power supply and heating of mobile energy storage system. When determining the supply data corresponding to the final demand forecast data, the location transfer time prediction value of mobile energy storage system is also used. It fully considers the spatial transfer uncertainty of mobile energy storage system, realizes the flexible spatial movement and flexible energy charging and discharging of mobile energy storage system, is closer to the operation of mobile energy storage system, further improves the reliability of scheduling method, and reduces diesel generator power generation and operating costs.

[0164] The following are experimental results verifying the scheduling method of the mobile energy storage system according to the embodiments of this application.

[0165] Here, the preset time period is 24 hours, and the prediction model is a Long Short-Term Memory (LSTM) network model. The electricity price situation of the distribution network at different times is as follows: Figure 6 As shown. The Gurobi solver was used to solve the model. The energy supply cost of the mobile energy storage system was 6472 yuan. The distribution of supply data at various times is shown in [the image / description]. Figures 7-9 .in, Figure 7 The actual spatial location of the mobile energy storage system. Figure 8 This describes the energy storage status of the mobile electric energy storage subsystem and the thermal storage status of the mobile phase change energy storage subsystem. Figure 9 This includes the actual power of the mobile electric energy storage subsystem, the diesel engine power, and the power of the mobile phase change energy storage subsystem.

[0166] It should be understood that although each step in the flowchart involved in the embodiments described above is shown in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in the embodiments described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be alternately or alternately executed with at least part of other steps or steps or stages in other steps.

[0167] Based on the same inventive concept, the embodiments of the present application also provide a scheduling device in a mobile energy storage system for implementing the scheduling method in the mobile energy storage system described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more scheduling device embodiments in a mobile energy storage system provided below can refer to the limitations of the scheduling method in a mobile energy storage system described above, which will not be repeated here.

[0168] In one embodiment, as shown in Figure 10 A scheduling device in a mobile energy storage system is provided, comprising: an acquisition module, a scheduling module, and a determination module, wherein:

[0169] The acquisition module is configured to acquire demand prediction data corresponding to a plurality of target time points in a preset time period, wherein the demand prediction data comprises an electric load power demand prediction value, a thermal load power demand prediction value, and a position transfer time prediction value of the mobile energy storage system.

[0170] The scheduling module is configured to acquire constraint conditions and a scheduling model corresponding to the mobile energy storage system, wherein the constraint conditions comprise at least power supply operation constraint conditions and heat supply operation constraint conditions of the mobile energy storage system, and the scheduling model is used to represent a scheduling target of the mobile energy storage system in the preset time period.

[0171] The determination module is configured to determine supply data corresponding to the demand prediction data according to the demand prediction data and the scheduling model in a case where the demand prediction data and the constraint conditions satisfy the scheduling target.

[0172] In one embodiment, the acquisition module is specifically configured to:

[0173] obtain historical demand data corresponding to each historical moment in the historical period, the historical demand data including a historical electric load power demand value, a historical thermal load power demand value, and a historical position transfer time of the mobile energy storage system;

[0174] obtain demand prediction data corresponding to each target moment according to the historical demand data corresponding to each historical moment and the prediction model.

[0175] In an embodiment, the determining module is specifically configured to:

[0176] input the historical demand data corresponding to each historical moment into the prediction model to obtain demand prediction initial data corresponding to each target moment;

[0177] for each target moment, obtain a plurality of demand prediction data corresponding to the demand prediction initial data by using a Monte Carlo sampling model.

[0178] In an embodiment, the determining module is further specifically configured to:

[0179] obtain a normal distribution function satisfied by the demand prediction initial data;

[0180] input the normal distribution function and the demand prediction initial data into the Monte Carlo sampling model to obtain the plurality of demand prediction data corresponding to the demand prediction initial data.

[0181] In an embodiment, the scheduling model includes a cost control condition, and the apparatus further includes:

[0182] if the demand prediction data and the constraint condition both satisfy the cost control condition, it is determined that the demand prediction data and the constraint condition both satisfy the scheduling target.

[0183] In an embodiment, the mobile energy storage system includes a mobile electric energy storage subsystem and a mobile phase change energy storage subsystem, and the constraint condition corresponding to the mobile energy storage system is obtained, including:

[0184] obtain a power supply operation constraint condition corresponding to the mobile electric energy storage subsystem, a heat supply operation constraint condition corresponding to the mobile phase change energy storage subsystem, and an electric-thermal conversion constraint condition corresponding to the mobile electric energy storage subsystem and the mobile phase change energy storage subsystem.

[0185] Each module in the scheduling apparatus of the mobile energy storage system described above can be realized in whole or in part by software, hardware, and a combination thereof. Each module described above can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform operations corresponding to each module.

