Method and related device for optimizing and scheduling user-side resources considering virtual energy storage

Abstract

The present application provides a method and related device for optimizing the scheduling of user-side resources considering virtual energy storage. The method includes: obtaining the output data of the distribution network in the target area within a preset time period, obtaining the first electricity price, and determining the power consumption status data set and operation status data set of the user-side resources according to the first electricity price. Determining the virtual energy storage model according to the operation status data set, determining the power generation output model according to the power consumption status data set and the first electricity price, and determining the first output model according to the new energy output data; determining the second output model according to the energy storage system output data, constructing a user-side resource collaborative scheduling model based on the virtual energy storage model, the power generation output model, the first output model and the second output model, and solving the model through a preset particle swarm optimization algorithm to obtain a target calculation result, where the target calculation result is used to configure the user-side resource collaborative scheduling model. By executing the method for appropriate optimization scheduling, power loss can be reduced.

Description

Technical Field

[0001] This application relates to the technical field of power systems, and in particular to a method and related device for optimizing the scheduling of user-side resources considering virtual energy storage. Background Art

[0002] In a power system, an optimization scheduling model plays an important role, and it can relatively flexibly schedule resources such as the energy system, energy storage system, and virtual energy storage system in the power system. However, existing optimization scheduling models are insufficient in exploring the flexible scheduling potential of various types of energy-consuming resources on the user side. Although the flexible resource models show a diverse trend, a unified modeling method has not yet been formed, which restricts the effective integration and scheduling of these resources in the power system and fails to fully utilize the user-side flexible resources. In addition, the existing life loss model of the energy storage system cannot scientifically and reasonably estimate the loss cost, thus affecting the economic benefit analysis and optimization scheduling of the energy storage system in the power system.

[0003] Therefore, in the power system, the problem of how to reduce power loss through appropriate optimization scheduling urgently needs to be solved. Summary of the Invention

[0004] Embodiments of this application provide a method and related device for optimizing the scheduling of user-side resources considering virtual energy storage, which realizes the problem of reducing power loss in the power system through appropriate optimization scheduling strategies.

[0005] In a first aspect, embodiments of this application provide a method for optimizing the scheduling of user-side resources considering virtual energy storage, which is applied to a server. The method includes:

[0006] Obtain the output data of the distribution network in the target area within a preset time period; the output data includes: new energy output data and energy storage system output data;

[0007] Obtain a first electricity price, and determine the electricity consumption status data set and operation status data set of user-side resources according to the first electricity price;

[0008] Determine a virtual energy storage model based on a preset first constraint condition and the operation status data set;

[0009] Determine a distributed power generation output model based on a preset second constraint condition, the electricity consumption status data set, and the first electricity price to obtain a power output model;

[0010] Determine a first output model according to a preset third constraint condition and the new energy output data;

[0011] Determine a second output model according to a preset fourth constraint condition and the energy storage system output data;

[0012] Construct a collaborative scheduling model for user-side resources based on the virtual energy storage model, the power output model, the first output model, and the second output model;

[0013] Solve the collaborative scheduling model for user-side resources through a preset particle swarm optimization algorithm to obtain a target calculation result, where the target calculation result is used to configure the collaborative scheduling model for user-side resources.

[0014] In a second aspect, an embodiment of the present application provides a user-side resource optimal scheduling device considering virtual energy storage, which is applied to a server. The device includes:

[0015] An acquisition unit for acquiring the power output data of the distribution network in a target area within a preset time period; the power output data includes: new energy power output data and energy storage system power output data; acquiring a first electricity price, and determining the electricity consumption status data set and the operation status data set of user-side resources according to the first electricity price;

[0016] A determination unit for determining a virtual energy storage model based on a preset first constraint condition and the operation status data set; determining a distributed power source output model based on a preset second constraint condition, the electricity consumption status data set, and the first electricity price to obtain a power output model; determining a first output model according to a preset third constraint condition and the new energy power output data; determining a second output model according to a preset fourth constraint condition and the energy storage system power output data;

[0017] A control unit for constructing a collaborative scheduling model for user-side resources based on the virtual energy storage model, the power output model, the first output model, and the second output model;

[0018] A calculation unit for solving the collaborative scheduling model for user-side resources through a preset particle swarm optimization algorithm to obtain a target calculation result, where the target calculation result is used to configure the collaborative scheduling model for user-side resources.

[0019] In a third aspect, an embodiment of the present application provides a server, including a processor, a memory, a communication interface, and one or more programs. Among them, the above one or more programs are stored in the above memory and are configured to be executed by the above processor. The above programs include instructions for executing the steps in any method of the first aspect of the embodiments of the present application.

[0020] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium. Among them, the above computer-readable storage medium stores a computer program for electronic data exchange. Among them, the above computer program enables a computer to execute some or all of the steps described in any method of the first aspect of the embodiments of the present application.

[0021] Fifth aspect, an embodiment of the present application provides a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in any of the methods in the first aspect of the embodiments of the present application. The computer program product can be a software installation package.

[0022] A method for optimizing the scheduling of user-side resources considering virtual energy storage described in the present application is applied to a server. By obtaining the output data of the distribution network in the target area within a preset time period, where the output data includes: new energy output data and energy storage system output data; obtaining the first electricity price, and determining the power consumption status data set and operation status data set of the user-side resources according to the first electricity price; then, determining a virtual energy storage model based on a preset first constraint condition and the operation status data set; determining a distributed power generation output model based on a preset second constraint condition, the power consumption status data set, and the first electricity price to obtain a power output model; determining a first output model according to a preset third constraint condition and the new energy output data; determining a second output model according to a preset fourth constraint condition and the energy storage system output data; then, constructing a user-side resource collaborative scheduling model based on the virtual energy storage model, the power output model, the first output model, and the second output model; finally, solving the user-side resource collaborative scheduling model through a preset particle swarm algorithm to obtain a target calculation result, and the target calculation result is used to configure the user-side resource collaborative scheduling model. By implementing the embodiments of the present application, various energy-consuming resources on the user side are fully exploited, effectively integrated, and scheduled, so that the user-side resources can be fully utilized, thereby reducing the problem of power loss. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0024] Figure 1 It is a system architecture diagram of a method for optimizing the scheduling of user-side resources considering virtual energy storage provided by an embodiment of the present application;

[0025] Figure 2 It is a schematic structural diagram of a server provided by an embodiment of the present application;

[0026] Figure 3 It is a flowchart of a method for optimizing the scheduling of user-side resources considering virtual energy storage provided by an embodiment of the present application;

[0027] Figure 4 It is a schematic flowchart of another method for optimizing the scheduling of user-side resources considering virtual energy storage provided by an embodiment of the present application;

[0028] Figure 5 It is a schematic flowchart of constructing an optimization scheduling model for user-side resources considering virtual energy storage provided by an embodiment of the present application;

[0029] Figure 6 It is a schematic flowchart of the execution of a method for optimizing the scheduling of user-side resources considering virtual energy storage provided by an embodiment of the present application;

[0030] Figure 7 It is a timing diagram of a method for optimizing the scheduling of user-side resources considering virtual energy storage provided by an embodiment of the present application;

[0031] Figure 8 It is a block diagram of the functional units of a device for optimizing the scheduling of user-side resources considering virtual energy storage provided by an embodiment of the present application. Detailed implementation manners

[0032] In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present application.

[0033] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally further include steps or units not listed, or may optionally further include other steps or units inherent to these processes, methods, products, or devices.

[0034] The expression "at least one (item)" or a similar expression in the embodiments of the present application refers to any combination of these items, including any combination of single item (s) or plural item (s), which means one or more, and plural means two or more. For example, at least one (item) of a, b, or c can represent the following seven cases: a, b, c, a and b, a and c, b and c, a, b, and c. Each of a, b, and c can be an element or a set containing one or more elements.

[0035] In the embodiments of the present application, the "connection" mentioned refers to various connection methods such as direct connection or indirect connection to achieve communication between devices. The embodiments of the present application do not make any limitations on this.

[0036] Reference to "embodiments" in this document means that the specific features, structures, or characteristics described in connection with the embodiments may be included in at least one embodiment of the present application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.

[0037] First, the relevant terms involved in the present application are explained as follows:

[0038] User-side resources: User-side resources refer to power generation, power consumption, energy storage and other devices installed on the power consumption side, owned by users, and having the ability to interact with the distribution network. It can participate in the optimal dispatching or market response of the power system through technical means, thereby improving the energy utilization efficiency, reducing the power consumption cost and assisting the operation of the power grid.

[0039] Virtual energy storage: Virtual energy storage refers to the use of the regulation capabilities of independent control areas such as self-owned enterprises in the power grid, DC supporting power supplies, and user-side temperature control loads without adding new energy storage facilities, so as to simulate the charging and discharging behaviors of physical energy storage and provide low-cost and highly flexible regulation means for the power system.

[0040] Existing optimal dispatching models are insufficient in exploring the flexible dispatching potential of various types of energy resources on the user side. The flexibility resource models show a diverse trend, but no unified modeling method has been formed, which limits the effective integration and dispatching of these resources in the power system, resulting in the underutilization of user-side resources. Therefore, in the power system, there is a problem of poor optimal dispatching strategy for user-side resources, which in turn affects power loss.

[0041] To solve the above problems, an embodiment of the present application provides a method and related device for optimizing the scheduling of user-side resources considering virtual energy storage, which is applied to a server. By obtaining the output data of the distribution network in the target area within a preset time period; the output data includes: new energy output data and energy storage system output data; obtaining the first electricity price, and determining the electricity consumption status data set and operation status data set of the user-side resources according to the first electricity price; determining the virtual energy storage model based on the preset first constraint condition and the operation status data set; determining the distributed power output model based on the preset second constraint condition, the electricity consumption status data set and the first electricity price to obtain the power output model; determining the first output model according to the preset third constraint condition and the new energy output data; determining the second output model according to the preset fourth constraint condition and the energy storage system output data; constructing a user-side resource collaborative scheduling model based on the virtual energy storage model, the power output model, the first output model and the second output model; solving the user-side resource collaborative scheduling model through the preset particle swarm algorithm to obtain the target calculation result, and the target calculation result is used to configure the user-side resource collaborative scheduling model. In this way, various energy resources on the user side can be fully explored and effectively integrated and scheduled, so that the user-side resources can be fully utilized, thereby reducing power loss.

[0042] The following combines Figure 1 to illustrate the system architecture of a method for optimizing the scheduling of user-side resources considering virtual energy storage in an embodiment of the present application. Figure 1 FIG. is a system architecture diagram of a method for optimizing the scheduling of user-side resources considering virtual energy storage provided by an embodiment of the present application. The user-side resource collaborative scheduling system 100 considering virtual energy storage includes a user-side resource collaborative control platform 110 and a target distribution network 120. Among them, the user-side resource collaborative control platform 110 includes: a distributed power source 111, a virtual energy storage 112, an energy storage system 113, and a new energy system 114.

