New Energy Vehicle Charging Pile Load Balancing and Scheduling Method Based on Intelligent Algorithm

Abstract

The present invention relates to the technical field of new energy vehicles, and particularly to a load balancing and scheduling method for new energy vehicle charging piles based on intelligent algorithms, comprising the following steps: S1, data acquisition: real-time acquisition of the operating data of the charging piles; S2, charging demand prediction: prediction of the charging demands of each charging pile within a predetermined future time through a graph convolutional network model; S3, spatial scheduling optimization of the charging piles: according to the geographical distribution of the charging piles, the surrounding vehicle flow, and the results of the charging demand prediction, spatial optimization of the scheduling of the charging piles is carried out; S4, load scheduling and resource allocation: based on the results of the charging demand prediction and the spatial scheduling optimization of the charging piles, combined with the grid load situation, resource allocation is carried out. The present invention improves the utilization efficiency of the charging pile resources, optimizes the layout of the overall charging network, and ensures the fairness of the charging service and the balance of the grid load.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy vehicles, and particularly to a load balancing and scheduling method for new energy vehicle charging piles based on intelligent algorithms. Background Art

[0002] With the popularization of new energy vehicles, charging piles, as important infrastructure, have become a key link in promoting the development of the new energy vehicle industry. However, there are still great challenges in the operation efficiency, resource utilization rate of charging piles and the coordination problem with the power grid. The demand for charging piles is affected by multiple factors such as vehicle flow, power grid load and time period within a region. The demand differences in different regions and time periods lead to uneven distribution of charging pile resources, too long idle time of charging piles in some regions, while overloading may occur in other regions. Therefore, how to achieve load balancing and scheduling optimization of the charging pile network, improve the resource utilization efficiency of charging piles, and ensure the stable operation of the power grid at the same time is the focus and difficulty concerned by the current industry.

[0003] The existing technologies mainly rely on traditional static scheduling methods or single prediction models for charging pile resource allocation, and there are various deficiencies. On the one hand, static scheduling methods are difficult to respond to the dynamic changes of regional charging demands in real time, resulting in uneven resource allocation or lagging scheduling. On the other hand, the existing prediction models fail to fully consider the spatial correlation between charging piles and the dynamic changes of the surrounding environment (such as vehicle flow, power grid load), resulting in low accuracy of charging demand prediction. In addition, the existing technologies lack systematic optimization methods and cannot achieve full-process optimization from charging demand prediction, spatial scheduling to load allocation, with low resource utilization efficiency and service capacity, and it is difficult to ensure the use efficiency of charging piles and the balance of power grid operation.

[0004] To solve the deficiencies of the existing technologies, the present invention provides a load balancing and scheduling method for new energy vehicle charging piles based on intelligent algorithms, realizing efficient coordination between the charging pile network and the power grid, thereby optimizing the operation efficiency of the charging network, reducing the operation pressure of the power grid, and promoting the intelligent development of new energy vehicle charging infrastructure. Summary of the Invention

[0005] The present invention provides a load balancing and scheduling method for new energy vehicle charging piles based on intelligent algorithms.

[0006] The load balancing and scheduling method for new energy vehicle charging piles based on intelligent algorithms includes the following steps:

[0007] S1, data collection: Real-time collect the operation data of charging piles, including usage conditions, surrounding vehicle flow, battery status and power grid load;

[0008] S2, Charging demand prediction: Based on the collected operation data of charging piles, predict the charging demand of each charging pile within a predetermined future time (1 hour) through a Graph Convolutional Network (GCN) model;

[0009] S3, Spatial scheduling optimization of charging piles: According to the geographical distribution of charging piles, the surrounding vehicle flow, and the results of charging demand prediction, optimize the spatial scheduling of charging piles, specifically including:

[0010] S31, Regional demand assessment: According to the results of charging demand prediction, assess the demand in the area where the charging pile is located;

[0011] S32, Scheduling priority ranking: According to the results of regional demand assessment, formulate priorities for charging pile resource allocation and optimize resource distribution;

[0012] S33, Charging pile location optimization and layout adjustment: Based on the results of scheduling priority ranking, combined with the surrounding vehicle flow and the results of charging demand prediction, optimize the layout and location of charging piles;

[0013] S4, Load scheduling and resource allocation: Based on the results of charging demand prediction and the spatial scheduling optimization of charging piles, combined with the grid load situation, conduct resource allocation.

