Intelligent electric vehicle scheduling method and system based on element cosmic source network load storage

Abstract

The invention discloses an intelligent electric vehicle scheduling method and system based on element cosmic source network load storage. The method comprises the following steps: collecting real-time data of the electric vehicle through digital equipment, and transmitting the real-time data to a remote service platform through a vehicle-mounted terminal and a wireless communication network; the charging cost is determined according to the real-time data of the electric vehicle and a target input by a user, an electric vehicle charging and discharging strategy based on intelligent scheduling is constructed in a scheduling center in combination with the real-time state of a power grid, and a charging and discharging time window and power of the electric vehicle are dynamically planned; performing real-time optimization on the electric vehicles in the schedulable state in each time period; through day-ahead, intra-day and real-time multi-time-scale optimization, an active power distribution network multi-time-scale scheduling model based on source-network-load-storage cooperation is established, an entropy weight method is adopted to convert a multi-target problem into a single target for solving, and an optimal boundary constraint, reference electricity price and load guide strategy is obtained; and pushing personalized charging and discharging suggestions to a user through a mobile application or a vehicle-mounted system based on the intelligent scheduling electric vehicle charging and discharging strategy and the optimal boundary constraint and by referring to the electricity price and load guide strategy, and when the user transmits feedback information to a scheduling center, dynamically adjusting the charging and discharging strategy by the scheduling center.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent scheduling of electric vehicles, and in particular relates to an intelligent scheduling method and system for electric vehicles based on metaverse source, grid, load and storage. Background Art

[0002] In the transportation sector, electric vehicles (EVs) are becoming the key to future transportation due to their zero emissions, low noise, and high efficiency. However, as the number of EVs increases, their charging needs pose challenges to the stability and economic viability of the power grid.

[0003] Existing technical approaches for electric vehicle dispatch centers primarily rely on a single energy management framework, making it difficult to balance long-term planning with short-term adjustments. When intraday load forecasts deviate significantly, dispatch strategies based on a single time scale cannot be adjusted promptly, resulting in significant deviations from real-time operating conditions, increasing system energy consumption and operating costs. Furthermore, existing dispatch optimization algorithms lack dynamic response mechanisms to individual user needs, failing to fully utilize electric vehicles as mobile energy storage units for peak load shaving and price arbitrage, further reducing overall system profitability.

[0004] Therefore, existing technologies are unable to effectively cope with the dynamic optimization needs of electric vehicle charging and discharging in new energy scenarios with high-frequency fluctuations, which affects the economy and flexibility of the dispatching center. Summary of the Invention

[0005] To address the deficiencies in the prior art, the present invention provides a method and system for intelligent scheduling of electric vehicles based on Metaverse source-grid-load-storage. Through advanced digital technology and intelligent algorithms, electric vehicles are used as distributed energy storage units, working in conjunction with energy storage devices in the power grid to achieve optimized scheduling. Electric vehicles can be directed to discharge during peak load periods and charged during off-peak periods, thereby achieving peak load shaving and valley filling, improving grid operation efficiency. Furthermore, by combining Internet of Vehicles technology and big data analysis, the charging status of electric vehicles and grid load conditions can be monitored in real time, and charging power and time can be dynamically adjusted, providing important data support for grid planning and scheduling.

[0006] In order to solve the above technical problems, the present invention adopts the following technical solutions.

[0007] The present invention first discloses an electric vehicle intelligent scheduling method based on Metaverse source-grid-load-storage, which includes the following steps:

[0008] Step 1: Collect real-time data of electric vehicles through digital equipment and transmit it to the remote service platform through the vehicle terminal and wireless communication network;

[0009] Step 2: Based on the real-time data of the electric vehicle and the user-entered target, the charging cost is determined. The dispatch center combines the real-time status of the power grid to build an electric vehicle charging and discharging strategy based on intelligent scheduling, dynamically plans the charging and discharging time windows and power of the electric vehicle, and performs real-time optimization on the electric vehicles that are in a dispatchable state in each time period;

[0010] Step 3: Through day-ahead, intraday, and real-time multi-timescale optimization, a multi-timescale dispatch model for the active distribution network based on source-grid-load-storage collaboration is established. The entropy weight method is used to transform the multi-objective problem into a single objective for solution, and the optimal boundary constraints, reference electricity price, and load guidance strategy are obtained.

[0011] Step 4: Based on the intelligently dispatched electric vehicle charging and discharging strategy and the optimal boundary constraint, reference electricity price, and load guidance strategy, personalized charging and discharging recommendations are pushed to users via mobile applications or vehicle-mounted systems. When users transmit feedback information to the dispatch center, the dispatch center dynamically adjusts the charging and discharging strategies.

[0012] The present invention further includes the following preferred embodiments:

[0013] The electric vehicle charging and discharging strategy based on intelligent scheduling is constructed in the dispatching center in combination with the real-time status of the power grid, further comprising:

[0014] Divide a day into T time periods of unit length τ, and update the data of all connected electric vehicles at the beginning of each time period:

[0015]

[0016] in, is the dispatchable time of the i-th electric vehicle, The time of joining the network, The target off-grid time set for the user;

[0017] The charge and discharge plan of electric vehicles in a scheduling cycle is represented by an N×T matrix X:

[0018]

[0019] Among them, x i，t is the charging and discharging power of the i-th electric vehicle in time period t, x i，t >0 means charging, x i，t <0 indicates discharge, T is the maximum time length;

[0020] For N V2G and N CHAR The vehicles satisfy the following requirements:

[0021]

[0022] Among them, P char is the maximum charging power, P dis is the maximum discharge power; N V2G The number of N electric vehicles connected to the grid that support vehicle-grid interaction is recorded as, N CHAR is the number of vehicles that only support charging, and the proportion of vehicles that support V2G is γ, that is, N V2G =γN;

[0023] The initial power of the electric vehicle when it is connected to the grid Expressed as:

[0024]

[0025] in, The maximum capacity of electric vehicle batteries;

[0026] Assume that the target power set by the user for the electric vehicle is When off-grid, the battery capacity meets the following requirements:

[0027]

[0028] At the same time, the battery power at any time within the dispatchable time meets the following requirements:

[0029]

[0030] The determining of the charging cost further includes:

[0031] Assuming that the charging and discharging behavior remains unchanged within a unit time period, calculate the comprehensive load of electric vehicles connected to the grid

[0032]

[0033] Assume that the basic load of other electrical equipment, excluding electric vehicles, is The basic load remains unchanged in the unit time period, and the total load z is calculated. t :

[0034]

[0035] The system real-time electricity price is a linear change of the total load in each time period, that is:

[0036] g(z t )=k0+k1z t

[0037] Among them, g(z t) is the electricity price in time period t, and the charging cost of electric vehicles is calculated. k0 represents the fixed electricity price benchmark of the system, and k1 represents the electricity price variation coefficient caused by unit load:

