Multi-microgrid optimization scheduling method and system based on temporal and spatial characteristics of electric vehicles

Abstract

The present invention provides a multi-microgrid optimization scheduling method and system based on the spatiotemporal characteristics of electric vehicles. The method includes constructing a highway microgrid model, a spatiotemporal prediction model for electric vehicle charging based on graph convolution and an improved Autoformer, and a highway multi-microgrid shared energy storage architecture; constructing a highway multi-microgrid multi-mode and multi-function optimization scheduling model based on the highway microgrid model, the electric vehicle charging spatiotemporal prediction model, and the highway multi-microgrid shared energy storage architecture; solving the highway multi-microgrid multi-mode and multi-function optimization scheduling model based on the electric vehicle charging spatiotemporal prediction model, the highway multi-microgrid shared energy storage architecture, and an improved spatiotemporal collaborative quantum vulture search algorithm to obtain an optimal scheduling strategy for the highway multi-microgrid system. The present invention can improve energy storage utilization and microgrid operation reliability.

Description

Technical Field

[0001] The present invention belongs to the technical field of power grid dispatching, and in particular relates to a multi-microgrid optimization dispatching method and system based on the spatiotemporal characteristics of electric vehicles. Background Art

[0002] As the global energy transition deepens, non-renewable fossil fuels are gradually being replaced due to their limited resources and significant negative environmental impacts. Against this backdrop, researchers are committed to developing sustainable and environmentally friendly alternative energy solutions. This energy transition, combined with the widespread adoption of intelligent end devices, is driving the development of microgrid technologies that integrate distributed generation units, power loads, energy storage modules, and energy management systems. It is also promoting research on the construction and coordinated operation of multi-microgrid systems.

[0003] In the transportation energy sector, the widespread adoption of electric vehicles (EVs) is intertwined with the increasing share of variable renewable energy generation. EV charging behavior exhibits significant spatiotemporal characteristics—volatility in time and a heterogeneous distribution in space. This spatiotemporal dynamic complicates charging load forecasting and poses significant challenges to the reliable and economical operation of multi-microgrid systems, including highway microgrids.

[0004] In multi-microgrid systems (particularly in highway microgrid scenarios), the introduction of energy storage units (ESS) provides an effective means to smooth out fluctuations in renewable energy output, balance loads, improve local consumption capacity, and enhance power supply quality and system stability. However, current investment costs for energy storage facilities are high. Deploying independent energy storage systems for each microgrid in a multi-microgrid system not only results in significant, repetitive investments but, more critically, hinders the flexible sharing and coordinated optimization of energy storage resources across time and space, reducing the overall resource utilization efficiency and economic viability of the system. Therefore, there is an urgent need to research optimized scheduling methods that can effectively coordinate resources across multiple microgrids and fully exploit the potential of the temporal and spatial characteristics of electric vehicles. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention provides a multi-microgrid optimization scheduling method and system based on the spatiotemporal characteristics of electric vehicles, which are used to solve the technical problems in the prior art.

[0006] In one aspect, the present invention provides the following technical solution: a multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles, comprising:

[0007] Build a highway microgrid model;

[0008] Build a spatiotemporal prediction model for electric vehicle charging based on graph convolution and improved Autoformer;

[0009] Build a multi-microgrid shared energy storage architecture for highways;

[0010] Based on the highway microgrid model, the electric vehicle charging spatiotemporal prediction model and the highway multi-microgrid shared energy storage architecture, a highway multi-microgrid multi-mode and multi-functional optimization scheduling model is constructed;

[0011] Based on the electric vehicle charging spatiotemporal prediction model, the highway multi-microgrid shared energy storage architecture and the improved spatiotemporal collaborative quantum vulture search algorithm, the highway multi-microgrid multi-mode and multi-functional optimization scheduling model is solved to obtain the optimal scheduling strategy for the highway multi-microgrid system.

[0012] Compared with the existing technology, the beneficial effects of the present invention are as follows: the present invention combines the highway energy storage system and uses cloud computing to optimize shared energy storage scheduling, and optimizes scheduling based on the spatiotemporal characteristics of electric vehicle charging, the status of energy storage equipment and the load of the microgrid. First, the spatiotemporal distribution characteristics of electric vehicles and their impact on charging piles are analyzed; secondly, the distributed and centralized energy storage devices in the highway multi-microgrid are uniformly managed for energy storage sharing, and the energy storage capacity is dynamically allocated according to the needs of different regions; then, based on the new energy power generation power forecast data and the spatiotemporal forecast data of electric vehicle charging, combined with the energy storage equipment, a multi-mode and multi-functional optimization scheduling model is designed to improve the energy storage utilization rate and the reliability of microgrid operation; finally, an improved spatiotemporal collaborative quantum vulture search algorithm suitable for high-speed multi-microgrids is used to solve the multi-mode and multi-functional optimization scheduling model, improve the prediction accuracy and efficiency, and obtain the optimal scheduling strategy for the highway multi-microgrid system.