[0186] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 11 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for scheduling a mobile energy storage system. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0187] Those skilled in the art will understand that Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0188] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0189] Obtain demand forecast data corresponding to multiple target times within a preset time period. The demand forecast data includes the predicted values ​​of electrical load power demand, thermal load power demand, and the predicted value of the location transfer time of the mobile energy storage system.

[0190] Obtain the constraints and scheduling model corresponding to the mobile energy storage system. The constraints include at least the power supply operation constraints and heating operation constraints of the mobile energy storage system. The scheduling model is used to characterize the scheduling target of the mobile energy storage system within a preset time period.

[0191] If both the demand forecast data and the constraints meet the scheduling objective, the supply data corresponding to the demand forecast data is determined based on the demand forecast data and the scheduling model.

[0192] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0193] obtain historical demand data corresponding to each historical time in the historical period, the historical demand data including a historical electric load power demand value, a historical thermal load power demand value, and a historical position transfer time of the mobile energy storage system; and obtain demand prediction data corresponding to each target time according to the historical demand data corresponding to each historical time and the prediction model.

[0194] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0195] input the historical demand data corresponding to each historical time into the prediction model to obtain demand prediction initial data corresponding to each target time; and for each target time, obtain multiple demand prediction data corresponding to the demand prediction initial data by using a Monte Carlo sampling model.

[0196] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0197] obtain a normal distribution function satisfied by the demand prediction initial data; and input the normal distribution function and the demand prediction initial data into the Monte Carlo sampling model to obtain the multiple demand prediction data corresponding to the demand prediction initial data.

[0198] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0199] if the demand prediction data and the constraint condition both satisfy the cost control condition, it is determined that the demand prediction data and the constraint condition both satisfy the scheduling target.

[0200] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0201] obtain a power supply operation constraint condition corresponding to the mobile electric energy storage subsystem, a heat supply operation constraint condition corresponding to the mobile phase change energy storage subsystem, and an electric-thermal conversion constraint condition corresponding to the mobile electric energy storage subsystem and the mobile phase change energy storage subsystem.

[0202] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program, when executed by a processor, implements the following steps:

[0203] obtain demand prediction data corresponding to each target time in a preset time period, the demand prediction data including an electric load power demand prediction value, a thermal load power demand prediction value, and a position transfer time prediction value of the mobile energy storage system;

[0204] obtain constraint conditions and a scheduling model corresponding to the mobile energy storage system, the constraint conditions at least including power supply operation constraint conditions and heat supply operation constraint conditions of the mobile energy storage system, and the scheduling model being used to represent a scheduling target of the mobile energy storage system in a preset time period;

[0205] In a case where the demand prediction data and the constraint conditions both satisfy the scheduling target, supply data corresponding to the demand prediction data is determined according to the demand prediction data and the scheduling model.

[0206] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0207] obtain historical demand data corresponding to a plurality of historical time points in a historical period, the historical demand data including historical electrical load power demand values, historical thermal load power demand values, and historical position transfer times of the mobile energy storage system; and obtain the demand prediction data corresponding to each target time point according to the historical demand data corresponding to each historical time point and the prediction model.

[0208] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0209] input the historical demand data corresponding to each historical time point into the prediction model to obtain demand prediction initial data corresponding to each target time point; and for each target time point, obtain a plurality of demand prediction data corresponding to the demand prediction initial data by using a Monte Carlo sampling model.

[0210] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0211] obtain a normal distribution function satisfied by the demand prediction initial data; and input the normal distribution function and the demand prediction initial data into the Monte Carlo sampling model to obtain the plurality of demand prediction data corresponding to the demand prediction initial data.

[0212] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0213] If the demand prediction data and the constraint conditions both satisfy the cost control condition, it is determined that the demand prediction data and the constraint conditions both satisfy the scheduling target.

[0214] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0215] obtain power supply operation constraint conditions corresponding to the mobile electrical energy storage subsystem, heat supply operation constraint conditions corresponding to the mobile phase change energy storage subsystem, and electrical-thermal conversion constraint conditions corresponding to the mobile electrical energy storage subsystem and the mobile phase change energy storage subsystem.

[0216] In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the following steps:

[0217] obtaining demand prediction data corresponding to each target time in the preset time period, the demand prediction data comprising an electric load power demand prediction value, a thermal load power demand prediction value, and a mobile energy storage system position transfer time prediction value;

[0218] obtaining a constraint condition and a scheduling model corresponding to the mobile energy storage system, the constraint condition comprising at least a power supply operation constraint condition and a heat supply operation constraint condition of the mobile energy storage system, and the scheduling model being used to represent a scheduling target of the mobile energy storage system in the preset time period;

[0219] in a case where the demand prediction data and the constraint condition both satisfy the scheduling target, determining supply data corresponding to the demand prediction data according to the demand prediction data and the scheduling model.