[0038]

[0039] Calculate the total cost of charging an electric vehicle:

[0040]

[0041] The real-time optimization of the electric vehicles in the dispatchable state in each time period further includes:

[0042] The dispatch center calculates the dispatch strategy at the beginning of each time period and publishes it to the electric vehicles. The total number of dispatchable vehicles in time period t is N′, which can be divided into two categories. One category is electric vehicles that have been connected to the network for a certain period of time, namely One category is electric vehicles that are connected to the grid during this period, namely Calculate the remaining schedulable time

[0043]

[0044] The optimization range is changed dynamically, and the size of the optimization range is the maximum value of the remaining dispatchable time of the dispatchable vehicles in the current time period:

[0045]

[0046] Among them, W t is the optimization range of time period t;

[0047] The length of the scheduling strategy calculated for each time period is the corresponding optimization time window, and the electric vehicle uses the header of the received scheduling strategy as the charging and discharging strategy for the current time period.

[0048] The construction of an electric vehicle charging and discharging strategy based on intelligent scheduling further includes:

[0049] Calculate the network loss sensitivity PLS of node m m :

[0050]

[0051] Where S represents the network loss and P represents the active power injected by the node; the partial differential of the network loss with respect to the active power is obtained:

[0052]

[0053] Where Q is the reactive power injected into the node, |V| and θ are the amplitude and phase angle of the node voltage;

[0054] Calculate the network loss cost, i.e. the network loss sensitivity index J2:

[0055]

[0056] in, is the total load of electric vehicles on node m, k2 is the conversion coefficient, and M is the total number of nodes in the network;

[0057] Minimizing the total cost is the algorithm goal:

[0058]

[0059] subject to:

[0060]

[0061] The establishment of a multi-time-scale scheduling model for an active distribution network based on source-grid-load-storage collaboration further includes:

[0062] Taking the distribution network's scheduling cost as the minimum in the entire scheduling cycle as the goal, the planned output of each scheduling resource is determined. The objective function is:

[0063]

[0064] Among them, C pure，t is the electricity purchase cost of the distribution network during period t, C ope，t 、C comp，t are the operating cost of the distribution network in period t and the calling cost paid by the distribution network to the load; C dis，t is the cost of curtailing wind and solar power during period t;

[0065] The power purchase cost of the distribution network is C pure，t for:

[0066] C pure，t =ρ grid，t P grid，t

[0067] Among them, ρ grid，t and P grid，t are the unit price and quantity of electricity purchased by the distribution network from the upper power grid during period t respectively;

[0068] Distribution network operating cost C ope，t The cost of DG operation is C dg，t MT operating cost C mt，t and the operating cost of ES C es，t It consists of 3 parts:

[0069]

[0070] Among them, ρ dg，t and Pdg，t is the DG unit electricity operation cost and power generation; ρ mt，t and P mt，t is the operating cost and power generation per MT unit of electricity; a es，c 、b es，c 、a es，d 、b es，d and c es is the equipment consumption parameter of ES, P es，c，t and P es，d，t is the ES charging and discharging power during period t;

[0071] Among them, the calling cost C paid by the distribution network to the load is comp，t for:

[0072] C comp，t =ρ A，dr，t P A，int，t +ρ B，dr，t P B，con，t +ρ C，dr，t P C，con，t

[0073] ρ A,dr,t , ρ B,dr,t , ρ C,dr,t Respectively represent the unit call compensation price of Class A, Class B, and Class C loads; P A,int,t 、P B,con,t 、P C,con,t They represent the control call power of type A, type B, and type C loads in time period t respectively;

[0074] Among them, the cost of curtailing wind and solar power is C dis，t for:

[0075] C dis，t =ρ dis，t ΔP dis，t

[0076] Among them, ρ dis，t , ΔP dis，t They are the unit electricity curtailment cost and amount of curtailment in period t respectively.

[0077] The establishment of a multi-time-scale scheduling model for an active distribution network based on source-grid-load-storage collaboration further includes:

[0078] Increase EV dispatch cost C ev，t :

[0079]

[0080] Among them, α ev，c，t , α ev，d，t and Compensate for EV charging and discharging electricity prices and participate in grid dispatching;

[0081] The economic benefits of EVs are calculated based on the changes in electricity purchase costs before and after EVs respond to grid dispatch:

[0082]

[0083] Among them, ρ ev，t is the EV charging electricity price during period t; It represents the charging power of electric vehicles in response to scheduling during time period t, that is, the part directly controlled by the dispatch center and involved in optimization; represents the total charging power of all electric vehicles in time period t;

[0084] The DG utilization rate is expressed as the ratio of DG consumption to total DG power generation within the dispatch period:

[0085]

[0086] The comprehensive objective function is:

[0087] minf=min(λ1f1-λ2f2+λ3f3)

[0088] Among them, λ1, λ2, and λ3 are weight coefficients.

[0089] The present invention also discloses an electric vehicle intelligent dispatching system based on Metaverse source, grid, load and storage, which utilizes the aforementioned electric vehicle intelligent dispatching method based on Metaverse source, grid, load and storage, including:

[0090] A real-time data collection module is used to collect real-time data of electric vehicles through digital devices and transmit it to the remote service platform through the vehicle terminal and wireless communication network;

[0091] An electric vehicle charging and discharging strategy construction module is used to determine the charging cost based on the real-time data of the electric vehicle and the user-entered target, and to construct an electric vehicle charging and discharging strategy based on intelligent scheduling in the dispatch center in combination with the real-time status of the power grid, dynamically plan the charging and discharging time windows and power of the electric vehicle, and perform real-time optimization on the electric vehicles that are in a dispatchable state in each time period;

[0092] The multi-timescale scheduling module is used to establish a multi-timescale scheduling model for active distribution networks based on source-grid-load-storage collaboration through day-ahead, intraday, and real-time multi-timescale optimization. The entropy weight method is used to transform the multi-objective problem into a single objective for solution, and the optimal boundary constraints, reference electricity price, and load guidance strategy are obtained.

[0093] A user feedback module is used to push personalized charging and discharging recommendations to users through mobile applications or vehicle systems based on the intelligently scheduled electric vehicle charging and discharging strategy and the optimal boundary constraints, reference electricity prices, and load guidance strategies. When users transmit feedback information to the dispatch center, the dispatch center dynamically adjusts the charging and discharging strategies.

[0094] Accordingly, the present application also discloses a terminal, including a processor and a storage medium;

[0095] The storage medium is used to store instructions;

[0096] The processor is used to operate according to the instructions to execute the steps of the aforementioned electric vehicle intelligent scheduling method based on metaverse source, grid, load and storage.