[0014] Optionally, the data collection in S1 includes:

[0015] S11, Charging pile usage: Through the intelligent terminal installed on the charging pile, real-time monitor the usage status, charging power, charging duration, and number of users of the charging pile;

[0016] S12, Surrounding vehicle flow: Through the vehicle flow monitoring equipment (traffic cameras) installed around the charging pile, real-time collect the vehicle flow data on the roads around the charging pile, and dynamically update it in combination with the real-time vehicle flow information provided by the traffic data platform;

[0017] S13, Battery status: Through the Battery Management System (BMS) of new energy vehicles connected to the charging pile, real-time obtain the battery power, charging status, and temperature of the vehicle;

[0018] S14, Grid load: Through the power load monitoring sensors installed at key nodes of the grid, real-time obtain the load situation, voltage fluctuation, and current data of the grid.

[0019] Optionally, the charging demand prediction in S2 includes:

[0020] S21. Construct the charging pile graph structure: Construct the graph structure of charging piles based on the geographical locations and spatial relationships between charging piles. Consider the charging piles as nodes in the graph, and the node features include the historical usage of charging piles, the surrounding vehicle flow, the battery status, and the grid load. The edges between charging piles represent the spatial or traffic dependence relationships between them, and the edge weights are assigned based on the Euclidean distance and the surrounding vehicle flow;

[0021] S22. Graph convolution operation: In the graph convolutional network (GCN) model, use the graph convolution operation to process the charging pile graph structure. The graph convolution operation propagates through the adjacency matrix and the node feature matrix .

[0022] S23. Charging demand prediction: At the last layer of the graph convolutional network (GCN) model, map the node features to the predicted values through a fully connected layer, that is, the charging demand of each charging pile within a predetermined future time (1 hour).

[0023] Optionally, the regional demand assessment in S31 includes:

[0024] S311. Collect charging demand prediction data: Collect the predicted charging demand of each charging pile;

[0025] S312. Calculate the charging pile weight: Calculate the weight of the charging pile by considering the traffic flow around the charging pile and the geographical location (through the Euclidean distance ); ;

[0026] S313. Evaluate the total regional charging demand: Based on the predicted charging demand of each charging pile and the corresponding weight , evaluate the charging demand of the entire region. The total regional charging demand is the weighted average of the demands of each charging pile in the region.

[0027] Optionally, the scheduling priority ranking in S32 includes:

[0028] S321. Calculate the charging pile priority: According to the regional demand assessment result and the predicted charging demand of each charging pile, calculate the priority score of each charging pile and rank the charging piles according to the priority;

[0029] S322. Priority ranking: According to the calculated priority scores of the charging piles, rank all the charging piles. The charging piles with higher priority are ranked in the front. The priority ranking of the charging piles determines the order of resource allocation;

[0030] S323, Resource Allocation Optimization: During the scheduling process, according to the priority sorting result, charging resources are allocated in descending order. When resources are limited, charging piles with higher priorities are preferentially satisfied.

[0031] Optionally, the charging pile location optimization and layout adjustment in S33 include:

[0032] S331, Determine the Priority Location Distribution of Charging Piles: According to the priority sorting result of charging piles, charging piles are preferentially deployed in high-priority areas;

[0033] S332, Adjust the Layout Based on Demand and Traffic: Combine the surrounding vehicle traffic and the prediction result of charging demand to optimize the distribution of charging piles.

[0034] Optionally, the adjusting the layout based on demand and traffic in S332 includes:

[0035] S3321, Calculate the Demand and Traffic Weight: According to the prediction result of charging demand in the area and the surrounding vehicle traffic, calculate the comprehensive demand traffic weight of each charging pile area ;

[0036] S3322, Optimize the Layout of Charging Piles: According to the comprehensive demand traffic weight , optimize the layout of charging piles. When exceeds the high demand threshold , it is defined as a high demand and high traffic area, and the density of charging piles is increased. When is lower than the low demand threshold , it is defined as a low demand and low traffic area, and the number of charging piles is reduced or the resource allocation is optimized by sharing charging piles.

