Charging pile intelligent scheduling system and method based on edge calculation

Abstract

The invention discloses an intelligent charging pile scheduling system and method based on edge computing. The intelligent charging pile scheduling system comprises a data acquisition module, an edge computing node, an edge algorithm module, a data sharing and collaboration module, a user interface module, an energy management module and a fault diagnosis module. By transferring the data processing task to the edge device for processing, the situation of data transmission delay can be reduced, the real-time performance is improved, and therefore the scheduling timeliness and the calling efficiency are improved, in addition, through combination of the edge computing node and the edge algorithm module, intelligent scheduling and management can be achieved according to various situations and factors, and the scheduling efficiency is improved. A local scheduling decision is made, the utilization efficiency of charging pile resources is optimized, the experience is smoother when a user uses the charging pile, the waiting time of the user is shortened, and the satisfaction degree of the user is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent scheduling of charging piles, and in particular to an intelligent scheduling system and method for charging piles based on edge computing. Background Art

[0002] Intelligent scheduling of charging piles is to optimize and schedule the use of charging piles by real-time monitoring of the usage of charging piles, battery charging status, user needs and other information, so as to improve charging efficiency, reduce energy consumption and reduce user waiting time. The intelligent scheduling system of charging piles in the prior art has the following shortcomings during use: 1. Long data transmission delay, resulting in untimely scheduling and low scheduling efficiency; 2. In the process of analyzing and scheduling, it is impossible to perform intelligent analysis and calculation according to various complex situations and factors, resulting in insufficient energy utilization, poor user experience and unsatisfactory scheduling effect; Based on the above, this application proposes a charging pile intelligent scheduling system and method based on edge computing. Summary of the invention

[0003] Based on the technical problems existing in the background technology, the present invention proposes a charging pile intelligent scheduling system and method based on edge computing.

[0004] The present invention proposes an edge computing-based charging pile intelligent scheduling system, which includes a data acquisition module, an edge computing node, an edge algorithm module, a data sharing and collaboration module, a user interface module, an energy management module and a fault diagnosis module;

[0005] The data acquisition module, energy management module and fault diagnosis module are all connected to the charging pile, the edge algorithm module is deployed on the edge computing node, the edge algorithm module and the fault diagnosis module are both connected to the user interface module, the energy management module is connected to the user interface module and the edge computing node, and the data sharing and collaboration module is connected to the edge computing node.

[0006] Preferably, the data acquisition module is used to collect data in real time from each charging pile, including information on the status of the charging pile, user charging needs and charging speed, and the collected information is transmitted to the edge computing node, which uses a low-latency, high-bandwidth edge network to transmit the information.

[0007] Preferably, the edge computing node is a computing and data processing unit located on the edge device, responsible for real-time processing and analysis of the collected data, and executing intelligent algorithms in conjunction with the edge algorithm module to make local scheduling decisions;

[0008] The specific logical steps are as follows:

[0009] (1) The edge computing node cleans, formats, and removes noise from the collected data to ensure data quality;

[0010] (2) The edge computing node combines with the edge algorithm module to extract useful feature data from the data using the support vector machine intelligent algorithm, train the feature data, generate a support vector machine model, input the real-time collected data into the trained support vector machine model, and use the trained support vector machine model to classify the real-time collected data and find out the patterns and features in the data;

[0011] (3) Based on the analysis results of the support vector machine, predictions about the status of charging piles and user needs can be obtained, and local scheduling decisions can be made based on the prediction results;

[0012] (4) The edge computing node allocates and schedules charging pile resources based on the local scheduling decisions made to optimize resource utilization efficiency.