[0097] Accordingly, the present application also discloses a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the aforementioned intelligent scheduling method for electric vehicles based on metaverse source, grid, load and storage are implemented.

[0098] The beneficial effect of the present invention is that, compared with the prior art, the present invention provides an intelligent scheduling method and system for electric vehicles based on the metaverse source, grid, load and storage. Based on the source, grid, load and storage collaborative optimization scheduling model, the entropy weight method is used to distribute weights for multi-objective optimization problems, thereby realizing dynamic regulation of electric vehicles, energy storage equipment and distributed power sources, effectively reducing system operating costs and improving system operating efficiency; based on real-time algorithms and rolling optimization mechanisms, in the scenario of new energy power generation fluctuations, a time-sharing scheduling strategy for electric vehicles is constructed to realize dynamic adjustment of the charging and discharging process, reduce load peak-valley differences, and reduce grid scheduling pressure; combined with user interaction and feedback mechanisms, the system can dynamically optimize the charging and discharging strategy according to user needs, while meeting user power needs, improving the flexibility of electric vehicles as energy storage units to participate in peak shaving and valley filling in the grid; by integrating electric vehicle data acquisition modules, scheduling optimization modules and user interaction modules, the system can effectively realize multi-dimensional collaborative optimization between electric vehicles, energy storage equipment and power grids, build an intelligent scheduling platform, and improve the overall economy and stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0099] Figure 1 This is a framework diagram of the digital source-grid-load-storage electric vehicle intelligent dispatching system in the present invention;

[0100] Figure 2 This is a framework diagram of the electric vehicle data acquisition system in the present invention;

[0101] Figure 3 It is a scheduling strategy diagram for each time period in the present invention;

[0102] Figure 4This is the flow chart of the intraday scheduling rolling optimization calculation solution in the present invention. DETAILED DESCRIPTION

[0103] In order to make the purpose, technical solutions and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0104] The embodiments described in this application are only part of the embodiments of the present invention, not all of the embodiments. Based on the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without making creative work are all within the scope of protection of the present invention.

[0105] As mentioned earlier, traditional charging methods are unorganized and lack interaction with the grid, leading to increased grid load fluctuations. This can cause localized overloads, particularly during peak hours, and impact grid security. Furthermore, the energy storage potential of electric vehicles is underutilized, preventing them from effectively participating in grid services such as peak load shaving and valley shifting, frequency and voltage regulation, and increasing the complexity and cost of grid operations.

[0106] To address the shortcomings of existing technologies, this invention proposes a method and system for intelligent dispatching of electric vehicles based on a Metaverse-based source-grid-load-storage system. First, digital devices collect real-time data from electric vehicles, including vehicle operating status, battery charge level, charging requirements, and location information. This data is transmitted to a remote service platform via an onboard terminal and wireless communication network, providing basic data support for subsequent intelligent dispatching. An intelligent dispatch-based charging and discharging strategy for electric vehicles is then formulated. Based on the user-input off-grid time and target power level, combined with the real-time status of the grid, the dispatch center dynamically plans charging and discharging time windows and power levels for electric vehicles, optimizing the dispatchable electric vehicles within each time period in real time. This strategy uses an optimization algorithm to ensure that user needs are met while minimizing grid impact and achieving peak load shifting. Then, a multi-timescale dispatching model for an active distribution network based on source-grid-load-storage collaboration is established. This model coordinates resources such as the upper-level grid, energy storage equipment, flexible loads, and electric vehicles through day-ahead, intraday, and real-time rolling optimization, optimizing dispatching costs and improving the utilization of distributed generation resources. The model uses an entropy weighting method to transform a multi-objective problem into a single-objective solution, ensuring the real-time and adaptable nature of the dispatching strategy. A flexible user interaction and feedback mechanism is also implemented. Based on the intelligently dispatched EV charging and discharging strategy and the optimal boundary constraints, reference electricity price, and load guidance strategy, personalized charging and discharging recommendations are pushed to users via mobile apps or onboard systems. Users can adjust these recommendations based on their needs and transmit feedback to the dispatch center in real time. The dispatch center dynamically adjusts the strategy based on user feedback to ensure that EV charging and discharging behavior matches the stability and economic efficiency of grid operation.

[0107] See also Figure 1As shown, the electric vehicle intelligent scheduling method based on Metaverse source-grid-load-storage disclosed in the present invention includes the following steps:

[0108] Step 1: Collect real-time data of electric vehicles through digital devices and transmit it to the remote service platform through the on-board terminal and wireless communication network.

[0109] See also Figure 2 The real-time data collection system for electric vehicles consists of three parts: an on-board terminal, a wireless communication network, and a remote service platform. Real-time data from electric vehicles is collected, including vehicle operating status, battery charge, charging requirements, and location information. These data are transmitted to the remote service platform via the on-board terminal and wireless communication network, providing basic data support for subsequent intelligent scheduling. The on-board terminal is installed on the electric vehicle and is used to collect, store, and transmit key status data of the entire vehicle and system components, such as electric vehicle operation, charging, and positioning. At the same time, it sends the data to the remote service platform through its built-in communication module. The wireless communication network transmits the data sent by the on-board terminal to the remote service platform server; the remote service platform is responsible for receiving the data sent by the on-board terminal and displaying it on the display screen after conversion according to the corresponding protocol rules. Among them, the remote service platform provides edge computing and cloud data synchronization functions, providing the dispatch center with structured and timely electric vehicle operation data. The dispatch center further performs real-time optimization and strategy generation based on this data.

[0110] Step 2: Based on the real-time data of the electric vehicle and the user-entered target, the charging cost is determined. In the dispatch center, a charging and discharging strategy for the electric vehicle based on intelligent scheduling is constructed in combination with the real-time status of the power grid. The charging and discharging time windows and power of the electric vehicle are dynamically planned, and the electric vehicles in the dispatchable state in each time period are optimized in real time.

[0111] The dispatch center dynamically plans the charging and discharging time windows and power consumption of electric vehicles based on the user's input off-grid time and target power consumption, combined with the real-time status of the power grid. This strategy optimizes the number of electric vehicles available for dispatch within each time period in real time. This strategy uses an optimization algorithm to ensure that while meeting user needs, it also reduces the impact on the power grid and achieves peak load shifting. Step 2 specifically includes the following steps:

[0112] In step 2.1, the dispatch center formulates and implements the electric vehicle dispatch strategy. The dispatch center is the information center responsible for facilitating the coordination of electric vehicles and the power grid within the region, with the capabilities to collect, distribute information, and perform calculations. Once connected to the grid, electric vehicles are subject to centralized dispatch from the dispatch center. After connecting an electric vehicle to the grid, users must set an off-grid time and target power level for their vehicle and upload this information, along with data such as the vehicle's initial power level, to the dispatch center. While connected to the grid, electric vehicles are dispatchable, and their charging and discharging behavior is controlled by the dispatch center. The dispatch center formulates a charging and discharging dispatch strategy, ensuring that all vehicle charging tasks are completed on time, and disconnects electric vehicles from the grid when their off-grid time is reached.