[0013] Preferably, in the step of constructing a highway microgrid model, the highway microgrid model includes a new energy generator set model, a fossil energy generator set model, an energy storage device model, and an electricity load model;

[0014] The new energy generator set model includes:

[0015] Photovoltaic generator model:

[0016] ;

[0017] Where, Indicates time The photovoltaic output power, Indicates time The light intensity, represents the effective area of ​​the photovoltaic panel, represents the photovoltaic conversion efficiency, represents the temperature coefficient, Indicates time ambient temperature, Indicates the reference temperature;

[0018] Wind turbine model:

[0019] ;

[0020] Where, Indicates time The wind power output power, Indicates time wind speed, Indicates the cut-in wind speed, Indicates the rated wind speed, Indicates the cut-out wind speed, Indicates the rated power of the fan;

[0021] The fossil energy generator model is:

[0022] ;

[0023] Where, Indicates time The output power of fossil energy units, Respectively represent the minimum output and maximum output of the unit;

[0024] The energy storage device model is:

[0025] ;

[0026] Where, Respectively indicate time The energy storage state of charge, represents the total energy storage capacity, Represent the charging efficiency and discharging efficiency respectively, 、 Represent charging power and discharging power respectively. 、 Respectively represent the maximum charging power and the maximum discharging power, Indicates a time interval;

[0027] The power load model includes:

[0028] Conventional electricity load model:

[0029]

[0030] Where, Indicates time Conventional power load, Indicates time Known load curve or predicted value;

[0031] Electric vehicle charging load model:

[0032]

[0033] Where, Indicates time The total charging load, Indicates time The number of electric vehicles charged, Indicates the The charging power of the vehicle.

[0034] Preferably, the step of constructing the electric vehicle charging spatiotemporal prediction model includes:

[0035] Fusing multi-source data related to highway networks, charging stations, and weekday and holiday traffic flow, converting actual highway routes into a highway topology using graph theory, and fusing the highway topology with the multi-source data to obtain a fused dataset.

[0036] Performing data preprocessing and hierarchical analysis on the fused data set to obtain electric vehicle charging load prediction characteristics;

[0037] Based on the electric vehicle charging load prediction characteristics, the time distribution characteristics and spatial distribution characteristics of the electric vehicle are obtained. According to the time distribution characteristics and the spatial distribution characteristics, graph convolution and improved Autoformer are used to perform spatial feature modeling and time feature modeling respectively to obtain an electric vehicle charging spatiotemporal prediction model.

[0038] Preferably, in the step of constructing a highway multi-microgrid shared energy storage architecture, the highway multi-microgrid shared energy storage architecture is:

[0039]

[0040] Where, Indicates the total state of charge of the virtual energy storage pool, Indicates the total charging power of the virtual energy storage battery, Indicates the total discharge power of the virtual energy storage battery, Represents the total number of distributed energy storage devices and centralized energy storage devices in the virtual energy storage pool, Indicates the number of The state of charge of the device, Respectively represent the first The charging power and discharging power of each device.

[0041] Preferably, the highway multi-microgrid multi-mode multi-function optimization scheduling model is specifically:

[0042] ;

[0043] ;

[0044] ;

[0045] ;

[0046] ;

[0047] ;

[0048] Where, It is the comprehensive reliability index of the system. is the time section within the scheduling cycle, Number the sub-microgrid in the multi-microgrid system, Power supply adequacy index, is the voltage stability margin, To support the efficiency of energy storage, For microgrids Internal key load nodes, Representation node exist Key load requirements for the time period, Actual supply node Power, For microgrids exist Total critical load demand for the time period, For microgrids Internal busbar node, For nodes exist The voltage amplitude of the time period, is the rated voltage, The upper limit of voltage, etc. To support microgrids Energy storage unit, Energy storage unit The discharge power, The reverse power generated by EV, Energy storage unit Charge and discharge efficiency, For microgrids The maximum instantaneous support power required, For maximum energy throughput, is the total number of time periods, Indicates time period The charging power, Indicates time period The discharge power, Represent the charging efficiency and discharging efficiency respectively, Indicates the time interval, To maximize time utilization, 、 Represent the first and second indicator functions respectively.

[0049] Preferably, the constraints of the highway multi-microgrid multi-mode and multi-function optimization scheduling model include:

[0050] Key load constraints:

[0051] ;

[0052] Where, The power shortage ratio allowed for the total critical load;

[0053] Energy storage battery operating status constraints:

[0054] ;

[0055] Where, Indicates the state of charge of the energy storage device. Respectively The minimum and maximum values ​​of

[0056] Energy storage backup capacity constraints:

[0057] ;

[0058] Where, No. Microgrids in Total spare capacity for the time period, 、 For the Microgrids in The spare capacity in the charging mode and discharging mode during the period, For the Microgrids in The load of the period, For the The main load ratio in a microgrid.