[0043] Among them, the target distribution network 120 can refer to the distribution network of a region, which can be distributed in rural areas or small and medium-sized cities, and is not limited here. The target distribution network 120 is used as a regional power hub to establish two-way power interaction and information transmission with the user-side resource collaborative control platform 110. On the one hand, the target distribution network 120 provides key information such as real-time electricity prices and grid load status to the user-side resource collaborative control platform 110, guiding user-side resources to participate in grid peak shaving and new energy consumption; on the other hand, it receives the electricity transmitted by the user-side resource collaborative control platform 110 to relieve the regional power supply pressure. In actual operation, the target distribution network 120 monitors the power supply and demand balance, and through the electricity price incentive mechanism, guides distributed power sources 111 and energy storage systems 113 to generate electricity or discharge electricity during power shortages, and coordinates with user-side resources to achieve power storage and consumption during new energy surpluses, improving the stability and economy of the power grid.

[0044] Among them, the user-side resource collaborative control platform 110 integrates and manages distributed power sources 111, virtual energy storage 112, energy storage systems 113, and new energy systems 114, and realizes resource collaborative control by constructing a unified optimal scheduling model. Among them, the distributed power source 111 can be small-scale thermal power generation or micro gas turbine power generation, etc., all of which have independent power generation capabilities and are not specifically limited here. The user-side resource collaborative control platform 110 fits its power generation efficiency and output through a mathematical model, and dynamically adjusts the power generation power according to the electricity price signal and power demand of the target distribution network 120, reducing the power generation cost and pollution emissions while meeting the electricity demand. The virtual energy storage 112 aggregates temperature-controlled loads (such as air conditioners and water heaters) to form an equivalent energy storage, uses the thermal inertia of the equipment to adjust the electricity consumption power without affecting the user's comfort, calculates the adjustable capacity and time period according to its thermal dynamic model, and incorporates it into the optimal scheduling to achieve low-cost flexible power adjustment and assist the grid in peak shaving and new energy consumption. The energy storage system 113, as a physical energy storage unit, has charge and discharge constraints and a life loss model. The user-side resource collaborative control platform 110 monitors its state of charge in real time, and formulates charge and discharge strategies according to the electricity price fluctuation and new energy output prediction, for example, charging at low valleys and discharging at peaks, to achieve electricity price arbitrage and suppress the fluctuation of new energy output. The new energy system 114 includes: separate power generation, hydroelectric power generation, or photovoltaic power generation, which is not limited here. Taking photovoltaic as an example, its output is intermittent. The user-side resource collaborative control platform 110 predicts the power generation curve through a prediction model, combines the grid consumption capacity, and coordinates with the virtual energy storage 112 and the energy storage system 113 to formulate a consumption strategy. When the power generation is excessive, the virtual energy storage is preferentially used to increase the load consumption, and the remaining power is stored by the energy storage system to reduce the light abandonment rate.

[0045] In a possible embodiment, when the user-side resource optimization scheduling system 100 considering virtual energy storage operates, the user-side resource collaborative regulation platform 110 communicates bidirectionally with the target distribution network 120. The user-side resource collaborative regulation platform 110 collects real-time resource data (such as distributed power generation efficiency, virtual energy storage temperature, battery health status of the energy storage system, new energy output prediction), constructs a mathematical model, and establishes a multi-objective optimization function. At the same time, an improved particle swarm algorithm is used for iterative optimization to generate an optimal scheduling strategy. Taking a rural distribution network as an example, at noon in summer, when there is an excess of photovoltaic power, the target distribution network 120 sends a consumption instruction. The platform calls the virtual energy storage 112 to adjust the power consumption of the temperature control equipment, controls the charging of the energy storage system 113, and starts the distributed power generation 111 to operate at low power for the remaining power. At night, when there is no photovoltaic output, the platform schedules the energy storage system 113 to discharge according to the electricity price to reduce the user's electricity purchase cost.

[0046] It can be seen that through the above system architecture of a user-side resource optimization scheduling method considering virtual energy storage, deep collaboration and refined regulation of user-side resources can be achieved, the new energy consumption level can be improved, the operation stability of the distribution network can be enhanced, and thus the power loss can be reduced.

[0047] The following combines Figure 2 to describe the server in the embodiments of the present application. Figure 2 is a schematic structural diagram of a server provided by an embodiment of the present application. As Figure 2 shown, the server 200 includes one or more processors 210, a memory 220, a communication interface 230, and one or more programs 221. The processor 210 is communicatively connected to the memory 220 and the communication interface 230 through an internal communication bus.

[0048] Among them, the processor 210 may be a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, units, and circuits described in conjunction with the disclosure of the present application. The processor may also be a combination that realizes computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and so on. The communication unit may be a communication interface, a transceiver, a transceiver circuit, etc., and the storage unit may be a memory.

[0049] Among them, the memory 220 can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0050] Among them, the one or more programs 221 are stored in the above-mentioned memory 220 and are configured to be executed by the above-mentioned processor 210. The one or more programs 221 include instructions for performing any step in the following embodiments of a data processing method.

[0051] It can be understood that the server 200 may include more or fewer structural elements than those in the above structural block diagram. For example, it includes a power module, physical buttons, a Wi-Fi module, a speaker, a Bluetooth module, sensors, a display module, etc., which are not limited herein. It can be understood that the server 200 can carry a system architecture such as Figure 1 the system architecture of a user-side resource optimization scheduling method considering virtual energy storage as described above.

[0052] After understanding the software and hardware architecture of the present application, the following combines Figure 3 to illustrate a user-side resource optimization scheduling method considering virtual energy storage in the embodiments of the present application. Figure 3 is a schematic flowchart of a user-side resource optimization scheduling method considering virtual energy storage provided by the embodiments of the present application, which specifically includes the following steps:

[0053] Step S310: Obtain the output data of the target area distribution network within a preset time period; the output data includes: new energy output data and energy storage system output data.

[0054] Among them, the new energy output data is a set of power generation power and related operating status data of new energy power generation equipment in the target area distribution network within a preset time period. It can be photovoltaic output, wind power output, hydropower output, etc., which is not limited here. Taking distributed photovoltaics as an example, its data covers core parameters such as the real-time power generation power and cumulative power generation of photovoltaic power stations, and also includes meteorological data such as light intensity and temperature that affect power generation efficiency. These data are collected in real time by power monitoring devices and meteorological sensors to form a time series data set, accurately reflecting the dynamic characteristics of new energy power generation.

[0055] Among them, the energy storage system output data is a set of operating data such as charge and discharge power and state of charge (SOC) of energy storage devices in the target area distribution network within a preset time period. As a key unit for regulating power supply and demand, the output data of the energy storage system includes information such as the magnitude and time period distribution of charge and discharge power and the real-time change of SOC, which is collected by the built-in monitoring device of the energy storage system and reflects the operating status and regulation ability of the device.

[0056] Specifically, the output data is obtained through the intelligent monitoring system of the target area distribution network. This intelligent monitoring system of the target area distribution network integrates multiple collection terminals. For new energy devices, power sensors and meteorological monitoring devices are deployed to collect power generation power, light intensity, etc.; for the energy storage system, through the power monitoring module and the SOC calculation unit, the charge and discharge power and remaining power are obtained. It should be noted that the selection of the preset time period needs to be combined with the operating characteristics and dispatching requirements of the distribution network. If the proportion of new energy in the target area is high, the daily time period can be selected to analyze the daily fluctuations. If long-term strategies are concerned, the monthly or quarterly time period can be selected to study the seasonal laws. In addition, the acquisition of output data is the basis for multi-objective optimal dispatching. By integrating the intermittency of new energy and the regulation ability of energy storage, a more practical mathematical model can be constructed.

[0057] Step S320: Obtain the first electricity price, and determine the power consumption status data set and operating status data set of the user-side resources according to the first electricity price.

[0058] Among them, the first electricity price is the real-time electricity price or time-of-use electricity price signal of the power market released by the target distribution network the next day, and it is the core economic parameter used to solve the optimal scheduling of user-side resources. The determination of the first electricity price is usually affected by various factors, including power generation costs, supply and demand relationships in the power market, policy regulation, etc. In different time periods, the first electricity price may change, forming different electricity price models such as peak-valley electricity prices. This electricity price is dynamically adjusted based on factors such as the real-time power supply and demand relationship of the distribution network, power generation costs, and fluctuations in new energy output. For example, the electricity price increases during peak electricity consumption periods and decreases during low valleys, forming a price signal to encourage user-side resources to participate in grid regulation. The electricity consumption status data set is a collection of electricity consumption behavior data of user-side resources, including key information such as user electricity consumption power, electricity consumption time period, and start-stop status of electrical equipment, which is not limited here. The operation status data set is a collection of operation parameters of various devices (such as distributed power sources, virtual energy storage, energy storage systems) in user-side resources under the influence of electricity prices. For distributed power sources, it includes power generation power, efficiency, start-stop status; for energy storage systems, it involves charge-discharge power, SOC, cycle times, etc.; for virtual energy storage, it includes temperature changes of temperature control equipment, power regulation amount, and time period distribution. These data are collected by built-in sensors and monitoring modules of the devices, reflecting the operation characteristics of the devices under the guidance of electricity prices, and are used to construct device operation models to support the parameter input of multi-objective optimal scheduling algorithms.

[0059] Specifically, after obtaining the first electricity price, the data acquisition terminals are integrated through the user-side resource collaborative control platform. For the electricity consumption status, the total electricity consumption power of users and electricity consumption data of sub-devices are monitored in real time using smart meters, and combined with the division of electricity price time periods (such as peak, flat, and valley periods), the electricity consumption behaviors in different electricity price intervals are marked. For the operation status, the operation parameters of power generation equipment are obtained through the distributed power source monitoring system, the charge-discharge data of energy storage are collected with the help of the energy storage management system, and the temperature and power regulation information of temperature control equipment are collected relying on the virtual energy storage aggregation platform. Then, the user-side resource collaborative scheduling platform cleans and extracts features from the original data. For example, features such as the proportion of electricity consumption during peak periods and load volatility are extracted from the electricity consumption data, and parameters such as the adjustable capacity and response speed of the devices are refined from the operation data. Finally, a structured electricity consumption status data set and operation status data set are formed, laying a data foundation for the construction of subsequent optimal scheduling models.