[0220] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0221] obtaining historical demand data corresponding to each historical time in a historical time period, the historical demand data comprising a historical electric load power demand value, a historical thermal load power demand value, and a historical position transfer time of the mobile energy storage system; and obtaining the demand prediction data corresponding to each target time according to the historical demand data corresponding to each historical time and a prediction model.

[0222] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0223] inputting the historical demand data corresponding to each historical time into the prediction model to obtain demand prediction initial data corresponding to each target time; and for each target time, obtaining a plurality of demand prediction data corresponding to the demand prediction initial data by using a Monte Carlo sampling model.

[0224] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0225] obtaining a normal distribution function satisfied by the demand prediction initial data; and inputting the normal distribution function and the demand prediction initial data into the Monte Carlo sampling model to obtain the plurality of demand prediction data corresponding to the demand prediction initial data.

[0226] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0227] if the demand prediction data and the constraint condition both satisfy a cost control condition, determining that the demand prediction data and the constraint condition both satisfy the scheduling target.

[0228] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0229] The power supply operation constraint condition corresponding to the mobile electric energy storage subsystem, the heat supply operation constraint condition corresponding to the mobile phase change energy storage subsystem, and the electric-thermal conversion constraint condition corresponding to the mobile electric energy storage subsystem and the mobile phase change energy storage subsystem are obtained.

[0230] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware. 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-mentioned embodiments. Any reference to a memory, database or other medium used in the embodiments provided in the present application can include at least one of a non-volatile and volatile memory. The non-volatile memory can include a read-only memory (ROM), a magnetic tape, a floppy disk, a flash memory, an optical storage, a high-density embedded non-volatile memory, a resistive memory (ReRAM), a magnetoresistive random access memory (MRAM), a ferroelectric random access memory (FRAM), a phase change memory (PCM), a graphene memory, etc. The volatile memory can include a random access memory (RAM) or an external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as a static random access memory (SRAM) or a dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a blockchain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0231] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, however, as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present disclosure.

[0232] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A scheduling method for a mobile energy storage system, characterized in that, The method includes: Obtain demand forecast data corresponding to multiple target times within a preset time period. The demand forecast data includes predicted values ​​for electrical load power demand, predicted values ​​for thermal load power demand, and predicted values ​​for the location transfer time of the mobile energy storage system. The constraints and scheduling model corresponding to the mobile energy storage system are obtained. The mobile energy storage system includes a mobile electric energy storage subsystem and a mobile phase change energy storage subsystem. The constraints include power supply operation constraints corresponding to the mobile electric energy storage subsystem, heating operation constraints corresponding to the mobile phase change energy storage subsystem, and electrothermal conversion constraints corresponding to the mobile electric energy storage subsystem and the mobile phase change energy storage subsystem. The scheduling model is used to characterize the scheduling target of the mobile energy storage system within the preset time period. The power supply operation constraints include the spatial location uniqueness constraint of the mobile electric energy storage subsystem, the spatial transfer continuity constraint of the mobile electric energy storage subsystem, the travel time constraint of the mobile electric energy storage subsystem, the charging power constraint at the distribution network node, the discharge constraint in remote villages, and the energy storage state constraint of the mobile electric energy storage subsystem. The power supply operation constraints are as follows: Boolean variables The values ​​1 and 0 respectively indicate that the mobile energy storage subsystem described in scenario s is on / off the road from location i to j at time t. and These represent the rated charging power and rated discharging power of the mobile energy storage subsystem, respectively. and This represents the actual discharge power and actual charging power of the mobile energy storage subsystem described in scenario s at time t. This indicates the rated energy storage capacity of the mobile energy storage subsystem; Indicates charge / discharge efficiency; , and These represent the actual energy storage state, minimum energy storage state, and maximum energy storage state of the mobile energy storage subsystem at time t in scenario s, respectively. The heating operation constraints include the spatial location uniqueness constraint of the mobile phase change energy storage subsystem, the spatial transfer continuity constraint of the mobile phase change energy storage subsystem, the travel time constraint of the mobile phase change energy storage subsystem, the heat storage power constraint at the distribution network node, the heat release power constraint in remote villages, and the heat storage state constraint of the mobile phase change energy storage subsystem. The heating operation constraints are as follows: Boolean variables The values ​​1 and 0 respectively indicate that the mobile phase change energy storage subsystem described in scenario s is on / off the road from location i to j at time t. and These represent the rated thermal storage power and rated thermal release power of the mobile phase change energy storage subsystem, respectively. and This represents the actual heat storage power and actual heat release power of the mobile phase change energy storage subsystem at time t under scenario s; This indicates the rated thermal storage capacity of the mobile phase change energy storage subsystem; Indicates charge / discharge efficiency; , and These represent the actual thermal storage state, minimum thermal storage state, and maximum thermal storage state of the mobile phase change energy storage subsystem at time t in scenario s, respectively. The electrothermal conversion constraints are as follows: ， ， in, and These represent the actual operating power and electrothermal conversion efficiency of the heat pump in the mobile phase change energy storage subsystem at time t in scenario s, respectively. This represents the maximum power that the line can be injected at time t under scenario s; This represents the actual discharge power of the mobile energy storage subsystem at time t under scenario s; The scheduling model includes cost control conditions; if both the demand forecast data and the constraints satisfy the cost control conditions, then it is determined that both the demand forecast data and the constraints satisfy the scheduling objective; the expression of the scheduling model is as follows: s.t. = ; = ； in, This represents the electricity price at time t in the distribution network; This indicates the hourly driving cost of the mobile energy storage subsystem. This indicates the hourly driving cost of the mobile phase change energy storage subsystem. It is the unit power generation cost of a diesel engine; This represents the power output of the diesel generator at time t in scenario s; If both the demand forecast data and the constraints satisfy the scheduling objective, the supply data corresponding to the demand forecast data is determined based on the demand forecast data and the scheduling model. The step of obtaining demand prediction data corresponding to multiple target times within a preset time period includes: Acquire historical demand data corresponding to multiple historical moments within a historical period. The historical demand data includes historical electrical load power demand values, historical thermal load power demand values, and the historical location transfer time of the mobile energy storage system. Based on the historical demand data and prediction models corresponding to each historical moment, the demand prediction data corresponding to each target moment is obtained.