[0037] Optionally, the load scheduling and resource allocation in S4 include:

[0038] S41, Adjust the Load Demand: According to the prediction result of charging demand, the comprehensive demand traffic weight of the charging pile space scheduling optimization , combined with the real-time load situation of the power grid , dynamically adjust the load priority of each area;

[0039] S42, Resource Allocation and Execution: Based on the adjusted area load priority, calculate the resource allocation amount.

[0040] Optionally, the load demand adjustment in S41 includes:

[0041] S411, Evaluate the Area Demand and Grid Carrying Capacity: According to the comprehensive demand traffic weight of the area Based on the real-time load situation of the power grid, by calculating the remaining carrying capacity of the power grid, it is determined whether it is necessary to limit or adjust the regional load;

[0042] S412, Dynamically adjust the regional priority: Combining the comprehensive demand flow weight and the remaining carrying capacity of the power grid, dynamically adjust the load priority of each region.

[0043] Optionally, the resource allocation and execution in S42 include:

[0044] S421, Calculate the resource allocation amount: According to the adjusted regional priority and the total available resource amount, calculate the resource allocation amount for each region;

[0045] S422, Execute resource allocation: Allocate the calculated resource allocation amount to the charging piles in each region.

[0046] Advantages of the present invention:

[0047] In the present invention, through the comprehensive collection and integrated analysis of the operation data of new energy vehicle charging piles, accurate prediction of charging demand is achieved. Based on the graph convolutional network model, fully combining the geographical location of the charging piles, the surrounding vehicle flow, the battery state and the power grid load, a spatial relationship graph between the charging piles is constructed, and the future charging demand is predicted through node feature propagation and fully connected layers, significantly improving the accuracy and adaptability of the prediction. The accurate charging demand prediction provides a scientific basis for subsequent scheduling optimization, ensuring that the charging demands in different regions at different time periods are promptly responded to, thereby effectively improving the load balance and operation efficiency of the charging pile network.

[0048] In the present invention, through the spatial scheduling optimization of the charging piles, combining regional demand assessment, priority ranking, and the optimization and layout adjustment of the charging pile locations, the spatial distribution of the charging pile resources can be dynamically optimized, clarifying the characteristics of high-demand and high-flow regions and low-demand and low-flow regions, formulating targeted resource allocation strategies, not only reducing the idle time of the charging piles, but also avoiding the overloading phenomenon, significantly improving the utilization efficiency of the charging pile resources, optimizing the layout of the overall charging network, and ensuring the fairness of the charging service and the balance of the power grid load.

[0049] In the present invention, by dynamically adjusting the regional priority and power resource allocation strategy, the efficiency and fairness of charging resources are ensured. Combining the real-time load situation of the power grid and regional demands, the remaining carrying capacity of the power grid is calculated in real time, and the priorities of high-demand areas and low-demand areas are dynamically adjusted to avoid power grid overload, improve the flexibility of resource allocation. The resource allocation and execution are based on the adjusted priorities, and power resources are reasonably allocated to not only meet the service requirements of high-demand areas but also optimize the resource utilization rate of low-demand areas, ensuring the efficient coordination of the charging pile network and the power grid system, significantly reducing the operation cost, and enhancing the response ability, service quality of the charging network, as well as the operation stability and sustainability of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only those of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0051] Figure 1 Schematic diagram of the balance and scheduling method process for the embodiments of the present invention;

[0052] Figure 2 Schematic diagram of the optimization of the charging pile space scheduling for the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] The present invention will be described in detail below in conjunction with the drawings and specific embodiments. At the same time, it should be noted here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments. For some well-known technologies, those skilled in the art can also adopt other alternative methods for implementation; and the drawings are only for more specifically describing the embodiments and are not intended to specifically limit the present invention.