[0013] Preferably, in (3), the local scheduling decision is as follows:

[0014] ① Charging pile resource allocation: According to user needs and the real-time status of charging piles, decide which charging piles will be allocated to which users for charging to maximize resource utilization efficiency. The mathematical expression used is:

[0015] Among them C ij represents the cost of assigning vehicle i to charging station j (including distance and waiting time), X ij ∈{0,1}, represents the allocation variable. If vehicle i is assigned to charging station j, then X ij =1, otherwise 0;

[0016] ② Priority sorting of charging piles: Prioritize the charging piles according to user needs, load conditions of the charging piles, and performance indicators of the charging piles, and give priority to allocating charging pile resources to important users or users who are in urgent need of charging. The mathematical expression used is:

[0017]

[0018] Where λ is the arrival rate (the rate at which vehicle requests arrive), μ is the service rate (the rate at which charging piles process requests), and T - is the average waiting time. By optimizing λ and μ, the waiting time of vehicles in queue can be reduced;

[0019] ③. Optimize charging speed: By adjusting the charging power and charging time of each charging pile, the charging speed is optimized to make the charging process more efficient and reduce user waiting time;

[0020] ④. Consider the grid load: Combined with the local grid load situation, avoid excessive consumption of grid resources and maintain the smooth operation of the grid;

[0021] ⑤. Real-time optimization scheduling: Dynamically adjust the scheduling strategy based on real-time monitored data and user needs to maximize the efficiency and performance of the system.

[0022] Preferably, the data processed by the edge computing node is sent to the data sharing and collaboration module, which integrates and analyzes the data to obtain more comprehensive charging pile status and information, promotes data sharing and collaborative work between different charging piles, and maximizes resource utilization efficiency.

[0023] Preferably, the user interface module is used to display the intelligent scheduling results, and to display the real-time status and availability information of the charging piles in an intuitive manner, so as to facilitate user query and use. In addition, users can make charging reservations, set preferences, and view charging history operations to enhance user experience and participation;

[0024] The energy management module is used to monitor, count and analyze the energy consumption of charging piles, provide support for the energy management of the system, and help optimize energy management and save energy;

[0025] The fault diagnosis module is responsible for monitoring and diagnosing faults in the charging pile equipment, timely discovering and handling equipment faults, ensuring the stable operation of the charging pile system, automatically triggering the early warning mechanism to alarm and remind personnel when a fault occurs, and transmitting the fault information to the user interface module for display, so that the user can intuitively know the fault situation.

[0026] The present invention also proposes a charging pile intelligent scheduling method based on edge computing, comprising the following steps:

[0027] S1: The data acquisition module obtains real-time data from each charging pile device, including the location of the charging pile, charging status, and battery charging status, and transmits the collected data to the edge computing node through a low-latency, high-bandwidth edge network;

[0028] S2: The edge computing node processes and analyzes the collected data in real time, and uses the support vector machine intelligent algorithm in combination with the edge algorithm module to make local scheduling decisions;

[0029] S3: The edge computing node sends the local scheduling decision in S2 to the charging pile and user equipment, and each charging pile responds to the adjustment command of the edge computing node in real time;

[0030] S4: Send the data processed by the edge computing node in S2 to the data sharing and collaboration module, which integrates and analyzes the data to obtain more comprehensive charging pile status and information, promotes data sharing and collaboration between different charging piles, and transmits the acquired information to the edge computing node for further analysis to maximize resource utilization efficiency;

[0031] S5: Send the local scheduling decision made in S2 and the response results of each charging pile in S3 to the user interface module for display, and display the real-time status and availability information of the charging pile in an intuitive way to facilitate user query and use;

[0032] S6: The fault diagnosis module monitors and diagnoses the fault conditions of the charging pile equipment in real time, promptly discovers and handles equipment faults, ensures the stable operation of the charging pile system, automatically triggers the early warning mechanism to alarm and remind personnel when a fault occurs, and transmits the fault information to the user interface module for display, so that the user can intuitively know the fault condition.

[0033] Preferably, in S6, the mathematical expression used when triggering the early warning mechanism is: D = || XX ref ||2, where X is real-time data, X ref is the normal state parameter, ||.||2 represents the Euclidean distance, and when D>threshold, the alarm mechanism is triggered.