[0059] Preferably, the step of solving the highway multi-microgrid multi-mode and multi-function optimization scheduling model based on the electric vehicle charging spatiotemporal prediction model, the highway multi-microgrid shared energy storage architecture, and the improved spatiotemporal collaborative quantum vulture search algorithm to obtain the optimal scheduling strategy for the highway multi-microgrid system includes:

[0060] Obtain a preset vulture search algorithm, initialize the preset vulture search algorithm to a quantum superposition state, and use a quantum coded solution space:

[0061] ;

[0062] Where, 、 are the first and second probability amplitudes respectively;

[0063] When the group in the preset vulture search algorithm falls into a local optimum, the quantum collapse mechanism is triggered and forces the individual to collapse to a certain state according to the probability amplitude:

[0064]

[0065] Where, Indicates the Individuals in The new position after iterations, is the current solution position, In the solution space New solutions generated uniformly randomly within the are the lower and upper bounds of the optimization variables, is a uniformly distributed random number, is the quantum collapse probability;

[0066] Embedding a pre-prediction layer in the preset vulture search algorithm and dynamically weighting the key spatiotemporal factors of the highway , to obtain the improved space-time collaborative quantum vulture search algorithm:

[0067] ;

[0068] Where, is the attention weight, is the query matrix, is the bond matrix, is the value matrix, is the key vector dimension, To scale the dot product attention, is the normalization function;

[0069] Based on the electric vehicle charging spatiotemporal prediction model, the highway multi-microgrid shared energy storage architecture and the improved spatiotemporal collaborative quantum vulture search algorithm suitable for high-speed multi-microgrids, the highway multi-mode and multi-functional optimization scheduling model is solved to obtain the optimal scheduling strategy for the highway multi-microgrid system.

[0070] In a second aspect, the present invention provides the following technical solution: a multi-microgrid optimization scheduling system based on the spatiotemporal characteristics of electric vehicles, the system comprising:

[0071] The first building module is used to build a highway microgrid model;

[0072] The second building block is used to build a spatiotemporal prediction model for electric vehicle charging based on graph convolution and improved Autoformer;

[0073] The third building block is used to build a multi-microgrid shared energy storage architecture for highways;

[0074] A fourth construction module is configured to construct a highway multi-microgrid multi-mode and multi-functional optimization scheduling model based on the highway microgrid model, the electric vehicle charging spatiotemporal prediction model, and in combination with the highway multi-microgrid shared energy storage architecture;

[0075] A solution module is used to solve the highway multi-microgrid multi-mode and multi-functional optimization scheduling model based on the electric vehicle charging spatiotemporal prediction model, the highway multi-microgrid shared energy storage architecture, and the improved spatiotemporal collaborative quantum vulture search algorithm to obtain the optimal scheduling strategy for the highway multi-microgrid system.

[0076] In a third aspect, the present invention provides the following technical solution: a computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor; when the processor executes the computer program, the multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles as described above is implemented.

[0077] In a fourth aspect, the present invention provides the following technical solution: a storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles as described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0079] Figure 1 Flowchart of a multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles provided in Example 1 of the present invention;

[0080] Figure 2 A structural block diagram of a multi-microgrid optimization scheduling system based on the spatiotemporal characteristics of electric vehicles provided in the second embodiment of the present invention;

[0081] Figure 3 A schematic diagram of the hardware structure of a computer provided in another embodiment of the present invention.

[0082] The embodiments of the present invention will be further described below with reference to the accompanying drawings. DETAILED DESCRIPTION

[0083] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the embodiments of the present invention, and should not be construed as limiting the present invention.

[0084] Example 1

[0085] In the first embodiment of the present invention, Figure 1 As shown in FIG, a multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles includes:

[0086] S1. Build a highway microgrid model;

[0087] Specifically, in step S1, the highway microgrid model includes a new energy generator set model, a fossil energy generator set model, an energy storage device model, and an electricity load model;

[0088] The new energy generator set model includes:

[0089] Photovoltaic generator model:

[0090] ;

[0091] Where, Indicates time The photovoltaic output power (unit: W or kW), Indicates time Light intensity (unit: W / m 2 ), Indicates the effective area of ​​the photovoltaic panel (unit: m 2 ), represents the photovoltaic conversion efficiency (dimensionless), Indicates the temperature coefficient (% / °C), Indicates time Ambient temperature (unit: °C), represents the reference temperature (unit: °C), which is 25°C in this application;

[0092] Wind turbine model:

[0093] ;

[0094] Where, Indicates time Wind power output power (unit: W or kW), Indicates time Wind speed (unit: m / s), Indicates the cut-in wind speed, Indicates the rated wind speed, Indicates the cut-out wind speed, Indicates the rated power of the fan;

[0095] The cut-in wind speed is the minimum wind speed at which the wind turbine starts generating electricity, and the cut-out wind speed is the maximum wind speed at which the wind turbine stops generating electricity.