[0054] As Figure 1 - Figure 2 shown, the load balancing and scheduling method for new energy vehicle charging piles based on intelligent algorithms includes the following steps:

[0055] S1, Data collection: Real-time collect the operation data of the charging piles, including usage, surrounding vehicle flow, battery status, and power grid load;

[0056] S2, Charging demand prediction: Based on the collected operation data of the charging piles, predict the charging demands of each charging pile within a predetermined future time (1 hour) through a graph convolutional network (GCN) model;

[0057] S3. Optimization of Charging Pile Space Scheduling: Based on the geographical distribution of charging piles, the surrounding vehicle flow, and the results of charging demand prediction, conduct spatial optimization of the charging pile scheduling to reduce the idle time of charging piles and avoid overloading. Specifically, it includes:

[0058] S31. Regional Demand Assessment: Based on the results of charging demand prediction, assess the demand in the area where the charging piles are located;

[0059] S32. Scheduling Priority Ranking: Based on the results of regional demand assessment, formulate priorities for the allocation of charging pile resources to optimize resource distribution;

[0060] S33. Optimization of Charging Pile Location and Layout Adjustment: Based on the results of scheduling priority ranking, combined with the surrounding vehicle flow and the results of charging demand prediction, optimize the layout and location of charging piles to ensure the efficient use of resources;

[0061] S4. Load Scheduling and Resource Allocation: Based on the results of charging demand prediction and the optimization of charging pile space scheduling, combined with the grid load situation, conduct resource allocation;

[0062] Through the above content, it is possible to predict charging demand in real time, and through strategies such as spatial scheduling optimization, load scheduling, and resource allocation, effectively improve the utilization efficiency of charging pile resources, reduce the idle time of charging piles, avoid overloading, thereby achieving the efficient allocation of charging pile resources and the balance of grid load. This not only improves the service capacity of charging piles but also helps to reduce the operating pressure on the grid and ensure the sustainable development of new energy vehicle charging infrastructure.

[0063] The data collection in S1 includes:

[0064] S11. Charging Pile Usage: Through the intelligent terminal installed on the charging pile, monitor the usage status, charging power, charging duration, and number of users of the charging pile in real time;

[0065] S12. Surrounding Vehicle Flow: Through the installation of vehicle flow monitoring devices (traffic cameras) around the charging piles, collect the vehicle flow data on the roads around the charging piles in real time, and dynamically update it in combination with the real-time vehicle flow information provided by the traffic data platform;

[0066] S13. Battery Status: Through the battery management system (BMS) of new energy vehicles connected to the charging piles, obtain the battery power, charging status, and temperature of the vehicles in real time;

[0067] S14. Grid Load: Through the power load monitoring sensors installed at key grid nodes, obtain the grid load situation, voltage fluctuations, and current data in real time;

[0068] Through the above, the operating conditions of the charging piles and the surrounding environment can be comprehensively and accurately grasped. By integrating Internet of Things, sensor, and communication technologies, the load distribution of the charging piles can be dynamically adjusted to ensure the efficiency and safety of the charging process, while avoiding grid overload. This not only improves the utilization efficiency of charging pile resources but also provides accurate data support for subsequent charging demand prediction, load scheduling, and resource optimization, thereby effectively reducing the operating costs of charging facilities and enhancing the overall coordination and sustainability of the power grid and transportation system.

[0069] The charging demand prediction in S2 includes:

[0070] S21, constructing the charging pile graph structure: Construct the graph structure of the charging piles according to the geographical location and spatial relationship between the charging piles. Consider the charging piles as nodes in the graph, and the node features include the historical usage of the charging piles, the surrounding vehicle flow, the battery status, and the grid load. The edges between the charging piles represent the spatial or traffic dependence relationship between the charging piles, and the edge weights are assigned through the Euclidean distance and the surrounding vehicle flow, expressed as:

[0071] ;

[0072] Among them, represents the Euclidean distance between charging pile and charging pile , and are the coordinates of the two charging piles respectively;

[0073] ;

[0074] Among them, represents the edge weight of the traffic flow influence between charging pile and charging pile , and are the traffic flows near charging piles and respectively;

[0075] ;

[0076] Among them, is the comprehensive edge weight between charging pile and charging pile , and are the weight coefficients;

[0077] S22, graph convolution operation: In the graph convolutional network (GCN) model, use the graph convolution operation to process the charging pile graph structure. The graph convolution operation is performed through the adjacency matrix and the node feature matrix Propagation is expressed as:

[0078] ;

[0079] Among them, is the node feature representation of the th layer. Initially, , is the normalized adjacency matrix, which is used to represent the relationship between charging piles, is the weight matrix of the th layer, is the ReLU activation function, is the node feature representation of the th layer, and the spatial features of the charging piles are extracted layer by layer;