[0060] Consistent with the above Figure 3 illustrated embodiment, please refer to Figure 4 , Figure 4 is a schematic flow chart of another method for optimizing the scheduling of user-side resources considering virtual energy storage provided by an embodiment of the present application, which is applied to a server. The method specifically includes the following steps:

[0061] S410. Obtain the historical electricity consumption data and historical electricity prices of the target area distribution network;

[0062] S420. Train a preset machine learning model based on the historical power consumption data and the historical electricity prices to obtain a power consumption - electricity price relationship model;

[0063] S430. Input the first electricity price into the power consumption - electricity price relationship model to obtain first power consumption data;

[0064] S440. Obtain the electrical equipment in the user - side resources to get a first equipment set;

[0065] S450. Determine the power consumption distribution of the first equipment set according to the first power consumption data to obtain a first power consumption distribution set;

[0066] S460. Extract the power consumption corresponding to the first equipment set from the first power consumption data to obtain a first power consumption volume set;

[0067] S470. Determine the power consumption status data set according to the first power consumption distribution set and the first power consumption volume set;

[0068] S480. Determine the operating parameters of each device in the first equipment set to obtain a first operating parameter set;

[0069] S490. Determine the operating status data set corresponding to the first equipment set according to the first power consumption volume set and the first operating parameter set.

[0070] Among them, the historical power consumption data includes information such as the power consumption, power consumption period, and equipment start - stop frequency accumulated by the users on the user side of the target area distribution network, depicting the user's power consumption behavior pattern. The historical electricity prices include sequence data such as time - of - use electricity prices and real - time electricity prices, reflecting the electricity price fluctuation law. The preset machine learning model can be a random forest model, or a Gradient Boosting Decision Tree (GBDT), or a Long Short - Term Memory (LSTM), or a fusion model of ensemble learning methods and LSTM, which is not limited here. Taking the machine learning model that fuses GBDT and LSTM as an example, GBDT can capture the non - linear mapping between electricity prices and power consumption data, and LSTM can process time - series dependent features. The inputs of this model include features such as historical electricity prices, power consumption, and user types, and the output is the predicted power consumption data. During the training process, the parameters are optimized through the mean square error loss function to improve the prediction accuracy.

[0071] Specifically, historical electricity consumption data is obtained through a cloud server. After data cleaning to remove outliers (for example, the sudden change points of electricity consumption power are corrected by the moving average method, and missing values are filled by the missing value filling method), historical electricity prices are obtained from the power grid trading platform and stored aligned by timestamp. Then, time-domain features are extracted from the historical electricity consumption data (such as the daily maximum electricity consumption power, the peak-valley difference of weekly electricity consumption), statistical features are extracted from the historical electricity prices, and the input feature matrix includes time periods, electricity prices, historical electricity consumption in the same period, etc. Then, the real-time first electricity price is input into the model. The model is based on the historical learning mode, predicts the electricity consumption power in each time period, and generates the first electricity consumption data. Then, electrical equipment is obtained through the user-side resource platform to form the first equipment set, and based on the first electricity consumption data, the electricity consumption ratio of the equipment in different time periods is analyzed to determine the electricity consumption distribution set. The electricity consumption of the equipment is parsed from the first electricity consumption data, and the electricity consumption distribution and electricity consumption are integrated to construct an electricity consumption status data set, which includes fields such as equipment identification, time period, electricity consumption power, electricity consumption, etc. For the first equipment set, operating parameters are obtained. For example, the temperature adjustment range of the temperature control equipment, the rotation speed and load rate of the motor, etc. are formed into the first operating parameter set. Finally, combining the electricity consumption and the operating parameters, the operating status data set is determined, such as the equipment operating duration, start-stop times, load rate changes, etc., to comprehensively characterize the equipment operating status.

[0072] Step S330, determine the virtual energy storage model based on the preset first constraint condition and the operating status data set.

[0073] Among them, the preset first constraint condition is a set of a series of restrictive conditions that the virtual energy storage system must follow during operation. These conditions are set based on physical laws, equipment characteristics, and actual application requirements, aiming to ensure the safe, stable, and efficient operation of the virtual energy storage system. From a physical level, it includes the power limit of the equipment. For example, the maximum and minimum power ranges of temperature control loads (such as air conditioners, water heaters, etc.) are to avoid equipment damage due to overload operation. It also includes time constraints and constraints for interacting with the power grid. The operating status data set is a detailed description of the operating conditions of various equipment in the user-side resources. It reflects the actual operating status and performance of the equipment at different times. For the temperature control load equipment involved in the virtual energy storage, the operating status data set includes the real-time power, temperature change, start-stop status, etc. of the equipment, which are not limited here. By deeply mining the operating status data set, the operating rules, energy consumption characteristics of the equipment, and its response to different external conditions can be understood, providing a data basis for accurately constructing the virtual energy storage model.

[0074] In a possible embodiment, the determining the virtual energy storage model based on the preset first constraint condition and the operating status data set specifically includes the following steps:

[0075] 331. Obtain the temperature control devices in the target area distribution network to get k temperature control devices; k is a natural number greater than 1;

[0076] 332. Virtualize each of the k temperature control devices into a virtual energy storage device to get k virtual energy storage devices;

[0077] 333. Obtain the device parameters of each of the k virtual energy storage devices to get k device parameters;

[0078] 334. Determine k virtual energy storage parameters and k load temperatures according to the operation status data set and the k device parameters;

[0079] 335. Determine the virtual energy storage model based on the first constraint condition, the k virtual energy storage parameters and the k load temperatures;

[0080] Among them, the determining k virtual energy storage parameters and k load temperatures according to the operation status data set and the k device parameters includes:

[0081] 3341. Obtain a target virtual energy storage device and its corresponding target device parameters; the target virtual energy storage device is any one of the k virtual energy storage devices;

[0082] 3342. Determine the load temperature corresponding to the target virtual energy storage device according to the operation status data set to get the load temperature of the target virtual energy storage device;

[0083] 3343. Obtain the actual ambient temperature corresponding to the target virtual energy storage device;

[0084] 3344. Determine the heat loss value corresponding to the target virtual energy storage device according to the target device parameters to get the first heat loss value;

[0085] 3345. Determine the difference between the load temperature of the target virtual energy storage device and the actual ambient temperature to get the first temperature difference;

[0086] 3346. Determine the heat compensation value of the target virtual energy storage device according to the first temperature difference based on the mapping relationship between the preset temperature difference and heat compensation to get the first heat compensation value;

[0087] 3347. Determine the target heat loss value according to the first heat compensation value and the first heat loss value;

[0088] 3348. Determine the virtual energy storage parameters of the target virtual energy storage device based on the target heat loss value and the load temperature of the target virtual energy storage device.

[0089] Specifically, when determining the virtual energy storage model, it is first necessary to preprocess the operating state data set. Since the collected data may have problems such as noise and missing values, which will affect the accuracy of the model, operations such as denoising and filling missing values are required. For example, for abnormal fluctuations in power data, a filtering algorithm can be used for smoothing; for missing values in temperature data, interpolation can be used for filling. Then, according to the constraint conditions, the preprocessed operating state data is constrained. Then, based on the filtered data, the basic structure of the virtual energy storage model is constructed. Modeling methods such as equivalent circuit models and thermodynamic models can be adopted and selected according to the characteristics and requirements of the virtual energy storage system. Taking the temperature-controlled load as an example, the thermodynamic model can well describe the relationship between the temperature change of the device and energy storage. When determining the model parameters, optimization algorithms can be used for solution. For example, the least squares method, genetic algorithm, etc. are used, which are not limited here, so that the error between the output of the model and the actual operating state data is minimized.

[0090] For a clearer explanation, the above can be described by the following optimization model. Among the user-side resources, temperature-controlled loads such as water heaters and air conditioners can be regarded as virtual energy storage. The virtual energy storage model for aggregating temperature-controlled loads is as follows:

[0091]

[0092]

[0093]

[0094]

[0095]

[0096]

[0097]

[0098]

[0099] ,

[0100] Among them, is t the state of charge of the virtual energy storage in the time period, is t the state of charge of the virtual energy storage in the -1 time period, is the heat capacity of the kth temperature-controlled load (virtual energy storage), is the k ambient temperature of the th temperature-controlled load, is the temperature of the temperature-controlled load during period t, is the number of temperature-controlled loads (i.e., k in the above), is the k set temperature of the th temperature-controlled load, k is the adjustable range of the th temperature-controlled load, is the virtual energy storage state parameter, is obtained by least squares fitting, t is the charge and discharge power during period is the maximum and minimum values of the state of charge, and are the maximum and minimum values of the allowable charge and discharge power, is the power consumption of the aggregated temperature-controlled load, is the heat loss power of the aggregated temperature-controlled load, is the k thermal resistance of the

[0101] th temperature-controlled load. Among them, the heat loss power of the aggregated temperature-controlled load has the following calculation formula:

[0102]

[0103]

[0104] Among them, is the k thermal resistance of the th temperature-controlled load, k is the set temperature of the t th temperature-controlled load during period is the k th temperature-controlled load during period t ambient temperature, is the k thermal resistance of the th temperature-controlled load, k is the switch state of the

[0105] Step S340: Based on the preset second constraint condition, the power consumption state data set, and the first electricity price, determine the distributed power generation output model to obtain the power generation output model.

[0106] Among them, the preset second constraint condition is a comprehensive calculation of various limiting conditions that distributed power sources must follow during actual operation. These conditions are set based on multiple factors such as the security, stability, and economy of the power system. It includes the physical characteristic constraints of the distributed power source itself. For example, the maximum and minimum output limits of the distributed power source are determined by the design parameters of the power source equipment. At the same time, it also includes the ramp rate limit of the power source, that is, the maximum change in the power output of the power source per unit time. This is to ensure the stability of the power system and avoid problems such as voltage fluctuations caused by sudden changes in power output. Economically, the second constraint condition also includes cost-benefit, such as the start-stop cost and maintenance cost of the power source. These factors will affect the optimal power output decision of the power source.

[0107] Among them, the power consumption status data set is a detailed description of the power consumption of power users within a certain period of time, reflecting the power consumption demand and power consumption pattern on the user side. This data includes information such as the real-time power consumption of users, power consumption time, and types of power-consuming equipment. By analyzing the power consumption status data set, the power consumption habits and demand change rules of users can be understood. For example, the peak and off-peak periods of power consumption of some users within a specific period of time, and the power consumption characteristics of different types of power-consuming equipment. This information is crucial for determining the power output model of the distributed power source because the power output of the distributed power source needs to match the power consumption demand of users to achieve the balance between power supply and demand in the power system.