[0113] See also Figure 3 The dispatch center has a dispatch cycle of one day, which is divided into T time periods of unit length τ. The dispatch center updates the data of all electric vehicles connected to the network at the beginning of each time period. The information submitted by electric vehicles when they join the network can be obtained:

[0114]

[0115] in, is the dispatchable time of the i-th electric vehicle, The time of joining the network, The target off-grid time set for the user.

[0116] Among the N electric vehicles connected to the grid, only a portion of them support vehicle-to-grid (V2G), and the number is N. V2G , the remaining vehicles only support charging, the number is recorded as N CHAR The proportion of vehicles supporting V2G is γ, that is

[0117] N V2G =γN

[0118] The charge and discharge planning of electric vehicles in a scheduling cycle is represented by an N×T matrix X.

[0119]

[0120] Among them, x i，t is the charging and discharging power (kW) of the i-th electric vehicle in time period t, x i，t >0 means charging, x i，t <0 indicates discharge, and T is the maximum time length.

[0121] For N V2G and N CHAR The vehicles satisfy the following requirements:

[0122]

[0123] Among them, P char is the maximum charging power, P dis is the maximum discharge power.

[0124] Initial power of electric vehicles when they are connected to the grid for:

[0125]

[0126] in, The maximum capacity of an electric vehicle battery.

[0127] The target power set by the user for the electric vehicle is When off-grid, the battery capacity meets the following requirements:

[0128]

[0129] At the same time, the battery power at any time within the dispatchable time meets the following requirements:

[0130]

[0131] Among them, t q Indicates any moment in the scheduling cycle.

[0132] Step 2.2: Analyze the charging cost. The charging cost is the comprehensive electricity purchase cost after a series of power exchanges between the dispatch center and the power grid. Different electric vehicles have different charging and discharging behaviors in different time periods. Assuming that the charging and discharging behaviors remain unchanged in a unit time period, the comprehensive load of the electric vehicles connected to the grid is for:

[0133]

[0134] The basic load of other electrical equipment excluding electric vehicles is Assuming that the base load remains unchanged within the unit time period, the total load z t for:

[0135]

[0136] The system real-time electricity price is a linear change of the total load in each time period, that is:

[0137] g(z t )=k0+k1z t

[0138] Among them, g(z t) is the electricity price in time period t, k0 represents the fixed electricity price benchmark item of the system (yuan / kWh), and k1 represents the electricity price variation coefficient caused by unit load (yuan / kWh2).

[0139] The cost of charging an electric vehicle is:

[0140]

[0141] The total cost of charging an electric vehicle is:

[0142]

[0143] Step 2.3, adjust the optimization range of the real-time algorithm.

[0144] A global algorithm's prerequisite for achieving the optimal scheduling strategy is accurate, all-day forecast data for electric vehicles. However, the time an electric vehicle connects to the grid and its initial state are highly random, making it unsuitable for global algorithms. The real-time scheduling strategy employed in this invention does not require all-day forecasts for electric vehicles. Instead, it optimizes the dispatchable electric vehicles in each time period in real time to arrive at the optimal scheduling solution for the current time period.

[0145] The dispatch center calculates the dispatch strategy at the beginning of each time period and publishes it to the electric vehicles. Let the total number of dispatchable vehicles in time period t be N′, which can be divided into two categories: one is the electric vehicles that have been connected to the network for a certain period of time, that is, One category is electric vehicles that are connected to the grid during this period, namely Their remaining schedulable time is

[0146]

[0147] In order to make the real-time algorithm's charge and discharge planning fully compatible with the base load changes within a certain period of time, its optimization range changes dynamically. The size of the optimization range is the maximum value of the remaining dispatchable time of the dispatchable vehicles in the current time period:

[0148]

[0149] Among them, W t is the optimization range of time period t.

[0150] The length of the scheduling strategy calculated for each time period is the corresponding optimization time window. The electric vehicle will use the header of the received scheduling strategy as the charging and discharging strategy for the current time period. The scheduling strategy for the whole day is composed of these parts.

[0151] Step 2.4, calculate the network loss sensitivity index.

[0152] The grid loss costs caused by electric vehicle charging and discharging are closely related to node performance. Furthermore, during the optimization iteration process, the dispatching strategy allocates different loads to each node. Calculating grid losses directly through power flow calculations significantly increases the optimization process time, preventing the dispatch center from providing timely charging and discharging plans to all electric vehicle users. Therefore, Power Loss Sensitivity (PLS) is being considered as an auxiliary tool for decision-making.

[0153] Grid loss sensitivity indicates the sensitivity of grid loss to node power injection. Macroscopically, it can be considered the magnitude of grid loss caused by an increase in unit load at a grid node. To calculate grid loss sensitivity, first distribute the base load for the current time period to the grid, then calculate the partial differential of grid loss with respect to node active power. The expression is:

[0154]

[0155] Among them, PLS m is the network loss sensitivity of node m, S represents the network loss, and P represents the active power injected by the node. According to the Jacobian matrix in the power flow calculation, the partial differential of the network loss with respect to the active power can be obtained as follows:

[0156]

[0157] Where Q is the reactive power injected into the node, |V| and θ are the amplitude and phase angle of the node voltage.

[0158] Therefore, the network loss cost is the network loss sensitivity index J2, as shown in the following formula:

[0159]

[0160] in, is the total load of electric vehicles on node m, k2 is the conversion coefficient, and M is the total number of nodes in the network.

[0161] Furthermore, grid loss sensitivity is calculated based on the grid baseload, meaning each time period corresponds to a set of grid loss sensitivities. Because the dispatch strategy uses day-ahead forecasts for the baseload, grid loss sensitivities for all time periods can be calculated offline before daily dispatch begins. Subsequent optimization calculations require only the charging and discharging behavior of electric vehicles at the corresponding nodes, eliminating the need for repeated power flow calculations.

[0162] In step 2.5, under the premise of ensuring the completion of the electric vehicle charging and discharging tasks, the algorithm objective is to minimize the total cost. The optimization problem is expressed as follows:

[0163]

[0164] The following constraints are met:

[0165]

[0166] Step 3: Through day-ahead, intraday, and real-time multi-time-scale optimization, a multi-time-scale scheduling model for active distribution networks based on source-grid-load-storage collaboration is established. The entropy weight method is used to transform the multi-objective problem into a single objective for solution, and the optimal boundary constraints, reference electricity price, and load guidance strategy are obtained.