[0080] S23, charging demand prediction: At the last layer of the graph convolutional network (GCN) model, the node features are mapped to the predicted values through a fully connected layer, that is, the charging demand of each charging pile within a predetermined future time (1 hour), which is expressed as:

[0081] ;

[0082] Among them, is the feature representation of the th charging pile at the last layer, is the weight matrix of the fully connected layer, is the bias term, is the predicted charging demand of the th charging pile in the next hour;

[0083] Through the above content, it is possible to effectively combine multi-dimensional data such as the geographical location of charging piles, the surrounding vehicle flow, and the grid load, construct a spatial relationship graph between charging piles, and thus accurately predict the future charging demand of charging piles. By graph convolutional operations, the spatial and traffic dependencies between charging piles are extracted, which not only considers the historical usage of charging piles but also the impact of the surrounding environment. It can more flexibly adapt to the demand fluctuations in different regions and time periods, improve the accuracy of charging demand, optimize the load balancing and scheduling of charging piles, provide strong support for the efficient utilization of grid resources and the reasonable layout of new energy vehicle charging facilities, and further promote the coordinated development of the smart grid and the intelligent transportation system.

[0084] The regional demand assessment in S31 includes:

[0085] S311, collecting charging demand prediction data: Collecting the predicted charging demand of each charging pile;

[0086] S312, calculating the charging pile weight: By considering the traffic flow around the charging pile and geographical location (using Euclidean distance ) to calculate the weight of the charging pile , expressed as:

[0087] ;

[0088] Among them, is the weight of the charging pile , is the traffic flow around the charging pile , is the Euclidean distance from the charging pile to the nearest traffic node (such as an intersection), is the total number of all charging piles;

[0089] S313, evaluating the total charging demand of the area: Based on the predicted charging demand of each charging pile and the corresponding weight , evaluate the charging demand of the entire area. The total charging demand of the area is the weighted average of the demands of each charging pile in the area, expressed as:

[0090] ;

[0091] Among them, is the total charging demand of the area at time , is the predicted charging demand value of the charging pile at time ;

[0092] Through the above content, combined with the predicted charging demand of the charging pile, the surrounding traffic flow, and the geographical location, it provides an accurate decision-making basis for the allocation of charging pile resources. By considering the traffic flow and geographical distribution through weighting, it can better identify high-demand areas and key charging piles, avoid over-concentration or over-dispersion of resources, help improve the utilization efficiency of charging piles, optimize the layout of charging piles, ensure that charging resources can be reasonably allocated during high-demand charging periods, thereby improving the load balance and stability of the overall charging network, reducing the idle time of charging piles, avoiding overload phenomena, and maximizing the utilization rate of grid resources.

[0093] The scheduling priority ranking in S32 includes:

[0094] S321, calculating the charging pile priority: According to the regional demand evaluation result and the predicted charging demand of each charging pile, calculate the priority score of each charging pile, and rank the charging piles in priority, expressed as:

[0095] ;

[0096] S322, Priority Sorting: Based on the calculated priority scores of charging piles , sort all charging piles. The charging piles with higher priorities are ranked in the front. The priority sorting of charging piles determines the order of resource allocation. The sorting formula is expressed as:

[0097] ;

[0098] Among them, is the list of charging pile priority scores arranged in order of priority, represents the priority score of the charging pile;

[0099] S323, Resource Allocation Optimization: During the scheduling process, according to the priority sorting results, allocate charging resources in descending order. When resources are limited, give priority to charging piles with higher priorities to ensure that the charging piles in high-demand areas can obtain the required power support in a timely manner, and avoid resource waste or overloading. It is expressed as:

[0100] ;

[0101] Among them, is the resource allocated to the charging pile , is the priority score of the charging pile , is the total available resource quantity (total power capacity or the number of available charging interfaces of the charging pile), is the total number of charging piles;

[0102] Through the above content, resources can be reasonably allocated to charging piles. Through priority scoring, it is ensured that charging piles with higher demands obtain charging resources first, thus avoiding resource waste and overloading of some charging piles, effectively improving the resource utilization efficiency of charging piles, optimizing the overall operation of the charging network, ensuring the timely satisfaction of charging demands. In addition, the priority-based resource allocation method can flexibly respond to dynamic demand changes in different regions, help balance the grid load, reduce the impact of power fluctuations on charging piles, and improve the stability and sustainability of the system.