[0108] In a possible embodiment, determining the power output model of the distributed power source according to the preset second constraint condition based on the power consumption status data set and the first electricity price to obtain the power output model of the power source specifically includes the following steps:

[0109] 341. Obtain the load demand during the target power consumption period from the power consumption status data set; the time length of the target power consumption period is a preset value; the preset time period includes the target power consumption period;

[0110] 342. Determine the power output demand of the distributed power source according to the load demand to obtain the power output demand of the power source;

[0111] 343. Determine the mapping relationship between power output and efficiency based on the power output demand of the power source to obtain the first mapping relationship;

[0112] 344. Obtain the operating cost of the distributed power source and the electricity price corresponding to the target power consumption period to obtain the first operating cost and the target electricity price;

[0113] 345. Determine the difference between the target electricity price and the first electricity price to obtain the first electricity price difference;

[0114] 346. Determine the economic operation range of the distributed power source based on the first electricity price difference and the first operation cost to obtain the first economic operation range;

[0115] 347. Determine the output model of the distributed power source based on the second constraint condition, the first economic operation range, and the first mapping relationship to obtain the power output model.

[0116] Among them, the electricity consumption status data set records the electricity consumption information of users at different time periods. By screening and extracting it, the load demand of the target electricity consumption period can be accurately obtained. The preset time length can be flexibly set according to actual needs. For example, common target electricity consumption periods are 1 hour, 2 hours, etc. The preset time period usually covers multiple target electricity consumption periods, which can be a relatively long time span such as one day or one week. This helps to analyze the electricity consumption pattern from a more macroscopic perspective. The load demand reflects the amount of electric energy used by users during the target electricity consumption period. The distributed power source needs to provide corresponding electric energy to meet this demand, which requires considering factors such as power transmission loss and the conversion efficiency of the distributed power source itself. At the same time, it is also necessary to consider the intermittency and volatility of different types of distributed power sources (such as solar energy, wind energy, etc.) and make reasonable adjustments and predictions for the output demand. In addition, the efficiency of the distributed power source is not fixed and will change with the change of output. Within a certain output range, the power source efficiency will increase with the increase of output, but when the output exceeds a certain threshold, the efficiency may decrease. Obtain the operation cost of the distributed power source and the electricity price corresponding to the target electricity consumption period to obtain the first operation cost and the target electricity price.

[0117] Among them, the operating cost of distributed power sources includes equipment depreciation, maintenance costs, fuel costs, etc., and the first operating cost can be determined through cost analysis. The target electricity price refers to the electricity sales price during the target electricity consumption period, which can be obtained from the price data of the electricity market. The magnitude of the electricity price difference will affect the economic operation decision of the distributed power source. If the difference is positive and large, it indicates that more profits may be obtained by generating electricity and selling it to the grid during the target electricity consumption period; if the difference is negative, the economy of power generation needs to be carefully considered. The economic operation range refers to the range within which the distributed power source can operate to maximize economic benefits. This range can be determined by establishing an economic model. The preset second constraint conditions include the physical limitations of the distributed power source (such as maximum and minimum output limitations, ramp rate limitations, etc.) and the requirements for the safe and stable operation of the power system. When determining the output model, an optimal output plan needs to be solved under the premise of meeting the second constraint conditions, combined with the first economic operation range and the first mapping relationship. The solution method can be linear programming or non-linear programming, etc., which is not limited here. Taking the second constraint conditions as the constraint conditions and the maximization of economic benefits as the objective function, and considering the mapping relationship between output and efficiency at the same time, the optimal output curve of the distributed power source during the target electricity consumption period is solved, and this output curve is the power output model of the power source.

[0118] For a clearer illustration, the following uses a micro-turbine (MT) in distributed power sources as an example. As a common distributed power source on the user side, the output and efficiency of a micro-turbine can be fitted into a cubic function relationship, and its mathematical model is:

[0119]

[0120] Among them, is the efficiency of the MT at t time period, is the active power output of the MT at t time period, represents the rated active power output of the MT, represents the heat contained in the exhaust gas of the MT at t time period, represents the heat dissipation rate of the MT, represents the fuel cost of the MT, represents the unit price of natural gas, T is the number of total dispatching time periods, L is the minimum calorific value of natural gas, L =9.7kWh / m 3 , is the time interval when the MT uses fuel. In addition, 、 、 、 They are the efficiency coefficients of MT respectively.

[0121] Step S350: Determine the first output model according to the preset third constraint condition and the new energy output data.

[0122] Among them, the preset third constraint condition is a limitation condition set for the new energy power generation characteristics and the grid acceptance capacity, aiming to ensure the safe and stable operation of the power system. Among them, the new energy output data includes: output volatility constraint, which is used to limit the maximum change amplitude of the new energy output within a unit time to avoid grid frequency fluctuations; prediction error constraint, which is used to determine the uncertainty of the new energy output prediction, set the output confidence interval, and reserve spare capacity; grid access constraint, which is used to determine that the new energy output does not exceed the maximum carrying capacity of the distribution network to avoid line overload or voltage over-limit. According to the new energy output data and the third constraint condition, determine the first output model (i.e., the new energy output model).

[0123] Among them, the third constraint condition can be expressed by the following formula:

[0124]

[0125] Among them, represents the actual output of distributed photovoltaics, represents the maximum value of the photovoltaic predicted output. is a value preset according to the new energy system.

[0126] Step S360: Determine the second output model according to the preset fourth constraint condition and the energy storage system output data.

[0127] Among them, the preset fourth constraint condition is a limitation condition set for the physical characteristics of the energy storage system and the economic operation requirements, including: charge and discharge power constraint, the charge and discharge power of the energy storage system shall not exceed the rated value; state of charge (SOC) constraint, the SOC needs to be maintained within a safe range; life loss constraint: based on the Peukert equation cycle life model, limit the charge and discharge depth and daily cycle times to reduce the loss cost. Among them, the energy storage system output data is a set of operation parameters of the energy storage devices in the target area distribution network, including: charge and discharge power, real-time SOC value, cumulative cycle times, temperature (affecting battery efficiency and life).

[0128] Among them, first, data preprocessing and feature extraction are carried out on the historical energy storage output data, filtering out outliers (such as instantaneous power mutations), and using linear interpolation to fill in missing data. Then, a cycle life model based on the Peukert equation is constructed for the daily cycle times, average DOD, SOC volatility, etc. Finally, according to the output data of the energy storage system and the Peukert-based second output model (the output model of the energy storage system) is established.

[0129] Specifically, assuming that each energy storage system in the user-side resources is mainly composed of a storage battery, the model of the energy storage system constructed according to the constraints can be expressed as:

[0130]

[0131]

[0132]

[0133]

[0134] Among them, represents t the state of charge of the energy storage system at time period represents t the state of charge of the energy storage system at time period -1 represents the time interval represents the discharge efficiency of the energy storage system represents the charging power of the energy storage system represents the discharge power of the energy storage system represents the minimum value of the energy storage system capacity represents the maximum value of the energy storage system capacity represents the charge and discharge coefficient represents the maximum value of the charging power of the energy storage system represents the maximum value of the discharge power of the energy storage system.

[0135] Among them, based on the battery life model of the Peukert equation, the influence of the cycle times and charge-discharge depth of the energy storage battery on the battery life and the loss cost are as follows:

[0136]

[0137]

[0138]

[0139] Among them, represents the charge-discharge depth j represents the j th charge and discharge in the daily cycle charge and discharge times represents the battery life coefficient is a fixed value represents the daily cycle charge and discharge times represents the battery life loss ratio represents the initial battery life represents the loss cost coefficient represents the investment cost.

[0140] Step S370: Construct a collaborative scheduling model for user-side resources based on the virtual energy storage model, the power output model, the first output model, and the second output model.

[0141] Among them, the virtual energy storage model virtualizes the temperature control equipment in the target area distribution network into an energy storage device. By analyzing its operating status and parameters, the charge and discharge characteristics and capabilities of the virtual energy storage device are determined. It takes into account factors such as the load temperature, heat loss, and ambient temperature of the temperature control equipment, as well as the relationships between these factors and the virtual energy storage parameters (such as state of charge, charge and discharge power), and can simulate the functions of traditional energy storage devices to a certain extent, providing additional flexibility and adjustability for the scheduling of user-side resources. The power output model is the output scheme of distributed power sources determined based on the preset second constraint conditions, the power consumption status data set, and the first electricity price. It comprehensively considers the physical characteristics of distributed power sources (such as maximum and minimum output limits, ramp rate limits), the electricity consumption needs of users, and the electricity price changes in the power market, aiming to maximize economic benefits while meeting the user's needs. This model can dynamically adjust the output of distributed power sources according to different electricity consumption periods and electricity price situations to adapt to the supply-demand balance of the power system. The first output model is the optimal output curve of new energy power generation determined according to the preset third constraint conditions and new energy output data. Since new energy (such as solar energy, wind energy) has the characteristics of intermittency and volatility, this model considers factors such as the volatility constraint, prediction error constraint, and grid connection constraint of new energy output, and solves the optimal output of new energy power generation equipment at different times under these constraint conditions through an optimization algorithm to improve the consumption capacity of new energy and reduce the phenomena of abandoned wind and abandoned light. The second output model is the operation strategy of the energy storage system determined based on the preset fourth constraint conditions and the energy storage system output data. It considers the charge and discharge power constraint, state of charge constraint, and life loss constraint of the energy storage system, etc., and aims to minimize the operating cost (including the electricity purchase cost and life loss cost). Through the optimization algorithm, the charge and discharge power of the energy storage system at different times is determined to achieve the safe and economic operation of the energy storage system and provide support for the peak shaving of the power grid and the consumption rate of new energy.

[0142] In a possible embodiment, the constructing of the collaborative scheduling model for user-side resources based on the virtual energy storage model, the power output model, the first output model, and the second output model specifically includes the following steps:

[0143] 371. Preprocess the first electricity price, the power consumption status data set, and the operating status data set to obtain a target power data set;

[0144] 372. Determine the first resource scheduling model based on a preset model coupling method, the virtual energy storage model, and the power output model;

[0145] 373. Optimize the parameters of the first resource scheduling model according to the target power dataset to obtain the second resource scheduling model;

[0146] 374. Determine the target resource scheduling model according to the second resource scheduling model, the first power output model, and the second power output model;

[0147] 375. Determine the user-side resource collaborative scheduling model according to the first constraint condition, the second constraint condition, the third constraint condition, the fourth constraint condition, and the target resource scheduling model.