[0167] The intelligent electric vehicle dispatch strategy in step 2 is a real-time optimization strategy at the vehicle level, combining user objectives and the current state of the power grid. To further improve the system's global dispatch performance, a unified multi-timescale optimization model must be constructed at a higher level to serve as the boundary input for local vehicle dispatch. To this end, a multi-timescale dispatch model for active distribution networks is constructed based on the perspective of source-grid-load-storage synergy. This model achieves rolling coordination across three timescales: day-ahead, intraday, and real-time, improving overall resource utilization efficiency and dispatch economy. Through rolling optimization across day-ahead, intraday, and real-time, this multi-timescale dispatch model coordinates resources such as the upper-level power grid, energy storage equipment, flexible loads, and electric vehicles, optimizing dispatch costs and improving the utilization of distributed generation. An entropy weighting method is used to transform the multi-objective problem into a single-objective solution, ensuring the real-time and adaptable dispatch strategy.

[0168] The active distribution network dispatch center coordinates the upstream power grid, micro-turbines (MT), energy storage (ES), flexible loads, and electric vehicles (EVs). Through multi-timescale optimization (day-ahead, intraday, and real-time), it gradually reduces the impact of distributed generation (DG) and load forecast deviations on the system power balance. Because the change in user electricity consumption habits and the formulation of electricity prices are long-term processes, price-based user-side demand response (DR) is applied on the day-ahead basis. Figure 4 During the intraday phase, incentive policies are used to guide EVs to coordinate ES and MT to achieve DG consumption and peak-shaving and valley-filling. DR users participating in the incentive are first classified according to their operating characteristics, and then participate in scheduling at different time scales based on the classification. Step 3 specifically includes the following steps:

[0169] Step 3.1: Build a day-ahead scheduling model.

[0170] The day-ahead dispatch cycle is 24 hours, with a time interval of 1 hour. Based on the DG output and load demand, the planned output of each dispatch resource is determined with the goal of minimizing the dispatch cost of the distribution network during the entire dispatch cycle. The objective function is:

[0171]

[0172] Among them, C pure，t is the electricity purchase cost of the distribution network during period t, C ope，t 、C comp，t are the operating cost of the distribution network in period t and the calling cost paid by the distribution network to the load; C dis，t is the cost of curtailing wind and solar power during period t.

[0173] The power purchase cost of the distribution network is C pure，t for:

[0174] C pure，t =ρ grid，t P grid，t

[0175] Among them, ρ grid，t and P grid，t are the unit price and quantity of electricity purchased by the distribution network from the upper power grid during period t respectively.

[0176] Distribution network operating cost C ope，t The cost of DG operation is C dg，t MT operating cost C mt，t and the operating cost of ES C es，t It consists of 3 parts:

[0177]

[0178] Among them, ρ dg，t and P dg，t is the DG unit electricity operation cost and power generation; ρ mt，t and P mt，t is the operating cost and power generation per MT unit of electricity; a es，c 、b es，c 、a es，d 、b es，d and c es is the equipment consumption parameter of ES, P es，c，t and P es，d，t is the charging and discharging power of ES during period t.

[0179] Among them, the calling cost C paid by the distribution network to the load is comp，t for:

[0180] C comp，t =ρ A，dr，t P A，int，t +ρ B，dr，t P B，con，t +ρ C，dr，t P C，con，t

[0181] ρ A,dr,t , ρ B,dr,t , ρC,dr,t Respectively represent the unit call compensation electricity price (yuan / kWh) of Class A, Class B, and Class C loads; P B,con,t 、P C,con,t Respectively represent the control call power (kW) of type A, type B, and type C loads in time period t.

[0182] Among them, the cost of curtailing wind and solar power is C dis，t for

[0183] C dis，t =ρ dis，t ΔP dis，t

[0184] Among them, ρ dis，t , ΔP dis，t They are the unit electricity curtailment cost and amount of curtailment in period t respectively.

[0185] Model constraints include:

[0186] (1) Power balance constraints:

[0187]

[0188] in, Provides disorderly charging power for EVs.

[0189] (2) ES operation constraints, satisfying capacity, charge and discharge mutual exclusion and maximum charge and discharge constraints:

[0190]

[0191] Among them, E es，t 、E es，t-1 and η es，c ,η es，d is the storage capacity and charge-discharge efficiency of ES at time t and t-1; P es，min 、P es，max E is the upper and lower limits of ES charging and discharging power; es，t0 、E es，T E is the storage capacity at the beginning and end of the ES dispatch period; es，min 、E es，max The minimum and maximum storage capacity.

[0192] (3)MT operation constraints:

[0193]

[0194] Among them, P mt，max 、P mt，min and P mt+ 、P mt- They are the upper and lower limits of MT output and climbing power respectively.

[0195] (4) Energy transmission constraints with the upper power grid:

[0196] 0≤P grid，t ≤P grid，max

[0197] Among them, P grid，max It is the maximum transmission power between the distribution network and the upper-level power grid.

[0198] (5) Load adjustment constraints:

[0199] 0≤P A，int，t ≤P A，int，max

[0200] Among them, P A，int，max The maximum adjustment that can interrupt the load.

[0201] Step 3.2: Build an intraday scheduling rolling model.

[0202] Intraday scheduling is based on day-ahead planning, taking into account the distribution network, EV economics, and DG utilization. A multi-objective coordinated scheduling model for the active distribution network, combining source, grid, load, and storage, is established. While ensuring power balance, a rolling optimization algorithm is used, with a 4-hour lead time and rolling updates every 15 minutes.

[0203] (1) The economic efficiency of the distribution network is consistent with the day-ahead target in principle, and increases the EV dispatch cost C ev，t :

[0204]

[0205] Among them, α ev，c，t , α ev，d，t and Compensate for the electricity price of EV charging and discharging and the charging and discharging volume participating in grid dispatch.

[0206] The calculation formulas for the remaining costs are the same as those for day-ahead scheduling.

[0207] (2) The economic efficiency of EV can be reflected by the change in electricity purchase cost before and after EV responds to grid dispatch. The economic efficiency of EV can be given by the following formula:

[0208]

[0209] Among them, ρ ev，t is the EV charging electricity price during period t; represents the charging power (kW) of electric vehicles in response to scheduling in time period t, that is, the part directly controlled by the dispatch center and involved in optimization; Represents the total charging power (kW) of all electric vehicles in time period t.

[0210] (3) The DG utilization rate is expressed as the ratio of DG consumption to DG power generation during the dispatch period, which is expressed as:

[0211]

[0212] The comprehensive objective function is:

[0213] minf=min(λ1f1-λ2f2+λ3f3)

[0214] Among them, λ1, λ2, and λ3 are weight coefficients.