[0096] The fossil energy generator model is:

[0097] ;

[0098] Where, Indicates time Output power of fossil energy units (unit: MW), Respectively represent the minimum output and maximum output of the unit;

[0099] Specifically, the minimum output specifically indicates the technical lower limit, and the maximum output specifically indicates the rated power;

[0100] The energy storage device model is:

[0101] ;

[0102] Where, Respectively indicate time Energy storage state of charge (unit: kWh), Indicates the total energy storage capacity (unit: kWh), Represent the charging efficiency and discharging efficiency respectively, 、 Respectively represent charging power and discharging power (unit: kW), 、 Respectively represent the maximum charging power and maximum discharging power (unit: kW), Indicates the time interval (unit: h);

[0103] The power load model includes:

[0104] Conventional electricity load model:

[0105]

[0106] Where, Indicates time Conventional electricity load (unit: kW or MW), Indicates time Known load curve or predicted value (unit: kW or MW);

[0107] Electric vehicle charging load model:

[0108]

[0109] Where, Indicates time Total charging load (unit: kW), Indicates time The number of electric vehicles charged, Indicates the The charging power of the vehicle (usually a constant, such as 3kW).

[0110] S2. Build a spatiotemporal prediction model for electric vehicle charging based on graph convolution and improved Autoformer;

[0111] Wherein, the step S2 includes:

[0112] S21. Fusing multi-source data information related to the highway network, charging stations, and weekday and holiday traffic flow, converting actual highway routes into a highway topology using graph theory, and fusing the highway topology with the multi-source data information to obtain a fused dataset.

[0113] S22, performing data preprocessing and hierarchical analysis on the fused data set to obtain electric vehicle charging load prediction characteristics;

[0114] Specifically, the data preprocessing process here includes missing value filling, outlier processing, data normalization, etc. The hierarchical analysis is specifically based on the analysis of factors affecting electric vehicle charging, and the weight of each influencing factor is calculated through the hierarchical analysis method, and then the features with greater impact on the prediction are selected, so as to extract meaningful electric vehicle charging load prediction features from the original data.

[0115] S23. Obtaining the temporal distribution characteristics and spatial distribution characteristics of the electric vehicle based on the electric vehicle charging load prediction characteristics, and performing spatial feature modeling and temporal feature modeling using graph convolution and improved Autoformer according to the temporal distribution characteristics and the spatial distribution characteristics, respectively, to obtain a spatiotemporal prediction model for electric vehicle charging;

[0116] Specifically, the temporal distribution characteristics are obtained by multi-time scale prediction based on historical data of electric vehicle charging load, and the spatial distribution characteristics are obtained by predicting point demand and flow demand. This application is constructed using graph convolution (GCN) and an improved Autoformer model. The difference between this application and the electric vehicle charging prediction model in the prior art is that:

[0117] 1. Graph Convolutional Networks (GCNs) address the shortcomings of CNNs and RNNs in processing spatiotemporal features. GCNs are used to extract the spatiotemporal correlations of charging stations and explicitly model the geographical and traffic correlations between charging stations (for example, the loads of adjacent charging stations affect each other).

[0118]

[0119] Where, , represents the adjacency matrix Plus the self-connection (identity matrix ), used to retain the node’s own characteristics; is the degree matrix (diagonal elements are node degrees); For the Layer node feature matrix; is the learnable weight matrix; represents the activation function, For the Layer node feature matrix.

[0120] 2. The traditional Transformer relies on multi-head attention, which has high computational complexity and is insufficient in capturing long-term trends. Therefore, the improved Autoformer introduces square-solution attention and seasonal-trend decomposition to enhance the modeling ability of long-term trends:

[0121]

[0122] Where, Indicates the introduction of query, key, and value matrices; represents the key vector dimension; represents the temporal convolutional layer; Represents a learnable weight coefficient that balances global attention and local features, To model attention weights.

[0123] S3. Build a multi-microgrid shared energy storage architecture for highways;

[0124] The highway multi-microgrid shared energy storage architecture is as follows:

[0125]

[0126] Where, Indicates the total state of charge of the virtual energy storage pool, Indicates the total charging power of the virtual energy storage battery, Indicates the total discharge power of the virtual energy storage battery, Represents the total number of distributed energy storage devices and centralized energy storage devices in the virtual energy storage pool, Indicates the number of The state of charge of the device, Respectively represent the first The charging power and discharging power of each device.