[0148] Among them, for the abnormal power consumption values in the power consumption status dataset, statistical analysis methods (such as the three-sigma method, the method based on standard deviation) are used to identify and eliminate them. Similar solutions are also applied to the incorrect operation parameters in the operation status dataset. At the same time, the missing values in the dataset are filled, and interpolation methods (such as linear interpolation, spline interpolation) or statistical prediction methods based on historical data can be used. Then, the first electricity price, the power consumption status dataset, and the operation status data are standardized. The standardization method can be Z-score standardization, that is, converting the data into a distribution with a mean of 0 and a standard deviation of 1. Then, key features are extracted from the power consumption status dataset, such as peak power consumption periods, valley power consumption periods, average power consumption, etc., and features such as the operation efficiency and failure frequency of the equipment are extracted from the operation status dataset.

[0149] Among them, the preset model coupling method is a strategy for organically combining different models, aiming to give full play to the advantages of each model and achieve collaborative scheduling of resources. The preset model coupling method can be the information interaction method. For example, the power output model transmits the real-time power output information of the distributed power source to the virtual energy storage model, and the virtual energy storage model adjusts its charge and discharge strategy according to this information to cooperate with the output of the distributed power source. It can also be the target collaboration method, which unifies the goals of the two models to achieve the optimal overall resource scheduling. For example, with the common goal of maximizing the economic benefits and stability of the power system, the output of the virtual energy storage device and the distributed power source is reasonably allocated on the premise of meeting the user's power consumption needs. It is not limited here.

[0150] Among them, the target power dataset includes the preprocessed first electricity price, electricity consumption status dataset, and operation status data, which reflect the actual operation conditions and market environment of the power system. Although the first resource scheduling model has integrated the virtual energy storage model and the power output model, the parameters therein may not be optimal and need to be adjusted and optimized according to the actual data. The second resource scheduling model has been optimized in terms of parameters and can better coordinate the resource scheduling of virtual energy storage devices and distributed power sources. Specifically, the second resource scheduling model, the first power output model, and the second power output model are integrated to form a unified resource scheduling framework. In this framework, each model collaborates with each other to jointly complete the resource scheduling task of the power system.

[0151] In a possible embodiment, the determining the target resource scheduling model according to the second resource scheduling model, the first power output model, and the second power output model specifically includes the following steps:

[0152] 3741. Extract the constraint interval from the first power output model to obtain the first constraint interval;

[0153] 3742. Extract the constraint interval from the second power output model to obtain the second constraint interval;

[0154] 3743. Determine the constraint interval of the second resource scheduling model to obtain the third constraint interval;

[0155] 3744. Determine the target constraint interval according to the first constraint interval, the second constraint interval, and the third constraint interval;

[0156] 3745. Embed the first power output model and the second power output model into the second resource scheduling model to obtain the target embedding model;

[0157] 3746. Determine the target resource scheduling model based on the preset dynamic programming algorithm according to the target constraint interval and the target embedding model.

[0158] Among them, the first output model is the optimal output curve of new energy power generation determined according to the preset third constraint condition and new energy output data, and the first constraint interval is the feasible range of new energy output constituted by these restrictions. For example, due to the uncertainty of light intensity and wind power, the output of photovoltaic and wind power generation will have a certain fluctuation range at different times. At the same time, the power grid also has an upper limit requirement for the access power of new energy, which will all form constraints on new energy output. Extract the constraint interval from the second output model to obtain the second constraint interval. Among them, the second output model is the operation strategy of the energy storage system determined based on the preset fourth constraint condition and energy storage system output data. The fourth constraint condition mainly involves aspects such as the charge and discharge power limit, SOC limit, and life loss of the energy storage system. The second constraint interval is the feasible operation range of the energy storage system under these constraints. Determine the constraint interval of the second resource scheduling model to obtain the third constraint interval. Among them, the second resource scheduling model is a resource scheduling model that coordinates virtual energy storage devices and distributed power sources after parameter optimization. The constraint conditions of this model mainly come from the relevant restrictions of the virtual energy storage model and the power output model, such as the charge and discharge power and energy limit of the virtual energy storage device, the maximum and minimum output limits and ramp rate limits of the distributed power source, etc. The third constraint interval is the feasible scheduling range of the second resource scheduling model under these constraints. Then, it is the feasible operation range obtained by comprehensively considering all the constraint conditions of new energy power generation, energy storage system, and virtual energy storage device and distributed power source scheduling.

[0159] Specifically, aiming at minimizing curtailment of light and electricity cost, a collaborative optimization scheduling model for user-side flexibility resources is constructed according to the first, second, third, and fourth constraint intervals. This model can be expressed as:

[0160]

[0161]

[0162]

[0163]

[0164] Among them, represents the electricity cost, represents the curtailment of light cost, represents the electricity cost, represents the user-side comfort loss cost, represents the fuel cost of the micro steam turbine, represents the cost of the energy storage system, represents the photovoltaic cost coefficient, represents the user-side electricity cost coefficient, represents the virtual energy storage cost coefficient, tIndicates the t time period, T indicating a preset time period, indicating the actual output of distributed photovoltaics, indicating the maximum value of photovoltaic predicted output, indicating the charging power of the energy storage system, indicating t the load during the i.e., t the demand load for electricity on the user side during the time period, indicating t the actual load during the time period, i.e., t the actual load amount after demand response regulation during the time period.

[0165] For ease of understanding, please refer to Figure 5 , Figure 5 which is a schematic flow chart of the construction of a user-side resource optimal scheduling model considering virtual energy storage provided by an embodiment of the present application. It can be seen that the power output model, virtual energy storage model, new energy output model, and energy storage system output model are all used as basic modules. Parameters and constraints are input into the basic resource scheduling model, and the basic resource scheduling model is used to further support the construction of the user-side resource collaborative scheduling model. The power output model defines the output strategy of distributed power sources based on the electricity consumption status data set, the first electricity price, and preset constraints, reflecting its operating characteristics under electricity price fluctuations and load demands; the virtual energy storage model expresses the charge and discharge characteristics of virtual energy storage through the virtualization of temperature control devices and in combination with the operating status data and constraints; the new energy output model optimizes the output curve of new energy power generation according to the new energy output data and the third constraint condition to cope with its intermittency and volatility; the energy storage system output model clarifies the charge and discharge strategy of the energy storage based on the energy storage system output data and the fourth constraint condition to ensure safe and economic operation. The user-side resource collaborative scheduling model is constructed based on the basic resource scheduling model, comprehensively considering the constraint conditions of each model, and realizing global collaborative scheduling through an optimization algorithm. Among them, this model not only integrates single-resource scheduling strategies, but also optimizes the configuration from the system level.

[0166] Step S380, solve the user-side resource collaborative scheduling model through a preset particle swarm optimization algorithm to obtain a target calculation result, and the target calculation result is used to configure the user-side resource collaborative scheduling model.

[0167] Among them, the preset particle swarm optimization algorithm is an intelligent optimization algorithm improved based on reverse learning and iterative selection mechanism, aiming to solve the problems that the traditional particle swarm optimization algorithm is easy to fall into local optimum and has slow convergence speed. By introducing the reverse solution generation strategy and population diversity maintenance mechanism, this algorithm enhances the global search ability and local fine search ability of the algorithm, and is applicable to the high-dimensional non-linear optimization problem of the user-side resource collaborative scheduling model. Among them, the user-side resource collaborative scheduling model is a multi-objective optimization model, including objectives such as minimizing curtailment cost, minimizing electricity consumption cost, and minimizing user comfort loss, and is restricted by complex constraints such as virtual energy storage temperature constraint, energy storage life loss constraint, and distributed power generation ramp rate constraint. The particle swarm optimization algorithm searches for the optimal scheduling strategy in the feasible solution space by discretizing continuous decision variables into particle positions.

[0168] In a possible embodiment, solving the user-side resource collaborative scheduling model through the preset particle swarm optimization algorithm to obtain the target calculation result specifically includes the following steps:

[0169] 381. Obtain the new energy utilization rate corresponding to the new energy output data;

[0170] 382. Obtain the electricity consumption cost of the target area distribution network according to the first electricity price to obtain the first electricity consumption cost;

[0171] 383. Construct an optimization function according to the new energy utilization rate and the first electricity consumption cost to obtain the target optimization function;

[0172] 384. Determine the model parameters corresponding to the user-side resource collaborative scheduling model to obtain n model parameters; n is an integer greater than 1;

[0173] 385. Generate the first particle swarm according to the n model parameters, and initialize the initial position and initial velocity of each particle in the first particle swarm; the first particle swarm includes n particles; each particle corresponds to a model parameter;

[0174] 386. Determine the fitness of each particle in the first particle swarm according to the target optimization function to obtain n particle fitnesses;

[0175] 387. Determine the weight corresponding to each particle among the n particle fitnesses to obtain n weights;

[0176] 388. Adjust the positions and velocities of the n particles according to the n weights to obtain n particle target positions and n particle target velocities;

[0177] 389. Solve the target positions and target velocities of the n particles to obtain a second particle swarm; the second particle swarm includes: the positions of m particles and the velocities of m particles; m is a natural number greater than 1 and m is less than or equal to n.

[0178] 3810. Determine the fitness of each particle in the particle swarm according to the target optimization function and the second particle swarm to obtain the fitnesses of m particles.

[0179] 3811. Based on the particle swarm algorithm and the fitnesses of the m particles, determine the optimal solution of the user-side resource collaborative scheduling model to obtain the target calculation result.

[0180] Among them, the new energy output data represents the actual power generation of new energy power generation equipment such as photovoltaic and wind power at different times. The new energy utilization rate represents the degree to which new energy is actually effectively utilized, and it is affected by various factors, including the grid's accommodation capacity, the volatility of new energy power generation, and the user's electricity demand, etc., which are not limited here. The calculation of the new energy utilization rate is the ratio between the electricity actually utilized by new energy and the total electricity of new energy. Among them, the electricity actually utilized by new energy can be obtained by statistically counting the electricity transmitted by new energy power generation equipment to the grid and effectively used by users, and the total electricity generation of new energy is the electricity that new energy power generation equipment can theoretically generate during the corresponding time period, which can be calculated by integrating the power value in the new energy output data combined with the time interval to obtain the electricity value, and it can be obtained through empirical formulas, or through statistical models, or through machine learning models, which are not limited here. The user-side resource collaborative scheduling model includes multiple factors affecting resource scheduling, and the parameters corresponding to these factors constitute the model parameters. The model parameters may include the output coefficient of distributed power sources, the charge and discharge power of energy storage systems, the adjustment parameters of virtual energy storage devices, etc. By analyzing and sorting out the user-side resource collaborative scheduling model, these key model parameters are determined, and the number of them is denoted as n.

[0181] Among them, the electricity cost of the target area's distribution network is closely related to the user's electricity consumption power and the first electricity price. When calculating the first electricity cost, it is necessary to multiply the electricity consumption power of the target area at different time periods by the corresponding first electricity price, and then sum over all time periods. Its calculation formula can be expressed as:

[0182]

[0183] Among them, represents the first electricity cost, is the first electricity price, is the t electricity consumption power in the T time period, tFor each time period.