[0215] The model constraints are as follows:

[0216] (1) Power level constraint

[0217]

[0218] in, Charging power for EVs not participating in the dispatch; It represents the portion of EV charging power (kW) still under the control of the dispatch center after the user feedback strategy is adjusted during time period t to ensure load balance.

[0219] (2) Load adjustment constraints

[0220] 0≤P B，con，t ≤P B，con，max

[0221] Among them, P B，con，max It is the maximum adjustment amount for directly controlling load B.

[0222] (3)EV constraints

[0223] The time when EV is connected to the grid is random. By statistically analyzing the historical charging data of EV, the initial state of charge of the mth EV is obtained. Time of entering and leaving the network and

[0224]

[0225] Where: It is the dwell time of EV connected to the grid, i.e., the dispatch period; and is the storage capacity of the mth EV in period t and period t-1; and η ev，c ,η ev，d is the planned charging and discharging power and efficiency of the mth EV in period t; and is the initial power storage and battery capacity of the mth EV.

[0226] Through the mth EV off-grid electricity Determine whether the time period for EVs to participate in grid dispatch is reasonable, namely:

[0227]

[0228] Among them, P ev，max and Δt ev It is the sum of the maximum charging power of EV and the scheduling period.

[0229] Step 3.3: Modify the scheduling model in real time.

[0230] Real-time scheduling corrections are made, 15 minutes in advance, and updated every 5 minutes. The latest rolling optimization results of the day are used as the reference trajectory, the ultra-short-term wind and solar forecast data is input, the output deviation cost of each unit is taken into account, and the daily scheduling rolling plan is fine-tuned with the goal of minimizing operating costs. The objective function is:

[0231]

[0232] Among them, the superscript ′ is the daily scheduling plan output, ρ p，t and ΔP t They are the unit power deviation cost and deviation power of dispatchable resources in period t respectively. ΔP t >0 means the actual output is greater than the planned output, indicating that “wind and solar power abandonment” has occurred; ΔP t <0 means the actual output is less than the planned output, that is, there is a risk of insufficient power supply in the distribution network. t The value reflects the different operating states of the distribution network. Setting different ρ p，t Punishment will be imposed to encourage distribution networks to improve their dispatching strategies.

[0233] Based on the distribution network electricity purchase price, the penalty electricity price is set by adjusting the coefficient λ:

[0234]

[0235] Among them, λ is set to 0.5. The other targets are the same as those for intraday trading.

[0236] Model constraints include:

[0237] Power balance constraints:

[0238]

[0239] Load adjustment constraints:

[0240] 0≤P C，con，t ≤P C，con，max

[0241] Among them, P C，con，maxis the maximum adjustment amount of the direct control load C. The other constraints are consistent with intraday scheduling.

[0242] Step 3.4: Solve the model.

[0243] The intraday and real-time correction models involve optimizing the distribution network, EV, and DG consumption, taking into account three objective functions. An entropy weighting method is used to assign weights to each objective, ultimately transforming the multi-objective problem into a single objective for solution.

[0244] Step 4: Based on the intelligently scheduled electric vehicle charging and discharging strategy and the optimal boundary constraint, reference electricity price, and load guidance strategy, personalized charging and discharging recommendations are pushed to the user through a mobile application or an on-board system. When the user transmits feedback information to the dispatch center, the dispatch center dynamically adjusts the charging and discharging strategy.

[0245] As described above, in step 2, the dispatch center formulates an initial charging and discharging strategy based on user objectives and real-time status. In step 3, the system takes a global perspective and generates network-level optimal boundary constraints, reference electricity prices, and load guidance strategies based on a multi-timescale dispatch model: day-ahead, intraday, and real-time. Then, in step 4, based on these strategies and incorporating individual user characteristics and feedback, personalized "charging and discharging recommendations" are generated. These recommendations reflect both global optimization objectives and user response preferences, and are delivered to users as flexible strategies. The dispatch center generates these recommendations based on the local strategies generated in step 2 and the optimal boundary conditions (e.g., optimal load curves and price guidance curves) output in step 3, creating a unified user interface output. These recommendations include recommended charging time windows, discharging periods, price reminders, and load response incentives. Based on the intelligently dispatched electric vehicle charging and discharging strategies and the optimal boundary constraints, reference electricity prices, and load guidance strategies, personalized charging and discharging recommendations are delivered to users via mobile apps or onboard systems. Users can adjust charging and discharging according to their needs and transmit feedback to the dispatch center in real time. The dispatch center dynamically adjusts strategies based on user feedback to ensure that the charging and discharging behavior of electric vehicles matches the stability and economy of power grid operation.

[0246] Specifically, a user interaction interface is built based on mobile applications or in-vehicle systems, which is responsible for collecting users' personalized needs and preference information, such as target power (reflecting the user's expected proportion of battery power when off-grid), off-grid time, charging preferences (including preferences for charging time, cost, and speed), and discharge willingness (such as whether they are willing to discharge during peak hours of the power grid and the minimum discharge power).

[0247] Based on input from the user interface and the real-time status of the power grid, the dispatch center uses mobile apps or in-vehicle systems to push personalized charging and discharging recommendations to users. These recommendations include charging windows (charging during specific time periods helps optimize grid load), discharging windows (discharging during peak hours can earn financial compensation), cost analysis (the estimated charging costs and benefits of following the recommendations), and real-time electricity price information (including current and future price information), providing a comprehensive reference for users' charging and discharging decisions.

[0248] Users can adjust the recommended recommendations according to their needs and then feed the adjusted information back to the dispatch center through an interactive interface and wireless communication networks. The dispatch center dynamically adjusts charging and discharging strategies based on user feedback to ensure that the dispatch plan can adapt to changes in real time and has good adaptability. Among them, user feedback information includes key content such as adjusted charging time, changed discharge intention, and emergency charging requests (priority handling needs in special circumstances). The dispatch center recalculates and optimizes the dispatch strategy based on updated user needs and grid status to ensure that the charging and discharging behavior of electric vehicles matches the stability and economy of grid operation.

[0249] Through user interaction and feedback mechanisms, the present invention effectively achieves efficient interaction between electric vehicles and the power grid, thereby improving user satisfaction and enhancing the flexibility of power grid operation.