[0127] S4. Constructing a highway multi-microgrid multi-mode and multi-functional optimization scheduling model based on the highway microgrid model, the electric vehicle charging spatiotemporal prediction model, and the highway multi-microgrid shared energy storage architecture;

[0128] Among them, the multi-microgrid multi-mode and multi-functional optimization scheduling model for highways has the objective functions of maximizing the operation reliability of the multi-microgrid system and the energy storage utilization rate. The multi-microgrid multi-mode and multi-functional optimization scheduling model for highways is specifically as follows:

[0129] ;

[0130] ;

[0131] ;

[0132] ;

[0133] ;

[0134] ;

[0135] Where, is the comprehensive reliability index of the system (maximization target), is the time section within the scheduling cycle, Number the sub-microgrid in the multi-microgrid system, Power supply adequacy index, is the voltage stability margin, To support the efficiency of energy storage, For microgrids Internal key load nodes, Representation node exist Key load requirements for the time period, Actual supply node Power, For microgrids exist Total critical load demand for the time period, For microgrids Internal busbar node, For nodes exist The voltage amplitude of the time period, is the rated voltage, The upper limit of voltage, etc. To support microgrids Energy storage unit, Energy storage unit The discharge power, The reverse power generated by EV, Energy storage unit Charge and discharge efficiency, For microgrids The maximum instantaneous support power required, For maximum energy throughput, is the total number of time periods, Indicates time period The charging power, Indicates time period The discharge power, Represent the charging efficiency and discharging efficiency respectively, Indicates the time interval, To maximize time utilization, 、 Represent the first and second indicator functions respectively.

[0136] The constraints include:

[0137] Key load constraints:

[0138] ;

[0139] Where, The allowable power outage ratio of the total critical load.

[0140] Energy storage battery operating status constraints:

[0141] ;

[0142] Where, Indicates the state of charge of the energy storage device. Respectively The minimum and maximum values ​​of

[0143] Energy storage backup capacity constraints:

[0144] ;

[0145] Where, No. Microgrids in Total spare capacity for the time period, 、 For the Microgrids in The spare capacity in the charging mode and discharging mode during the period, For the Microgrids in The load of the period, For the The main load ratio in a microgrid.

[0146] S5. Based on the electric vehicle charging spatiotemporal prediction model, the highway multi-microgrid shared energy storage architecture, and the improved spatiotemporal collaborative quantum vulture search algorithm, the highway multi-microgrid multi-mode and multi-functional optimization scheduling model is solved to obtain the optimal scheduling strategy for the highway multi-microgrid system.

[0147] Wherein, the step S5 specifically includes:

[0148] S51. Obtain a preset vulture search algorithm, perform quantum superposition state initialization on the preset vulture search algorithm, and use quantum coding solution space:

[0149] ;

[0150] Where, 、 are the first and second probability amplitudes respectively;

[0151] Specifically, the preset vulture search algorithm here is an algorithm in the prior art and will not be described in detail here. The algorithm is improved through steps S51-S53 to obtain an improved spatiotemporal collaborative quantum vulture search algorithm. For the probability amplitude, the initial population covers the solution space probability distribution.

[0152] S52. When the group in the preset vulture search algorithm falls into a local optimum, the quantum collapse mechanism is triggered and the individuals are forced to collapse to a certain state according to the probability amplitude:

[0153]

[0154] Where, Indicates the Individuals in The new position after iterations, is the current solution position, In the solution space New solutions generated uniformly randomly within the are the lower and upper bounds of the optimization variables, is a uniformly distributed random number, is the quantum collapse probability;

[0155] Specifically, the second probability amplitude is actually also the quantum bit probability amplitude.

[0156] S53: embedding a pre-prediction layer in the preset vulture search algorithm and dynamically weighting key spatiotemporal factors of the highway , to obtain the improved space-time collaborative quantum vulture search algorithm:

[0157] ;

[0158] Where, is the attention weight, is the query matrix, is the bond matrix, is the value matrix, is the key vector dimension, To scale the dot product attention, is the normalization function.

[0159] S54. Based on the electric vehicle charging spatiotemporal prediction model and the highway multi-microgrid shared energy storage architecture, an improved spatiotemporal collaborative quantum vulture search algorithm suitable for high-speed multi-microgrids is used to solve the highway multi-microgrid multi-mode and multi-functional optimization scheduling model to obtain the optimal scheduling strategy for the highway multi-microgrid system.

[0160] A multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles is provided in a first embodiment of the present invention. The present invention combines highway energy storage systems and utilizes cloud computing to optimize energy storage cloud management and scheduling. Scheduling optimization is performed based on the spatiotemporal characteristics of electric vehicle charging, the status of energy storage devices, and the load of the microgrid. First, the spatiotemporal distribution characteristics of electric vehicles and their impact on charging piles are analyzed. Second, the distributed and centralized energy storage devices in multiple microgrids on highways are uniformly managed in the cloud, and cloud energy storage capacity is dynamically allocated according to the needs of different regions. Finally, based on renewable energy power generation power forecast data and electric vehicle charging spatiotemporal forecast data, combined with energy storage devices, a multi-objective optimization scheduling model is designed to balance highway electric vehicle charging demand, energy storage utilization, and microgrid operating costs.