[0103] The charging pile location optimization and layout adjustment in S33 include:

[0104] S331, Determine the Priority Location Distribution of Charging Piles: According to the priority sorting results of charging piles, deploy charging piles in high-priority areas first;

[0105] S332, Adjust the Layout Based on Demand and Traffic: Combine the surrounding vehicle traffic and the predicted results of charging demands to optimize the distribution of charging piles;

[0106] Through the above, the efficient allocation of charging pile resources is achieved, ensuring the concentrated layout of charging piles in areas with high demand, improving the coverage rate and response speed of charging services. At the same time, it avoids resource waste in low-demand areas, improves the utilization efficiency of charging piles, balances the load, reduces the impact of grid fluctuations, and enhances the service capacity of charging facilities and the stability of the power grid.

[0107] The layout adjustment based on demand and traffic in S332 includes:

[0108] S3321, calculation of demand and traffic weights: According to the charging demand prediction results of the area and the surrounding vehicle traffic, calculate the comprehensive demand traffic weight of each charging pile area , expressed as:

[0109] ;

[0110] Among them, and are the corresponding weight coefficients respectively, is the charging demand prediction result of the area, is the surrounding vehicle traffic, and are the maximum values of the charging demand values and traffic values in all areas respectively;

[0111] S3322, optimization of charging pile layout: According to the comprehensive demand traffic weight , optimize the layout of charging piles. When exceeds the high-demand threshold , it is defined as a high-demand and high-traffic area, and the density of charging piles is increased to meet higher charging demand and traffic demand. When is lower than the low-demand threshold , it is defined as a low-demand and low-traffic area, and the number of charging piles is reduced or the resource allocation is optimized by sharing charging piles to avoid resource waste;

[0112] The setting of the high-demand threshold and the low-demand threshold specifically includes:

[0113] Calculate the average value and standard deviation of the comprehensive demand traffic weight: According to the comprehensive demand traffic weight of each area, calculate the mean value and standard deviation of the comprehensive weights of all areas, expressed as:

[0114] ;

[0115] ;

[0116] Among them, is the total number of regions, is the comprehensive demand flow weight;

[0117] Set the high demand threshold: The high demand threshold is set based on the mean and standard deviation of the comprehensive weight, expressed as:

[0118] ;

[0119] Among them, is the adjustment coefficient, and its value ranges from 1 to 2;

[0120] Set the low demand threshold: The low demand threshold is set based on the mean and standard deviation of the comprehensive weight, expressed as:

[0121] ;

[0122] Among them, is the adjustment coefficient, and its value ranges from 1 to 2;

[0123] Through the above content, the precise optimization of the charging pile layout is realized, and high-demand high-flow regions and low-demand low-flow regions can be effectively identified, so as to achieve the reasonable allocation of resources. For high-demand regions, increase the charging pile density to meet the actual demand. For low-demand regions, reduce resource input or improve the utilization rate through shared charging piles, significantly improving the utilization efficiency of charging pile resources, optimizing the overall layout, reducing resource waste at the same time, ensuring the fairness of charging services and the balance of the power grid load.

[0124] The load scheduling and resource allocation in S4 include:

[0125] S41, Load demand adjustment: According to the charging demand prediction result and the comprehensive demand flow weight of the charging pile space scheduling optimization , combined with the real-time load situation of the power grid , dynamically adjust the load priority of each region to adapt to the load condition of the power grid and the regional demand;

[0126] S42, Resource allocation and execution: Based on the adjusted regional load priority, calculate the resource allocation amount to ensure the efficiency and fairness of resource allocation;

[0127] Through the above, it is possible to preferentially meet the charging needs of high-demand and high-weight regions, while dynamically adjusting the power distribution to avoid grid overload, thereby achieving the efficiency and fairness of resource allocation. Through real-time monitoring and feedback optimization, it is ensured that the load scheduling can adapt to the grid load fluctuations and regional demand changes, improving the response ability, resource utilization rate and overall service quality of the charging network, while ensuring the stability and reliability of the grid.