[0184] Specifically, the collaborative optimization model of user-side flexibility resources is solved by using an improved particle swarm optimization algorithm. By introducing reverse learning and iterative selection operators into the traditional particle swarm optimization algorithm, first record the initial value of the population and the comparison value of the results obtained by iteration. In the suppression stage, retain the particles with low similarity and high fitness to the current particle. Ensure that after the particles with high fitness are compared with the initial particles, the particles in the optimal position within the set threshold suppression range can enter the next iteration. First, initialize the velocity and position of the particles, and during the process of particle swarm optimization, generate a collaborative optimization scheduling strategy for user-side flexibility resources according to the position of the particles obtained by each optimization. Then, calculate the particle fitness F (i.e., the objective function) under the current optimization, update the velocity and position of the particle swarm according to the velocity and position update formula, and perform reverse learning on the particle swarm. Assume that there is a feasible solution x in the search space, then its reverse solution The calculation formula is:

[0185]

[0186]

[0187] Among them, is the reverse solution of the i th particle at the m th iteration optimization for the j dimensional position, is the i th particle at the m th iteration for the j dimensional position, is the historical minimum value of the i th particle at the m th optimization for the j dimensional, is the i th particle at the m th optimization for the j dimensional historical maximum value.

[0188] Then, find the adaptive weight w that changes with the particle fitness F, and its calculation formula is:

[0189]

[0190] Among them, f is the current fitness, is the average fitness, is the minimum fitness, is the maximum fitness, is the adaptive weight wThe minimum value, is the adaptive weight w The maximum value.

[0191] After each iteration, arrange the particles in descending order according to their adaptability. Designate the first particle as the first initial particle and add it to the memory group as a memory particle. For the particles from the second to the last particle, perform the following operations in sequence: If the distance from the current particle to the initial particle is greater than all the particles in the memory group, designate this particle as the new network center and add it to the memory group as a memory particle in the same way. If the distance from the current particle to the designated initial particle is less than all the particles in the memory group, eliminate this particle, where the distance i between particle u and particle is calculated according to the following formula:

[0192]

[0193] where, is the position of the i particle in the j d-th dimension, is the position of particle u in the j d-th dimension, n is the dimension, is the maximum value of the j d-th dimension, is the minimum value of the j d-th dimension.

[0194] Finally, within the range of the number of iterations, perform multiple optimizations to obtain the individual optimal value and the global optimal value of the particles. The particle position corresponding to the final global optimal value is the optimal solution of the collaborative optimization scheduling strategy for the user-side flexibility resources, and use it as the target calculation result. This result can be used to configure the user-side resource collaborative scheduling model to improve the utilization rate of new energy and reduce the electricity cost.

[0195] For ease of understanding, please refer to Figure 6 , Figure 6 which is a schematic flow chart of a method for optimizing the scheduling of user-side resources considering virtual energy storage provided by an embodiment of this application. It can be seen that by systematically integrating key information such as new energy output, distributed power output, virtual energy storage, energy storage system, and electricity price, the efficient scheduling of user-side resources is realized, thereby improving the new energy consumption rate and electricity economy, and promoting the economic and stable operation of the power system.

[0196] First, obtain the output data of new energy sources such as wind power and photovoltaic power connected to the grid, as well as the real-time electricity price in the electricity market the next day. The output data of new energy sources accurately reflects the power generation capacity of equipment such as wind power and photovoltaic power, and its volatility and intermittency characteristics have a significant impact on the stable operation of the power grid. As a price signal of the supply-demand relationship in the electricity market, the real-time electricity price can effectively guide the user-side resources to adjust their operation strategies. Next, based on the real-time electricity price, the user-side resource collaborative regulation platform predicts the electricity consumption status and operation status information of user-side resources, and constructs a user-side resource operation model. User-side resources cover various entities such as distributed power sources, virtual energy storage, and energy storage systems. Among them, the electricity consumption status involves key information such as user electricity consumption power and time period distribution, and the operation status includes core contents such as equipment parameters and efficiency. Through in-depth data analysis, the platform predicts the response modes of resources in different electricity price periods. For example, in high electricity price periods, virtual energy storage adjusts the load and the energy storage system discharges to reduce the electricity consumption cost.

[0197] Then, with the core goal of minimizing curtailment of photovoltaic power and electricity consumption cost, construct a user-side resource collaborative optimization scheduling model. The curtailment cost of photovoltaic power reflects the loss of unconsumed new energy, and the electricity consumption cost is directly related to the electricity price and the user's electricity consumption strategy. This model organically integrates the virtual energy storage model, power output model, new energy output model, and energy storage system output model, and fully considers the constraint conditions of each model (such as power limit, state of charge constraint, etc.) to form a multi-objective optimization system.

[0198] Finally, solve the model based on the improved particle swarm optimization algorithm, and finally obtain the optimal collaborative optimization scheduling strategy for user-side resources. The improved particle swarm optimization algorithm aims at the defects of the traditional algorithm and innovatively introduces mechanisms such as reverse learning and adaptive weight, which significantly improves the global search and local development capabilities of the algorithm. The algorithm maps the scheduling strategy to the particle position, and through iterative updating of the particle position and velocity, efficiently searches for the optimal solution under the constraint conditions. During the solution process, the fitness function accurately measures the curtailment of photovoltaic power and the electricity consumption cost, and the algorithm continuously optimizes the particle state, and finally determines the optimal scheduling plan for each resource in different time periods.

[0199] For easy understanding, please refer to Figure 7 , Figure 7 which is a timing diagram of a user-side resource optimization scheduling method considering virtual energy storage provided by an embodiment of this application. It can be seen that Figure 7Clearly present the interaction logic among the target area distribution network, the user-side platform, the optimization model, and the improved particle swarm optimization algorithm, and fully demonstrate the entire process from electricity price release to the generation of the optimal scheduling strategy. First, the target area distribution network, as the power market information source, releases the electricity price for the next day to the user-side platform. After receiving the electricity price, the user-side platform immediately predicts the resource status on the user side, covering the electricity consumption and operation status of distributed power sources, virtual energy storage, energy storage systems, etc. By analyzing historical data and real-time monitoring information, the user-side platform constructs a resource model to predict the operation characteristics such as the temperature control regulation ability of virtual energy storage and the charge-discharge efficiency of energy storage systems, laying a data foundation for subsequent optimization. Then, the user-side platform inputs the resource model into the optimization model. The optimization model takes minimizing curtailment of renewable energy and electricity consumption costs as the core objectives, integrates virtual energy storage models, power output models, new energy output models, etc., to form a collaborative optimization system, ensuring that the scheduling strategy meets the actual operation requirements. At the same time, the optimization model inputs the optimization objectives into the improved particle swarm optimization algorithm for the solution process. Then, the improved particle swarm optimization algorithm, as the solution tool, first initializes the particle swarm, sets the initial position and velocity of the particles, and each particle corresponds to a parameter combination of the scheduling strategy. During the iterative solution, the algorithm evaluates the particle swarm according to the objective function of the optimization model, and updates the particle state through improvement mechanisms such as reverse learning and adaptive weights to balance global exploration and local exploitation. The result of each iteration is returned to the optimization model, and after being screened and adjusted by the objective function, it continues until the convergence condition is met. Finally, the improved particle swarm optimization algorithm feeds back the optimal solution to the optimization model to generate the optimal scheduling strategy. After receiving the strategy, the user-side platform verifies its feasibility in combination with the operation requirements of the target area distribution network.

[0200] It can be seen that through a user-side resource optimization scheduling method considering virtual energy storage, the output data of the target area distribution network within a preset time period is obtained; the output data includes: new energy output data and energy storage system output data; the first electricity price is obtained, and based on the first electricity price, the electricity consumption status dataset and operation status dataset of the user-side resources are determined; based on the preset first constraint condition and the operation status dataset, a virtual energy storage model is determined; based on the preset second constraint condition, the electricity consumption status dataset, and the first electricity price, a distributed power output model is determined to obtain a power output model; according to the preset third constraint condition and the new energy output data, a first output model is determined; according to the preset fourth constraint condition and the energy storage system output data, a second output model is determined; based on the virtual energy storage model, the power output model, the first output model, and the second output model, a user-side resource collaborative scheduling model is constructed; through the preset particle swarm optimization algorithm, the user-side resource collaborative scheduling model is solved to obtain the target calculation result, and the target calculation result is used to configure the user-side resource collaborative scheduling model. In this way, various energy resources on the user side can be fully exploited, effectively integrated, and scheduled, enabling the full utilization of user-side resources and thus reducing power losses.

[0201] The above mainly introduces the solution of the embodiment of the present application from the perspective of the execution process on the method side. It can be understood that in order to implement the above functions, the server includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments provided in this article, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0202] The embodiment of the present application can divide the functions of the server according to the above method examples. For example, each functional unit can be divided corresponding to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. It should be noted that the division of units in the embodiment of the present application is illustrative, only a logical function division, and there may be other division methods in actual implementation.

[0203] In the case of dividing each functional module corresponding to each function, Figure 8 is a block diagram of the functional unit composition of a user-side resource optimal scheduling device considering virtual energy storage provided by an embodiment of the present application. The user-side resource optimal scheduling device 800 considering virtual energy storage is applied to a server. The device 800 includes:

[0204] An acquisition unit 810, configured to acquire the output data of the distribution network in the target area within a preset time period; the output data includes: new energy output data and energy storage system output data; acquire the first electricity price, and determine the power consumption status data set and operation status data set of the user-side resources according to the first electricity price;

[0205] A determination unit 820, configured to determine a virtual energy storage model based on a preset first constraint condition and the operation status data set; determine a distributed power source output model based on a preset second constraint condition, the power consumption status data set, and the first electricity price to obtain a power source output model; determine a first output model according to a preset third constraint condition and the new energy output data; determine a second output model according to a preset fourth constraint condition and the energy storage system output data;

[0206] A control unit 830, configured to construct a user-side resource collaborative scheduling model based on the virtual energy storage model, the power source output model, the first output model, and the second output model;

[0207] A calculation unit 840 is configured to solve the user-side resource collaborative scheduling model through a preset particle swarm optimization algorithm to obtain a target calculation result, and the target calculation result is used to configure the user-side resource collaborative scheduling model.