2. The method according to claim 1, characterized in that, The prediction model includes at least one of the following: Long Short-Term Memory Network (LSTM) model, Temporal Convolutional Network (TCN) model, and Temporal Graph Network (TGNs) model.

3. The method according to claim 2, characterized in that, The step of obtaining demand prediction data corresponding to each target time based on historical demand data and prediction models corresponding to each historical time includes: The historical demand data corresponding to each of the historical moments are input into the prediction model to obtain the initial demand prediction data corresponding to each of the target moments; For each target time point, a Monte Carlo sampling model is used to obtain multiple demand forecast data corresponding to the initial demand forecast data.

4. The method according to claim 3, characterized in that, The Monte Carlo sampling model is used to obtain multiple demand forecast data corresponding to the initial demand forecast data, including: Obtain the normal distribution function satisfied by the initial data for demand forecasting; The normal distribution function and the initial demand forecast data are input into the Monte Carlo sampling model to obtain multiple demand forecast data corresponding to the initial demand forecast data.

5. The method according to claim 1, characterized in that, The predicted location transfer time of the mobile energy storage system is the travel time required to travel from the starting station to the target station at the target time.

6. A dispatching device for a mobile energy storage system, characterized in that, The apparatus is used to perform the steps of the method according to any one of claims 1 to 5, the apparatus comprising: The acquisition module is used to acquire demand forecast data corresponding to multiple target times within a preset time period. The demand forecast data includes predicted values ​​of electrical load power demand, predicted values ​​of thermal load power demand, and predicted values ​​of location transfer time of mobile energy storage systems. The scheduling module is used to obtain the constraints and scheduling model corresponding to the mobile energy storage system. The mobile energy storage system includes a mobile electric energy storage subsystem and a mobile phase change energy storage subsystem. The constraints include power supply operation constraints corresponding to the mobile electric energy storage subsystem, heating operation constraints corresponding to the mobile phase change energy storage subsystem, and electrothermal conversion constraints corresponding to the mobile electric energy storage subsystem and the mobile phase change energy storage subsystem. The scheduling model is used to characterize the scheduling target of the mobile energy storage system within a preset time period. The power supply operation constraints include the spatial location uniqueness constraint of the mobile electric energy storage subsystem, the spatial transfer continuity constraint of the mobile electric energy storage subsystem, and the movement constraint of the mobile electric energy storage subsystem. The scheduling model includes constraints on driving time, charging power at distribution network nodes, discharging power in remote villages, and energy storage status of the mobile energy storage subsystem. The heating operation constraints include the spatial location uniqueness constraint, spatial transfer continuity constraint, driving time constraint, heat storage power constraint at distribution network nodes, heat release power constraint in remote villages, and heat storage status constraint. The scheduling model includes cost control conditions. If both the demand forecast data and the constraints satisfy the cost control conditions, then it is determined that both the demand forecast data and the constraints satisfy the scheduling objective. The determination module is used to determine the supply data corresponding to the demand forecast data based on the demand forecast data and the scheduling model, provided that both the demand forecast data and the constraints satisfy the scheduling objective. The acquisition module is specifically used to acquire historical demand data corresponding to multiple historical moments within a historical period. The historical demand data includes historical electrical load power demand values, historical thermal load power demand values, and the historical location transfer time of the mobile energy storage system. Based on the historical demand data corresponding to each historical moment and the prediction model, the demand prediction data corresponding to each target moment is obtained.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images