[0128] The load demand adjustment in S41 includes:

[0129] S411, evaluating the regional demand and grid carrying capacity: According to the comprehensive demand flow weight of the region and the real-time load condition of the grid, by calculating the remaining carrying capacity of the grid, judge whether it is necessary to limit or adjust the regional load, expressed as:

[0130] ;

[0131] Among them, represents the current remaining carrying capacity of the grid, is the maximum carrying load of the grid, is the real-time load of the current grid;

[0132] S412, dynamically adjusting the regional priority: Combining the comprehensive demand flow weight and the remaining carrying capacity of the grid, dynamically adjust the load priority of each region;

[0133] ;

[0134] Among them, is the load demand priority of the region;

[0135] Through the above, by real-time evaluating the remaining carrying capacity of the grid, it is ensured that the charging demand of high-demand regions can be met without causing grid overload. The dynamic priority adjustment mechanism enables high-demand regions to be preferentially allocated resources, while the resource use of low-demand regions is optimized, thereby achieving efficient coordination between the charging pile network and the grid, improving the flexibility of resource allocation and the stability of system operation.

[0136] The resource allocation and execution in S42 include:

[0137] S421, calculating the resource allocation amount: According to the adjusted regional priority and the total available resource amount, calculate the resource allocation amount for each region, expressed as:

[0138] ;

[0139] Among them, is the resource amount allocated to the region, is the total available resources of the power grid at present, is the total number of regions;

[0140] S422. Execute resource allocation: allocate the calculated resource allocation amount to the charging piles in each region;

[0141] Through the above content, it is ensured that the resource allocation matches the actual needs of the regions, enabling regions with high priority and high demand to obtain more sufficient resource support. At the same time, it is ensured that the basic resource allocation of low-demand regions is not ignored, and the allocation strategy is adjusted in a timely manner according to the changes in the power grid load and demand, effectively avoiding resource waste and power grid overload, and improving the overall resource utilization efficiency, charging service capacity, and the operation stability and flexibility of the power grid.

[0142] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A new energy vehicle charging pile load balancing and scheduling method based on an intelligent algorithm, characterized in that: The following steps are involved: S1, data collection: real-time collection of charging pile operation data, including usage, surrounding vehicle flow, battery status and grid load; S2, charging demand prediction: Based on the collected operation data of charging piles, the charging demand of each charging pile within the future scheduled time is predicted through the graph convolutional network model; S3, Optimization of charging pile spatial scheduling: Based on the geographical distribution of charging piles, the surrounding vehicle flow and the results of charging demand forecast, the scheduling of charging piles is spatially optimized, including: S31, regional demand assessment: Based on the charging demand forecast results, combined with the traffic flow around the charging pile and the geographical location of the charging pile, the demand in the area where the charging pile is located is assessed; S32, scheduling priority sorting: setting priorities for charging pile resource allocation based on the results of regional demand assessment and the predicted charging demand of each charging pile, and optimizing resource distribution; S33, charging pile location optimization and layout adjustment: based on the results of scheduling priority sorting, combined with the surrounding vehicle flow and charging demand prediction results, optimize the layout and location of the charging piles; S4, load scheduling and resource allocation: Based on the results of charging demand prediction and charging pile space scheduling optimization, combined with the grid load situation, resource allocation is performed. The load scheduling and resource allocation includes: S41, load demand adjustment: according to the comprehensive demand flow weight after the optimization of charging pile space scheduling , combined with the real-time load conditions of the power grid , dynamically adjust the load priority of each area, where the comprehensive demand flow weight Optimization calculation is performed based on the charging demand forecast results of the area and the surrounding vehicle flow, including: S411, Assessment of regional demand and grid carrying capacity: Based on the comprehensive demand flow weight of the region and the real-time load situation of the power grid, and by calculating the remaining carrying capacity of the power grid, determine whether it is necessary to limit or adjust the regional load; S412, dynamically adjust regional priorities: dynamically adjust the load priority of each region based on the comprehensive demand flow weight and the remaining carrying capacity of the power grid; The charging demand prediction in S2 includes: S21, constructing a graph structure of charging piles: constructing a graph structure of charging piles according to the geographical locations and spatial relationships between charging piles, treating charging piles as nodes in the graph, and node features including historical charging pile usage, surrounding vehicle flow, battery status, and grid load. Edges between charging piles represent spatial or traffic dependencies between charging piles, and edge weights are assigned by the Euclidean distance between charging piles and surrounding vehicle flow. S22, graph convolution operation: In the graph convolution network model, the graph convolution operation is used to process the charging pile graph structure. The graph convolution operation is performed through the adjacency matrix and the node feature matrix To spread; S23, Charging demand prediction: In the last layer of the graph convolutional network model, the node features are mapped to the predicted values ​​through the fully connected layer, that is, the charging demand of each charging pile within the scheduled time in the future.