[0208] In a possible embodiment, the obtaining unit 810 is specifically configured to determine the power consumption status data set and the operation status data set of the user-side resources according to the first electricity price:

[0209] Obtain the historical power consumption data and historical electricity prices of the target area distribution network;

[0210] Train a preset machine learning model according to the historical power consumption data and the historical electricity prices to obtain a power consumption and electricity price relationship model;

[0211] Input the first electricity price into the power consumption and electricity price relationship model to obtain first power consumption data;

[0212] Obtain the power-consuming devices in the user-side resources to obtain a first device set;

[0213] Determine the power consumption distribution of the first device set according to the first power consumption data to obtain a first power consumption distribution set;

[0214] Extract the power consumption corresponding to the first device set from the first power consumption data to obtain a first power consumption set;

[0215] Determine the power consumption status data set according to the first power consumption distribution set and the first power consumption set;

[0216] Determine the operation parameters of each device in the first device set to obtain a first operation parameter set;

[0217] Determine the operation status data set corresponding to the first device set according to the first power consumption set and the first operation parameter set.

[0218] In a possible embodiment, the determining unit 820 is specifically configured to determine the virtual energy storage model based on a preset first constraint condition and the operation status data set:

[0219] Obtain the temperature control devices in the target area distribution network to obtain k temperature control devices; k is a natural number greater than 1;

[0220] Virtualize each temperature control device among the k temperature control devices into a virtual energy storage device to obtain k virtual energy storage devices;

[0221] Obtain the device parameters of each virtual energy storage device among the k virtual energy storage devices to obtain k device parameters;

[0222] Determine k virtual energy storage parameters and k load temperatures according to the operating status data set and the k device parameters;

[0223] Determine the virtual energy storage model based on the first constraint condition, the k virtual energy storage parameters and the k load temperatures;

[0224] Among them, the determining of k virtual energy storage parameters and k load temperatures according to the operating status data set and the k device parameters includes:

[0225] Obtain the target virtual energy storage device and its corresponding target device parameters; the target virtual energy storage device is any one of the k virtual energy storage devices;

[0226] Determine the load temperature corresponding to the target virtual energy storage device according to the operating status data set to obtain the load temperature of the target virtual energy storage device;

[0227] Obtain the actual ambient temperature corresponding to the target virtual energy storage device;

[0228] Determine the heat loss value corresponding to the target virtual energy storage device according to the target device parameters to obtain the first heat loss value;

[0229] Determine the difference between the load temperature of the target virtual energy storage device and the actual ambient temperature to obtain the first temperature difference;

[0230] Determine the heat compensation value of the target virtual energy storage device according to the first temperature difference based on the mapping relationship between the preset temperature difference and heat compensation to obtain the first heat compensation value;

[0231] Determine the target heat loss value according to the first heat compensation value and the first heat loss value;

[0232] Determine the virtual energy storage parameters of the target virtual energy storage device based on the target heat loss value and the load temperature of the target virtual energy storage device.

[0233] In a possible embodiment, when the determining unit 820 determines the output model of the distributed power source according to the power consumption status data set and the first electricity price based on the preset second constraint condition to obtain the power output model, it is specifically used for:

[0234] Obtain the load demand of the target power consumption period from the power consumption status data set; the time length of the target power consumption period is a preset value; the preset time period includes the target power consumption period;

[0235] Determine the output demand of the distributed power source according to the load demand to obtain the power output demand;

[0236] Determine the mapping relationship between output and efficiency based on the power output demand of the power source to obtain the first mapping relationship;

[0237] Obtain the operating cost of the distributed power source and the electricity price corresponding to the target power consumption period to obtain the first operating cost and the target electricity price;

[0238] Determine the difference between the target electricity price and the first electricity price to obtain the first electricity price difference;

[0239] Determine the economic operation range of the distributed power source according to the first electricity price difference and the first operating cost to obtain the first economic operation range;

[0240] Determine the output model of the distributed power source based on the second constraint condition, the first economic operation range and the first mapping relationship to obtain the power output model.

[0241] In a possible embodiment, the control unit 830 is specifically configured to construct a user-side resource collaborative scheduling model based on the virtual energy storage model, the power output model, the first output model and the second output model:

[0242] Preprocess the first electricity price, the power consumption status data set and the operation status data set to obtain a target power data set;

[0243] Determine the first resource scheduling model based on a preset model coupling method, the virtual energy storage model and the power output model;

[0244] Optimize the parameters of the first resource scheduling model according to the target power data set to obtain the second resource scheduling model;

[0245] Determine the target resource scheduling model according to the second resource scheduling model, the first output model and the second output model;

[0246] Determine the user-side resource collaborative scheduling model according to the first constraint condition, the second constraint condition, the third constraint condition, the fourth constraint condition and the target resource scheduling model.

[0247] In a possible embodiment, the control unit 830 is specifically configured to determine the target resource scheduling model according to the second resource scheduling model, the first output model and the second output model:

[0248] Extract the constraint interval from the first output model to obtain the first constraint interval;

[0249] Extract the constraint interval from the second output model to obtain the second constraint interval;

[0250] Determine the constraint interval of the second resource scheduling model to obtain a third constraint interval;

[0251] Determine the target constraint interval according to the first constraint interval, the second constraint interval, and the third constraint interval;

[0252] Embed the first output model and the second output model into the second resource scheduling model to obtain a target embedded model;

[0253] Based on a preset dynamic programming algorithm, determine the target resource scheduling model according to the target constraint interval and the target embedded model.

[0254] In a possible embodiment, when the computing unit 840 solves the user-side resource collaborative scheduling model through a preset particle swarm optimization algorithm to obtain a target calculation result, it is specifically used for:

[0255] Obtain the new energy utilization rate corresponding to the new energy output data;

[0256] According to the first electricity price, obtain the electricity consumption cost of the target area distribution network to obtain a first electricity consumption cost;

[0257] Construct an optimization function according to the new energy utilization rate and the first electricity consumption cost to obtain a target optimization function;

[0258] Determine the model parameters corresponding to the user-side resource collaborative scheduling model to obtain n model parameters; n is an integer greater than 1;

[0259] Generate a first particle swarm according to the n model parameters, and initialize the initial position and initial velocity of each particle in the first particle swarm; the first particle swarm includes n particles; each particle corresponds to a model parameter;

[0260] Determine the fitness of each particle in the first particle swarm according to the target optimization function to obtain n particle fitnesses;

[0261] Determine the weight corresponding to each particle among the n particle fitnesses to obtain n weights;

[0262] Adjust the positions and velocities of the n particles according to the n weights to obtain n particle target positions and n particle target velocities;

[0263] Solve the n particle target positions and the n particle target velocities to obtain a second particle swarm; the second particle swarm includes: the positions of m particles and the velocities of m particles; m is a natural number greater than 1 and less than or equal to n;

[0264] Determine the fitness of each particle in the particle swarm according to the target optimization function and the second particle swarm, and obtain the fitness of m particles;

[0265] Based on the particle swarm algorithm and the fitness of the m particles, determine the optimal solution of the user-side resource collaborative scheduling model to obtain the target calculation result.

[0266] It can be seen that the user-side resource optimization scheduling device described in the embodiments of the present application comprehensively considers the virtual energy storage, energy storage system, power output of the power supply, and new energy output of the user-side resources for scheduling optimization, constructs a user-side resource collaborative optimization scheduling model, and solves it through an improved particle swarm algorithm. Finally, a user-side resource optimization scheduling method is obtained, thereby reducing power loss in the power system.

[0267] The embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute some or all of the steps of any method described in the above method embodiments. The above computer includes a server.

[0268] The embodiments of the present application also provide a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute some or all of the steps of any method described in the above method embodiments. The computer program product can be a software installation package, and the above computer includes a server.

[0269] It should be noted that for the above-mentioned embodiments, for the sake of simple description, they are all expressed as a series of action combinations. Those skilled in the art should know that the present application is not limited by the described action sequence, because some steps in the embodiments of the present application can be performed in other sequences or simultaneously. In addition, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions, steps, modules, or units involved are not necessarily essential to the embodiments of the present application.

[0270] In the above embodiments, the embodiments of the present application focus on different aspects of each embodiment. For parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0271] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by hardware instructed by a computer program. This program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. The aforementioned storage medium includes: various media that can store program codes such as ROM or random access memory RAM, magnetic disks, or optical discs.

[0272] The steps of the methods or algorithms described in the embodiments of the present application can be implemented in a hardware manner or by a processor executing software instructions. The software instructions can be composed of corresponding software modules. The software modules can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (EEPROM), registers, hard disks, removable hard disks, compact disc read-only memory (CD-ROM), or any other form of storage medium well-known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC. Additionally, the ASIC can be located in a terminal device or a management device. Of course, the processor and the storage medium can also exist as discrete components in the terminal device or the management device.

[0273] Those skilled in the art should be able to realize that in one or more of the above examples, the functions described in the embodiments of the present application can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. Each module / unit included in each device and product described in the above embodiments can be a software module / unit, a hardware module / unit, or can be partially a software module / unit and partially a hardware module / unit. For example, for each device and product applied to or integrated into a chip, each module / unit included therein can be implemented in the form of hardware such as circuits. Or, at least some of the modules / units can be implemented in the form of a software program that runs on a processor integrated inside the chip, and the remaining (if any) part of the modules / units can be implemented in the form of hardware such as circuits; for each device and product applied to or integrated into a chip module, each module / unit included therein can be implemented in the form of hardware such as circuits. Different modules / units can be located in the same component (such as a chip, a circuit module, etc.) or different components of the chip module. Or, at least some of the modules / units can be implemented in the form of a software program that runs on a processor integrated inside the chip module, and the remaining (if any) part of the modules / units can be implemented in the form of hardware such as circuits; for each device and product applied to or integrated into a terminal device, each module / unit included therein can be implemented in the form of hardware such as circuits. Different modules / units can be located in the same component (such as a chip, a circuit module, etc.) or different components inside the terminal device. Or, at least some of the modules / units can be implemented in the form of a software program that runs on a processor integrated inside the terminal device, and the remaining (if any) part of the modules / units can be implemented in the form of hardware such as circuits.

[0274] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of the embodiments of the present application. It should be understood that the above description is only the specific embodiments of the embodiments of the present application and is not used to limit the protection scope of the embodiments of the present application. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solutions of the embodiments of the present application should be included in the protection scope of the embodiments of the present application.