[0161] Example 2

[0162] like Figure 2 As shown, in the second embodiment of the present invention, a multi-microgrid optimization scheduling system based on the spatiotemporal characteristics of electric vehicles is provided, and the system includes:

[0163] The first building module 1 is used to build a highway microgrid model;

[0164] The second building block 2 is used to build an electric vehicle charging spatiotemporal prediction model based on graph convolution and improved Autoformer;

[0165] The third building block 3 is used to build a multi-microgrid shared energy storage architecture for highways;

[0166] A fourth construction module 4 is configured to construct a highway multi-microgrid multi-mode and multi-functional optimization scheduling model based on the highway microgrid model, the electric vehicle charging spatiotemporal prediction model, and in combination with the highway multi-microgrid shared energy storage architecture;

[0167] Solving module 5 is used to solve the highway multi-microgrid multi-mode and multi-function optimization scheduling model based on the electric vehicle charging spatiotemporal prediction model, the highway multi-microgrid shared energy storage architecture, and the improved spatiotemporal collaborative quantum vulture search algorithm to obtain the optimal scheduling strategy for the highway multi-microgrid system;

[0168] The second building block 2 includes:

[0169] A fusion submodule is used to fuse multi-source data information related to the highway network, charging stations, and weekday and holiday traffic flow, and convert the actual highway routes into a highway topology using graph theory, and fuse the highway topology with the multi-source data information to obtain a fused dataset;

[0170] A processing submodule, configured to perform data preprocessing and hierarchical analysis on the fused data set to obtain electric vehicle charging load prediction characteristics;

[0171] The spatiotemporal submodule is used to obtain the time distribution characteristics and spatial distribution characteristics of electric vehicles based on the electric vehicle charging load prediction characteristics, and use graph convolution and improved Autoformer to perform spatial feature modeling and time feature modeling respectively according to the time distribution characteristics and the spatial distribution characteristics to obtain the electric vehicle charging spatiotemporal prediction model.

[0172] The solution module 5 includes:

[0173] The encoding submodule is used to obtain a preset vulture search algorithm, initialize the preset vulture search algorithm to a quantum superposition state, and use a quantum encoding solution space:

[0174] ;

[0175] Where, 、 are the first and second probability amplitudes respectively;

[0176] The collapse submodule is used to trigger the quantum collapse mechanism and force the individual to collapse to a certain state according to the probability amplitude when the group in the preset vulture search algorithm falls into a local optimum:

[0177]

[0178] Where, Indicates the Individuals in The new position after iterations, is the current solution position, In the solution space New solutions generated uniformly randomly within the are the lower and upper bounds of the optimization variables, is a uniformly distributed random number, is the quantum collapse probability;

[0179] Embedding submodule, used to embed the pre-prediction layer in the preset vulture search algorithm and dynamically weight the key spatiotemporal factors of the highway , to obtain the improved space-time collaborative quantum vulture search algorithm:

[0180] ;

[0181] Where, is the attention weight, is the query matrix, is the bond matrix, is the value matrix, is the key vector dimension, To scale the dot product attention, is the normalization function;

[0182] A solution submodule is used to solve the highway multi-microgrid multi-mode and multi-functional optimization scheduling model based on the electric vehicle charging spatiotemporal prediction model and the highway multi-microgrid shared energy storage architecture and adopt an improved spatiotemporal collaborative quantum vulture search algorithm suitable for high-speed multi-microgrids to obtain the optimal scheduling strategy for the highway multi-microgrid system.

[0183] In other embodiments of the present invention, the embodiments of the present invention provide the following technical solutions: a computer, comprising a memory 102, a processor 101, and a computer program stored in the memory 102 and executable on the processor 101; when the processor 101 executes the computer program, the multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles as described above is implemented.

[0184] Specifically, the processor 101 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured as one or more integrated circuits for implementing the embodiments of the present invention.

[0185] Memory 102 may include a large-capacity memory for data or instructions. By way of example, and not limitation, memory 102 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 102 may include removable or non-removable (or fixed) media. Where appropriate, memory 102 may be internal or external to the data processing device. In certain embodiments, memory 102 is non-volatile memory. In certain embodiments, memory 102 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM) or a flash memory (FLASH), or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), where the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0186] The memory 102 may be used to store or cache various data files that need to be processed and / or used for communication, as well as possible computer program instructions executed by the processor 101 .

[0187] The processor 101 reads and executes computer program instructions stored in the memory 102 to implement the multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles.