2. The method for load balancing and scheduling of new energy vehicle charging piles based on intelligent algorithm according to claim 1 is characterized in that: The data collection in S1 includes: S11, Charging pile usage: through the smart terminal installed on the charging pile, the usage status, charging power, charging time and number of users of the charging pile are monitored in real time; S12, surrounding vehicle flow: by installing vehicle flow monitoring equipment around the charging pile, the vehicle flow data of the roads around the charging pile is collected in real time, and combined with the real-time vehicle flow information provided by the traffic data platform, it is dynamically updated; S13, battery status: obtain the battery power, charging status and temperature of the vehicle battery in real time through the new energy vehicle battery management system connected to the charging pile; S14, Grid load: Power load monitoring sensors installed at key grid nodes are used to obtain grid load conditions, voltage fluctuations, and current data in real time.

3. The method for load balancing and scheduling of new energy vehicle charging piles based on intelligent algorithm according to claim 1 is characterized in that: The regional needs assessment in S31 includes: S311, collecting charging demand prediction data: collecting the predicted charging demand of each charging pile; S312, calculating the weight of the charging pile: by considering the traffic flow around the charging pile and geographic location to calculate the weight of the charging pile ; S313, evaluate the total charging demand in the region: based on the predicted charging demand and corresponding weight of each charging pile , evaluate the charging demand of the entire region, the total regional charging demand It is the weighted average of the demand for charging piles in the region.

4. The method for load balancing and scheduling of new energy vehicle charging piles based on intelligent algorithm according to claim 3 is characterized in that: The scheduling priority sorting in S32 includes: S321, calculate charging pile priority: based on regional demand assessment results and the predicted charging demand of each charging pile, and calculate the priority score of each charging pile , prioritize the charging piles; S322, Priority sorting: based on the calculated charging pile priority score , sort all charging piles, and the charging piles with high priority are placed in front. The priority sorting of charging piles determines the order of resource allocation; S323, resource allocation optimization: During the scheduling process, charging resources are allocated in descending order according to the priority sorting results. When resources are limited, charging piles with high priority are given priority.

5. The method for load balancing and scheduling of new energy vehicle charging piles based on intelligent algorithm according to claim 4 is characterized in that: The charging pile location optimization and layout adjustment in S33 include: S331, determining the priority location distribution of charging piles: according to the priority sorting result of the charging piles, the charging piles are preferentially deployed in high priority areas; S332, adjust layout based on demand and flow: optimize the distribution of charging piles based on surrounding vehicle flow and charging demand forecast results.

6. The method for load balancing and scheduling of new energy vehicle charging piles based on intelligent algorithm according to claim 5 is characterized in that: The demand- and traffic-based layout adjustment in S332 includes: S3321, Demand and flow weight calculation: Calculate the comprehensive demand flow weight of each charging pile area based on the charging demand forecast results of the area and the surrounding vehicle flow. ; S3322, Optimization of charging pile layout: based on comprehensive demand flow weight , optimize the layout of charging piles, when Exceeding high demand threshold When the area is defined as a high-demand high-flow area, the density of charging piles is increased. Below low demand threshold When defining areas with low demand and low traffic, the number of charging piles can be reduced or resource allocation can be optimized by sharing charging piles.

7. The method for load balancing and scheduling of new energy vehicle charging piles based on intelligent algorithm according to claim 6 is characterized in that: The S4 also includes resource allocation and execution: calculating resource allocation amount based on the adjusted regional load priority.

8. The method for load balancing and scheduling of new energy vehicle charging piles based on intelligent algorithm according to claim 7 is characterized in that: The resource allocation and execution include: Calculate resource allocation: Calculate resource allocation for each region based on the adjusted region priority and total available resources. Execute resource allocation: Allocate the calculated resource allocation to the charging piles in each area.

Images