Claims

1. A method for optimizing the scheduling of user-side resources considering virtual energy storage, characterized in that Applied to a server, the method includes: Obtain the output data of the distribution network in the target area within a preset time period; the output data includes: new energy output data and energy storage system output data; Obtain the first electricity price, and determine the power consumption status data set and operation status data set of the user-side resources according to the first electricity price; Determine a virtual energy storage model based on a preset first constraint condition and the operation status data set; Determine a distributed power generation output model based on a preset second constraint condition, the power consumption status data, and the first electricity price, and obtain a power output model; Determine a first output model according to a preset third constraint condition and the new energy output data; the first output model is a new energy power generation output model; Determine a second output model according to a preset fourth constraint condition and the energy storage system output data; the second output model is an energy storage system output model; Construct a user-side resource collaborative scheduling model based on the virtual energy storage model, the power output model, the first output model, and the second output model; Solve the user-side resource collaborative scheduling model through a preset particle swarm optimization algorithm to obtain a target calculation result, and the target calculation result is used to configure the user-side resource collaborative scheduling model; Among them, the determining the virtual energy storage model based on the preset first constraint condition and the operation status data set includes: Obtain the temperature control devices in the distribution network of the target area to obtain k temperature control devices; k is a natural number greater than 1; Virtualize each of the k temperature control devices into a virtual energy storage device to obtain k virtual energy storage devices; Obtain the device parameters of each virtual energy storage device among the k virtual energy storage devices to obtain k device parameters; Determine k virtual energy storage parameters and k load temperatures according to the operation status data set and the k device parameters; Determine the virtual energy storage model based on the first constraint condition, the k virtual energy storage parameters, and the k load temperatures; Among them, the determining k virtual energy storage parameters and k load temperatures according to the operation status data set and the k device parameters includes: Obtain a target virtual energy storage device and its corresponding target device parameter; the target virtual energy storage device is any one of the k virtual energy storage devices; Determine the load temperature corresponding to the target virtual energy storage device according to the operation status data set to obtain the load temperature of the target virtual energy storage device; Obtain the actual ambient temperature corresponding to the target virtual energy storage device; Determine the heat loss value corresponding to the target virtual energy storage device according to the target device parameter to obtain a first heat loss value; Determine the difference between the load temperature of the target virtual energy storage device and the actual ambient temperature to obtain a first temperature difference; Determine the heat compensation value of the target virtual energy storage device according to the first temperature difference based on the mapping relationship between the preset temperature difference and heat compensation to obtain a first heat compensation value; Determine a target heat loss value according to the first heat compensation value and the first heat loss value; Determine the virtual energy storage parameters of the target virtual energy storage device based on the target heat loss value and the load temperature of the target virtual energy storage device; Among them, the method for determining the output model of the distributed power source according to the power consumption state data set and the first electricity price based on the preset second constraint condition, and obtaining the power output model includes: Obtain the load demand during the target power consumption period from the power consumption state data set; the time length of the target power consumption period is a preset value; the preset time period includes the target power consumption period; Determine the output demand of the distributed power source according to the load demand to obtain the power output demand; Based on the power output demand, determine the mapping relationship between output and efficiency to obtain the first mapping relationship; Obtain the operating cost of the distributed power source and the electricity price corresponding to the target power consumption period to obtain the first operating cost and the target electricity price; Determine the difference between the target electricity price and the first electricity price to obtain the first electricity price difference; According to the first electricity price difference and the first operating cost, determine the economic operating range of the distributed power source to obtain the first economic operating range; Based on the second constraint condition, the first economic operating range and the first mapping relationship, determine the output model of the distributed power source to obtain the power output model; Among them, the method for constructing the user-side resource collaborative scheduling model based on the virtual energy storage model, the power output model, the first output model and the second output model includes: Preprocess the first electricity price, the power consumption state data set and the operating state data set to obtain the target power data set; Based on the preset model coupling method, the virtual energy storage model and the power output model, determine the first resource scheduling model; Optimize the parameters of the first resource scheduling model according to the target power data set to obtain the second resource scheduling model; According to the second resource scheduling model, the first output model and the second output model, determine the target resource scheduling model; According to the first constraint condition, the second constraint condition, the third constraint condition, the fourth constraint condition and the target resource scheduling model, determine the user-side resource collaborative scheduling model.

2. The method according to claim 1, characterized in that, The method for determining the power consumption state data set and the operating state data set of the user-side resources according to the first electricity price includes: Obtain the historical power consumption data and historical electricity price of the target area distribution network; Train a preset machine learning model according to the historical power consumption data and the historical electricity price to obtain a power consumption and electricity price relationship model; Input the first electricity price into the power consumption and electricity price relationship model to obtain the first power consumption data; Obtain the electrical equipment in the user-side resources to obtain the first equipment set; Determine the power consumption distribution of the first equipment set according to the first power consumption data to obtain the first power consumption distribution set; Extract the power consumption corresponding to the first equipment set from the first power consumption data to obtain the first power consumption set; Determine the power consumption state data set according to the first power consumption distribution set and the first power consumption set; Determine the operating parameters of each device in the first device set to obtain the first operating parameter set; Determine the operating status data set corresponding to the first device set according to the first power consumption data set and the first operating parameter set.

3. The method according to claim 1, characterized in that, The determining the target resource scheduling model according to the second resource scheduling model, the first output model, and the second output model includes: Extract a constraint interval from the first output model to obtain a first constraint interval; Extract a constraint interval from the second output model to obtain a second constraint interval; Determine the constraint interval of the second resource scheduling model to obtain a third constraint interval; Determine a target constraint interval according to the first constraint interval, the second constraint interval, and the third constraint interval; Embed the first output model and the second output model into the second resource scheduling model to obtain a target embedding model; Determine the target resource scheduling model based on the preset dynamic programming algorithm according to the target constraint space and the target embedding model.

4. The method according to claim 1, wherein The obtaining the target calculation result by solving the user-side resource collaborative scheduling model through a preset particle swarm algorithm includes: Obtain the new energy utilization rate corresponding to the new energy output data; Obtain the electricity consumption cost of the target area distribution network according to the first electricity price to obtain a first electricity consumption cost; Construct an optimization function according to the new energy utilization rate and the first electricity consumption cost to obtain a target optimization function; Determine the model parameters corresponding to the user-side resource collaborative scheduling model to obtain n model parameters; n is an integer greater than 1; Generate a first particle swarm according to the n model parameters, and initialize the initial position and initial velocity of each particle in the first particle swarm; the first particle swarm includes n particles; each particle corresponds to a model parameter; Determine the fitness of each particle in the first particle swarm according to the target optimization function to obtain n particle fitnesses; Determine the weight corresponding to each particle among the n particle fitnesses to obtain n weights; Adjust the positions and velocities of the n particles according to the n weights to obtain n particle target positions and n particle target velocities; Solve the n particle target positions and the n particle target velocities to obtain a second particle swarm; the second particle swarm includes: the positions of m particles and the velocities of m particles; m is a natural number greater than 1 and less than or equal to n; Determine the fitness of each particle in the particle swarm according to the target optimization function and the second particle swarm to obtain m particle fitnesses; Determine the optimal solution of the user-side resource collaborative scheduling model based on the particle swarm algorithm and the m particle fitnesses to obtain the target calculation result.

5. An optimization scheduling device for user-side resources considering virtual energy storage, characterized in that, Applied to a server, the device includes: An acquisition unit, configured to acquire the output data of the target area distribution network within a preset time period; the output data includes: new energy output data and energy storage system output data; acquire a first electricity price, and determine the electricity consumption status data set and the operating status data set of the user-side resources according to the first electricity price. A determination unit, configured to determine a virtual energy storage model based on a preset first constraint condition and the operation status data set; determine a distributed power generation output model based on a preset second constraint condition, the power consumption status data, and the first electricity price, so as to obtain a power output model; determine a first output model according to a preset third constraint condition and the new energy output data; determine a second output model according to a preset fourth constraint condition and the energy storage system output data; the first output model is a new energy power generation output model; the second output model is an energy storage system output model; A control unit, configured to construct a user-side resource collaborative scheduling model based on the virtual energy storage model, the power output model, the first output model, and the second output model; A calculation unit, configured to solve the user-side resource collaborative scheduling model through a preset particle swarm optimization algorithm to obtain a target calculation result, and the target calculation result is used to configure the user-side resource collaborative scheduling model; Wherein, the determining k virtual energy storage parameters and k load temperatures according to the operation status data set and the k device parameters includes: Obtaining a target virtual energy storage device and its corresponding target device parameters; the target virtual energy storage device is any one of the k virtual energy storage devices; Determining the load temperature corresponding to the target virtual energy storage device according to the operation status data set to obtain the load temperature of the target virtual energy storage device; Obtaining the actual ambient temperature corresponding to the target virtual energy storage device; Determining the heat loss value corresponding to the target virtual energy storage device according to the target device parameters to obtain a first heat loss value; Determining the difference between the load temperature of the target virtual energy storage device and the actual ambient temperature to obtain a first temperature difference; Determining the heat compensation value of the target virtual energy storage device according to the first temperature difference based on a preset mapping relationship between the temperature difference and the heat compensation to obtain a first heat compensation value; Determining a target heat loss value according to the first heat compensation value and the first heat loss value; Determining the virtual energy storage parameters of the target virtual energy storage device based on the target heat loss value and the load temperature of the target virtual energy storage device; Wherein, the determining the power output model of the distributed power generation based on the power consumption status data set and the first electricity price according to a preset second constraint condition to obtain a power output model includes: Obtaining the load demand of a target power consumption period from the power consumption status data set; the time length of the target power consumption period is a preset value; the preset time period includes the target power consumption period; Determining the power output demand of the distributed power generation according to the load demand to obtain a power output demand; Determining a mapping relationship between the power output and the efficiency based on the power output demand to obtain a first mapping relationship; Obtaining the operation cost of the distributed power generation and the electricity price corresponding to the target power consumption period to obtain a first operation cost and a target electricity price; Determining the difference between the target electricity price and the first electricity price to obtain a first electricity price difference; Determining the economic operation range of the distributed power generation according to the first electricity price difference and the first operation cost to obtain a first economic operation range; Determine the output model of the distributed power source based on the second constraint condition, the first economic operation range, and the first mapping relationship to obtain the power output model; Among them, the construction of the user-side resource collaborative scheduling model based on the virtual energy storage model, the power output model, the first output model, and the second output model includes: Preprocess the first electricity price, the electricity consumption status data set, and the operation status data set to obtain a target power data set; Determine the first resource scheduling model based on a preset model coupling method, the virtual energy storage model, and the power output model; Optimize the parameters of the first resource scheduling model according to the target power data set to obtain a second resource scheduling model; Determine the target resource scheduling model according to the second resource scheduling model, the first output model, and the second output model; Determine the user-side resource collaborative scheduling model according to the first constraint condition, the second constraint condition, the third constraint condition, the fourth constraint condition, and the target resource scheduling model.

6. A server, characterized in that, Including: A processor, a memory, a communication interface, and one or more programs; The one or more programs are stored in the memory and are configured to be executed by the processor. The programs include instructions for performing the steps in the method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by the processor, the processor is caused to execute the method according to any one of claims 1-4.

Images