[0188] In some embodiments, the computer may further include a communication interface 103 and a bus 100. Figure 3 As shown, the processor 101 , the memory 102 , and the communication interface 103 are connected via a bus 100 and communicate with each other.

[0189] The communication interface 103 is used to implement communication between the various modules, devices, units, and / or equipment in the embodiments of the present invention. The communication interface 103 can also implement data communication with other components such as external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0190] Bus 100 includes hardware, software, or both, and couples components of a computer device to each other. Bus 100 includes, but is not limited to, at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 100 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Bus 100 may include one or more buses, where appropriate. Although embodiments of the present invention describe and illustrate a particular bus, the present invention contemplates any suitable bus or interconnect.

[0191] The computer can execute the multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles of the present invention based on the multi-microgrid optimization scheduling system obtained based on the spatiotemporal characteristics of electric vehicles, thereby realizing the multi-microgrid optimization scheduling based on the spatiotemporal characteristics of electric vehicles.

[0192] In some further embodiments of the present invention, in combination with the above-mentioned multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles, an embodiment of the present invention provides the following technical solution: a storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles.

[0193] Those skilled in the art will appreciate that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or in conjunction with such instruction execution system, apparatus, or device. For purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by an instruction execution system, apparatus, or device, or in conjunction with such instruction execution system, apparatus, or device.

[0194] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0195] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the aforementioned embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following technologies known in the art may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0196] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0197] The above-described embodiments merely represent several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent. It should be noted that a person of ordinary skill in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, and these variations and improvements fall within the scope of protection of the present invention. Therefore, the scope of protection of the patent for this invention shall be determined by the appended claims.

Claims

1. A multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles, characterized in that: include: Build a highway microgrid model; Build a spatiotemporal prediction model for electric vehicle charging based on graph convolution and improved Autoformer; Build a multi-microgrid shared energy storage architecture for highways; Based on the highway microgrid model, the electric vehicle charging spatiotemporal prediction model and the highway multi-microgrid shared energy storage architecture, a highway multi-microgrid multi-mode and multi-functional optimization scheduling model is constructed; Based on the electric vehicle charging spatiotemporal prediction model, the highway multi-microgrid shared energy storage architecture, and the improved spatiotemporal collaborative quantum vulture search algorithm, the highway multi-microgrid multi-mode and multi-functional optimization scheduling model is solved to obtain the optimal scheduling strategy for the highway multi-microgrid system; In the step of constructing a highway multi-microgrid shared energy storage architecture, the highway multi-microgrid shared energy storage architecture is: Where, Indicates the total state of charge of the virtual energy storage pool, Indicates the total charging power of the virtual energy storage battery, Indicates the total discharge power of the virtual energy storage battery, Represents the total number of distributed energy storage devices and centralized energy storage devices in the virtual energy storage pool, Indicates the number of The state of charge of the device, Respectively represent the first Charging power and discharging power of each device; The multi-microgrid multi-mode multi-function optimization scheduling model for highways is specifically as follows: ； ； ； ； ； ； Where, It is the comprehensive reliability index of the system. is the time section within the scheduling cycle, Number the sub-microgrid in the multi-microgrid system, Power supply adequacy index, is the voltage stability margin, To support the efficiency of energy storage, For microgrids Internal key load nodes, Representation node exist Key load requirements for the time period, Actual supply node Power, For microgrids exist Total critical load demand for the time period, For microgrids Internal busbar node, For nodes exist The voltage amplitude of the time period, is the rated voltage, is the upper limit of the voltage allowed, To support microgrids Energy storage unit, Energy storage unit The discharge power, The reverse power generated by EV, Energy storage unit Charge and discharge efficiency, For microgrids The maximum instantaneous support power required, For maximum energy throughput, is the total number of time periods, Indicates time period The charging power, Indicates time period The discharge power, Represent the charging efficiency and discharging efficiency respectively, Indicates the time interval, To maximize time utilization, 、 Represent the first and second indicator functions respectively.

2. The multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles according to claim 1 is characterized in that: In the step of constructing a highway microgrid model, the highway microgrid model includes a new energy generator set model, a fossil energy generator set model, an energy storage device model, and a power load model; The new energy generator set model includes: Photovoltaic generator model: ； Where, Indicates time The photovoltaic output power, Indicates time The light intensity, represents the effective area of ​​the photovoltaic panel, represents the photovoltaic conversion efficiency, represents the temperature coefficient, Indicates time ambient temperature, Indicates the reference temperature; Wind turbine model: ； Where, Indicates time The wind power output power, Indicates time wind speed, Indicates the cut-in wind speed, Indicates the rated wind speed, Indicates the cut-out wind speed, Indicates the rated power of the fan; The fossil energy generator model is: ； Where, Indicates time The output power of fossil energy units, Respectively represent the minimum output and maximum output of the unit; The energy storage device model is: ； Where, Respectively indicate time The energy storage state of charge, represents the total energy storage capacity, Represent the charging efficiency and discharging efficiency respectively, 、 Represent charging power and discharging power respectively. 、 Respectively represent the maximum charging power and the maximum discharging power, Indicates a time interval; The power load model includes: Conventional electricity load model: Where, Indicates time Conventional power load, Indicates time Known load curve or predicted value; Electric vehicle charging load model: Where, Indicates time The total charging load, Indicates time The number of electric vehicles charged, Indicates the The charging power of the vehicle.