[0250] The beneficial effect of the present invention is that, compared with the prior art, the present invention provides an intelligent scheduling method and system for electric vehicles based on the metaverse source, grid, load and storage. Based on the source, grid, load and storage collaborative optimization scheduling model, the entropy weight method is used to distribute weights for multi-objective optimization problems, thereby realizing dynamic regulation of electric vehicles, energy storage equipment and distributed power sources, effectively reducing system operating costs and improving system operating efficiency; based on real-time algorithms and rolling optimization mechanisms, in the scenario of new energy power generation fluctuations, a time-sharing scheduling strategy for electric vehicles is constructed to realize dynamic adjustment of the charging and discharging process, reduce load peak-valley differences, and reduce grid scheduling pressure; combined with user interaction and feedback mechanisms, the charging and discharging strategy is dynamically optimized according to user needs, while meeting user power needs, the flexibility of electric vehicles as energy storage units to participate in peak shaving and valley filling of the grid is improved; by integrating the electric vehicle data acquisition module, the scheduling optimization module and the user interaction module, the multi-dimensional collaborative optimization between electric vehicles, energy storage equipment and the grid is effectively realized, an intelligent scheduling platform is constructed, and the overall economy and stability of the system are improved.

[0251] The present invention may be a system, method, and / or computer program product. The present invention also discloses a Metaverse-based intelligent dispatching system for electric vehicles based on the aforementioned Metaverse-based intelligent dispatching method for electric vehicles, comprising:

[0252] A real-time data collection module is used to collect real-time data of electric vehicles through digital devices and transmit it to the remote service platform through the vehicle terminal and wireless communication network;

[0253] An electric vehicle charging and discharging strategy construction module is used to determine the charging cost based on the real-time data of the electric vehicle and the user-entered target, and to construct an electric vehicle charging and discharging strategy based on intelligent scheduling in the dispatch center in combination with the real-time status of the power grid, dynamically plan the charging and discharging time windows and power of the electric vehicle, and perform real-time optimization on the electric vehicles that are in a dispatchable state in each time period;

[0254] The multi-timescale scheduling module is used to establish a multi-timescale scheduling model for active distribution networks based on source-grid-load-storage collaboration through day-ahead, intraday, and real-time multi-timescale optimization. The entropy weight method is used to transform the multi-objective problem into a single objective for solution, and the optimal boundary constraints, reference electricity price, and load guidance strategy are obtained.

[0255] A user feedback module is used to push personalized charging and discharging recommendations to users through mobile applications or vehicle systems based on the intelligently scheduled electric vehicle charging and discharging strategy and the optimal boundary constraints, reference electricity prices, and load guidance strategies. When users transmit feedback information to the dispatch center, the dispatch center dynamically adjusts the charging and discharging strategies.

[0256] Based on the spirit of the present invention, those skilled in the art can easily conceive of a computer program product based on the aforementioned Metaverse-based intelligent dispatching method for electric vehicles (EVs). This computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure. Specifically, the present application also includes a terminal comprising a processor and a storage medium; the storage medium is configured to store instructions; and the processor is configured to operate according to the instructions to execute the steps of the aforementioned Metaverse-based intelligent dispatching method for electric vehicles (EVs).

[0257] Computer-readable storage medium can be the tangible device that can keep and store the instruction used by instruction execution device.Computer-readable storage medium can be, for example, but not limited to, electric storage device, magnetic storage device, optical storage device, electromagnetic storage device, semiconductor storage device or above-mentioned any suitable combination.The more specific example (non-exhaustive list) of computer-readable storage medium comprises: portable computer disk, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical coding device, for example, punch card or the convex structure in the groove that stores instruction thereon and above-mentioned any suitable combination.Computer-readable storage medium used here is not interpreted as instantaneous signal itself, such as radio wave or other free propagating electromagnetic wave, electromagnetic wave (for example, by the light pulse of fiber optic cable) that waveguide or other transmission medium propagates or the electric signal that is transmitted by wire.

[0258] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0259] The computer program instructions for performing the operation of the present disclosure can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, and conventional procedural programming languages ​​such as "C" language or similar programming languages. Computer-readable program instructions can be executed entirely on a user's computer, partially on a user's computer, executed as an independent software package, partially on a user's computer and partially on a remote computer, or executed entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer via any type of network including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., utilizing an Internet service provider to connect via the Internet). In some embodiments, by utilizing the state information of computer-readable program instructions to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0260] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. An intelligent dispatching method for electric vehicles based on Metaverse source-grid-load-storage, characterized in that: The following steps are involved: Step 1: Collect real-time data of electric vehicles through digital equipment and transmit it to the remote service platform through the vehicle terminal and wireless communication network; Step 2: Based on the real-time data of the electric vehicle and the user-entered target, the charging cost is determined. The dispatch center combines the real-time status of the power grid to build an electric vehicle charging and discharging strategy based on intelligent scheduling, dynamically plans the charging and discharging time windows and power of the electric vehicle, and performs real-time optimization on the electric vehicles that are in a dispatchable state in each time period; Step 3: Through day-ahead, intraday, and real-time multi-timescale optimization, a multi-timescale dispatch model for the active distribution network based on source-grid-load-storage collaboration is established. The entropy weight method is used to transform the multi-objective problem into a single objective for solution, and the optimal boundary constraints, reference electricity price, and load guidance strategy are obtained. Step 4: Based on the intelligently dispatched electric vehicle charging and discharging strategy and the optimal boundary constraint, reference electricity price, and load guidance strategy, personalized charging and discharging recommendations are pushed to users via mobile applications or vehicle-mounted systems. When users transmit feedback information to the dispatch center, the dispatch center dynamically adjusts the charging and discharging strategies.

2. The electric vehicle intelligent dispatching method based on Metaverse Source-Grid-Load-Storage according to claim 1 is characterized in that: The electric vehicle charging and discharging strategy based on intelligent scheduling is constructed in the dispatching center in combination with the real-time status of the power grid, further comprising: Divide a day into T time periods of unit length τ, and update the data of all connected electric vehicles at the beginning of each time period: in, is the dispatchable time of the i-th electric vehicle, The time of joining the network, The target off-grid time set for the user; The charge and discharge plan of electric vehicles in a scheduling cycle is represented by an N×T matrix X: Among them, x i，t is the charging and discharging power of the i-th electric vehicle in time period t, x i，t >0 means charging, x i，t <0 indicates discharge, T is the maximum time length; For N V2G and N CHAR The vehicles satisfy the following requirements: Among them, P char is the maximum charging power, P dis is the maximum discharge power; N V2G The number of N electric vehicles connected to the grid that support vehicle-grid interaction is recorded as, N CHAR is the number of vehicles that only support charging, and the proportion of vehicles that support V2G is γ, that is, N V2G =γN; The initial power of the electric vehicle when it is connected to the grid Expressed as: in, The maximum capacity of electric vehicle batteries; Assume that the target power set by the user for the electric vehicle is When off-grid, the battery capacity meets the following requirements: At the same time, the battery power at any time within the dispatchable time meets the following requirements:

3. The electric vehicle intelligent dispatching method based on Metaverse Source-Grid-Load-Storage according to claim 2 is characterized in that: The determining of the charging cost further includes: Assuming that the charging and discharging behavior remains unchanged within a unit time period, calculate the comprehensive load of electric vehicles connected to the grid Assume that the basic load of other electrical equipment, excluding electric vehicles, is The basic load remains unchanged in the unit time period, and the total load z is calculated. t : The system real-time electricity price is a linear change of the total load in each time period, that is: g(z t )=k0+k1z t Among them, g(z t ) is the electricity price in time period t, and the charging cost of electric vehicles is calculated. k0 represents the fixed electricity price benchmark of the system, and k1 represents the electricity price variation coefficient caused by unit load: Calculate the total cost of charging an electric vehicle:

4. The electric vehicle intelligent dispatching method based on Metaverse Source-Grid-Load-Storage according to claim 3 is characterized in that: The real-time optimization of the electric vehicles in the dispatchable state in each time period further includes: The dispatch center calculates the dispatch strategy at the beginning of each time period and publishes it to the electric vehicles. The total number of dispatchable vehicles in time period t is N′, which can be divided into two categories. One category is electric vehicles that have been connected to the network for a certain period of time, namely One category is electric vehicles that are connected to the grid during this period, namely Calculate the remaining schedulable time The optimization range is changed dynamically, and the size of the optimization range is the maximum value of the remaining dispatchable time of the dispatchable vehicles in the current time period: Among them, W t is the optimization range of time period t; The length of the scheduling strategy calculated for each time period is the corresponding optimization time window, and the electric vehicle uses the header of the received scheduling strategy as the charging and discharging strategy for the current time period.

5. The electric vehicle intelligent dispatching method based on Metaverse Source-Grid-Load-Storage according to claim 4 is characterized in that: The construction of an electric vehicle charging and discharging strategy based on intelligent scheduling further includes: Calculate the network loss sensitivity PLS of node m m : Where S represents the network loss and P represents the active power injected by the node; the partial differential of the network loss with respect to the active power is obtained: Where Q is the reactive power injected into the node, |V| and θ are the amplitude and phase angle of the node voltage; Calculate the network loss cost, i.e. the network loss sensitivity index J2: in, is the total load of electric vehicles on node m, k2 is the conversion coefficient, and M is the total number of nodes in the network; Minimizing the total cost is the algorithm goal: subject to:

6. The electric vehicle intelligent dispatching method based on Metaverse Source, Grid, Load and Storage according to claim 5 is characterized in that: The establishment of a multi-time-scale scheduling model for an active distribution network based on source-grid-load-storage collaboration further includes: Taking the distribution network's scheduling cost as the minimum in the entire scheduling cycle as the goal, the planned output of each scheduling resource is determined. The objective function is: Among them, C pure，t is the electricity purchase cost of the distribution network during period t, C ope，t 、C comp，t are the operating cost of the distribution network in period t and the calling cost paid by the distribution network to the load; C dis，t is the cost of curtailing wind and solar power during period t; The power purchase cost of the distribution network is C pure，t for: C pure，t Zρ grid，t P.S grid，t Among them, ρ grid，t and P grid，t are the unit price and quantity of electricity purchased by the distribution network from the upper power grid during period t respectively; Distribution network operating cost C ope，t The cost of DG operation is C dg，t MT operating cost C mt，t and the operating cost of ES C es，t It consists of 3 parts: Among them, ρ dg，t and P dg，t is the DG unit electricity operation cost and power generation; ρ mt，t and P mt，t is the operating cost and power generation per MT unit of electricity; a es，c 、b es，c 、a es，d 、b es，d and c es is the equipment consumption parameter of ES, P es，c，t and P es，d，t is the ES charging and discharging power during period t; Among them, the calling cost C paid by the distribution network to the load is comp，t for: C comp，t =ρ A，dr，t P A，int，t +r B，dr，t P B，con，t +r C，dr，t P C，con，t ρ A,dr,t , ρ B,dr,t , ρ C,dr,t Respectively represent the unit call compensation price of Class A, Class B, and Class C loads; P A,int,t 、P B,con,t 、P C,con,t They represent the control call power of type A, type B, and type C loads in time period t respectively; Among them, the cost of curtailing wind and solar power is C dis，t for: C dis，t =ρ dis，t ΔP dis，t Among them, ρ dis，t , ΔP dis，t They are the unit electricity curtailment cost and amount of curtailment in period t respectively.

7. The electric vehicle intelligent dispatching method based on Metaverse Source, Grid, Load and Storage according to claim 6 is characterized in that: The establishment of a multi-time-scale scheduling model for an active distribution network based on source-grid-load-storage collaboration further includes: Increase EV dispatch cost C ev，t : Among them, α ev，c，t , α ev，d，t and Compensate for EV charging and discharging electricity prices and participate in grid dispatching; The economic benefits of EVs are calculated based on the changes in electricity purchase costs before and after EVs respond to grid dispatch: Among them, ρ ev，t is the EV charging electricity price during period t; It represents the charging power of electric vehicles in response to scheduling during time period t, that is, the part directly controlled by the dispatch center and involved in optimization; represents the total charging power of all electric vehicles in time period t; The DG utilization rate is expressed as the ratio of DG consumption to total DG power generation within the dispatch period: The comprehensive objective function is: minf=min(λ1f1-λ2f2+λ3f3) Among them, λ1, λ2, and λ3 are weight coefficients.

8. An intelligent dispatching system for electric vehicles based on Metaverse source, grid, load and storage, characterized by: include: A real-time data collection module is used to collect real-time data of electric vehicles through digital devices and transmit it to the remote service platform through the vehicle terminal and wireless communication network; An electric vehicle charging and discharging strategy construction module is used to determine the charging cost based on the real-time data of the electric vehicle and the user-entered target, and to construct an electric vehicle charging and discharging strategy based on intelligent scheduling in the dispatch center in combination with the real-time status of the power grid, dynamically plan the charging and discharging time windows and power of the electric vehicle, and perform real-time optimization on the electric vehicles that are in a dispatchable state in each time period; The multi-timescale scheduling module is used to establish a multi-timescale scheduling model for active distribution networks based on source-grid-load-storage collaboration through day-ahead, intraday, and real-time multi-timescale optimization. The entropy weight method is used to transform the multi-objective problem into a single objective for solution, and the optimal boundary constraints, reference electricity price, and load guidance strategy are obtained. A user feedback module is used to push personalized charging and discharging recommendations to users through mobile applications or vehicle systems based on the intelligently scheduled electric vehicle charging and discharging strategy and the optimal boundary constraints, reference electricity prices, and load guidance strategies. When users transmit feedback information to the dispatch center, the dispatch center dynamically adjusts the charging and discharging strategies.

9. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of the electric vehicle intelligent scheduling method based on metaverse source, grid, load and storage according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the electric vehicle intelligent scheduling method based on metaverse source, grid, load and storage as described in any one of claims 1 to 7 are implemented.

Images