3. The multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles according to claim 1 is characterized in that: The steps to build a spatiotemporal prediction model for electric vehicle charging include: Fusing multi-source data related to highway networks, charging stations, and weekday and holiday traffic flow, converting actual highway routes into a highway topology using graph theory, and fusing the highway topology with the multi-source data to obtain a fused dataset. Performing data preprocessing and hierarchical analysis on the fused data set to obtain electric vehicle charging load prediction characteristics; Based on the electric vehicle charging load prediction characteristics, the time distribution characteristics and spatial distribution characteristics of the electric vehicle are obtained. According to the time distribution characteristics and the spatial distribution characteristics, graph convolution and improved Autoformer are used to perform spatial feature modeling and time feature modeling respectively to obtain an electric vehicle charging spatiotemporal prediction model.

4. The multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles according to claim 1 is characterized in that: The constraints of the highway multi-microgrid multi-mode multi-function optimization scheduling model include: Key load constraints: ； Where, The power shortage ratio allowed for the total critical load; Energy storage battery operating status constraints: ； Where, Indicates the state of charge of the energy storage device. Respectively The minimum and maximum values ​​of Energy storage backup capacity constraints: ； Where, No. Microgrids in Total spare capacity for the time period, 、 For the Microgrids in The spare capacity in the charging mode and discharging mode during the period, For the Microgrids in The load of the period, For the The main load ratio in a microgrid.

5. The multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles according to claim 1 is characterized in that: The step of solving the highway multi-microgrid multi-mode and multi-function optimization scheduling model based on the electric vehicle charging spatiotemporal prediction model, the highway multi-microgrid shared energy storage architecture, and the improved spatiotemporal collaborative quantum vulture search algorithm to obtain the optimal scheduling strategy for the highway multi-microgrid system includes: Obtain a preset vulture search algorithm, initialize the preset vulture search algorithm to a quantum superposition state, and use a quantum coded solution space: ； Where, 、 are the first and second probability amplitudes respectively; When the group in the preset vulture search algorithm falls into a local optimum, the quantum collapse mechanism is triggered and forces the individual to collapse to a certain state according to the probability amplitude: Where, Indicates the Individuals in The new position after iterations, is the current solution position, In the solution space New solutions generated uniformly randomly within the are the lower and upper bounds of the optimization variables, is a uniformly distributed random number, is the quantum collapse probability; Embedding a pre-prediction layer in the preset vulture search algorithm and dynamically weighting the key spatiotemporal factors of the highway , to obtain the improved space-time collaborative quantum vulture search algorithm: ； Where, is the attention weight, is the query matrix, is the bond matrix, is the value matrix, is the key vector dimension, To scale the dot product attention, is the normalization function; Based on the electric vehicle charging spatiotemporal prediction model, the highway multi-microgrid shared energy storage architecture and the improved spatiotemporal collaborative quantum vulture search algorithm suitable for high-speed multi-microgrids, the highway multi-mode and multi-functional optimization scheduling model is solved to obtain the optimal scheduling strategy for the highway multi-microgrid system.

6. A multi-microgrid optimization scheduling system based on the spatiotemporal characteristics of electric vehicles, wherein the system adopts the multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles according to claim 1, characterized in that: The system comprises: The first building module is used to build a highway microgrid model; The second building block is used to build a spatiotemporal prediction model for electric vehicle charging based on graph convolution and improved Autoformer; The third building block is used to build a multi-microgrid shared energy storage architecture for highways; A fourth construction module is configured to construct a highway multi-microgrid multi-mode and multi-functional optimization scheduling model based on the highway microgrid model, the electric vehicle charging spatiotemporal prediction model, and in combination with the highway multi-microgrid shared energy storage architecture; A solution module is used to solve the highway multi-microgrid multi-mode and multi-functional optimization scheduling model based on the electric vehicle charging spatiotemporal prediction model, the highway multi-microgrid shared energy storage architecture, and the improved spatiotemporal collaborative quantum vulture search algorithm to obtain the optimal scheduling strategy for the highway multi-microgrid system.

7. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles as described in any one of claims 1 to 5 is implemented.

8. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the multi-microgrid optimization scheduling method based on the spatiotemporal characteristics of electric vehicles as described in any one of claims 1 to 5.

Images