[0034] Preferably, in S4, the specific steps of data integration and analysis by the data sharing and collaboration module are as follows:

[0035] S401: Collect real-time data from different charging pile devices and systems, integrate the data into a unified platform, and unify the data formats from different sources to make the data consistent. At the same time, clean and process the collected data to remove duplicate, erroneous or incomplete data to ensure data quality;

[0036] S402: Aggregate and summarize the integrated data, aggregate data for different dimensions and indicators, obtain a comprehensive picture of the global data, and discover the correlation patterns and potential connections between the data by analyzing the correlations and common features between different charging piles;

[0037] S403: Integrate data to the operational level, integrating real-time data and historical data of charging pile operations to form a more comprehensive analysis result.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The present invention can reduce data transmission delays and improve real-time performance by transferring data processing tasks to edge devices for processing, thereby improving scheduling timeliness and retrieval efficiency. In addition, through the combination of edge computing nodes and edge algorithm modules, it can realize intelligent scheduling and management according to various situations and factors, make local scheduling decisions, optimize the utilization efficiency of charging pile resources, and make users experience smoother when using charging piles, reduce user waiting time, and improve user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a block diagram of a charging pile intelligent scheduling system based on edge computing proposed by the present invention;

[0041] Figure 2 This is a flow chart of an intelligent scheduling method for charging piles based on edge computing proposed by the present invention. DETAILED DESCRIPTION

[0042] The present invention will be further explained below in conjunction with specific embodiments.

[0043] Example

[0044] Reference Figure 1-2 ,This embodiment proposes an intelligent scheduling system for charging piles based on edge computing, including a data acquisition module, an edge computing node, an edge algorithm module, a data sharing and collaboration module, a user interface module, an energy management module and a fault diagnosis module; wherein the data acquisition module is used to collect data from each charging pile in real time, including the status of the charging pile, user charging requirements and charging speed information, and the collected information is transmitted to the edge computing node, which uses a low-latency, high-bandwidth edge network for transmission when transmitting information;

[0045] Edge computing nodes are computing and data processing units located on edge devices, responsible for real-time processing and analysis of collected data, and executing intelligent algorithms in conjunction with edge algorithm modules to make local scheduling decisions;

[0046] The specific logical steps are as follows:

[0047] (1) The edge computing node cleans, formats, and removes noise from the collected data to ensure data quality;

[0048] (2) The edge computing node combines with the edge algorithm module to extract useful feature data from the data using the support vector machine intelligent algorithm, train the feature data, generate a support vector machine model, input the real-time collected data into the trained support vector machine model, and use the trained support vector machine model to classify the real-time collected data and find out the patterns and features in the data;

[0049] (3) Based on the analysis results of the support vector machine, predictions about the status of charging piles and user needs can be obtained, and local scheduling decisions can be made based on the prediction results;

[0050] The local scheduling decisions made are as follows:

[0051] ① Charging pile resource allocation: According to user needs and the real-time status of charging piles, decide which charging piles will be allocated to which users for charging to maximize resource utilization efficiency. The mathematical expression used is:

[0052] Among them C ij represents the cost of assigning vehicle i to charging station j (including distance and waiting time), X ij ∈{0,1}, represents the allocation variable. If vehicle i is assigned to charging station j, then X ij =1, otherwise 0;

[0053] ② Priority sorting of charging piles: Prioritize the charging piles according to user needs, load conditions of the charging piles, and performance indicators of the charging piles, and give priority to allocating charging pile resources to important users or users who are in urgent need of charging. The mathematical expression used is:

[0054]

[0055] Where λ is the arrival rate (the rate at which vehicle requests arrive), μ is the service rate (the rate at which charging piles process requests), and T - is the average waiting time. By optimizing λ and μ, the waiting time of vehicles in queue can be reduced;

[0056] ③. Optimize charging speed: By adjusting the charging power and charging time of each charging pile, the charging speed is optimized to make the charging process more efficient and reduce user waiting time;

[0057] ④. Consider the grid load: Combined with the local grid load situation, avoid excessive consumption of grid resources and maintain the smooth operation of the grid;

[0058] ⑤. Real-time optimization scheduling: Dynamically adjust the scheduling strategy based on real-time monitoring data and user needs to maximize the efficiency and performance of the system;

[0059] (4) The edge computing node allocates and schedules charging pile resources based on the local scheduling decisions made to optimize resource utilization efficiency;

[0060] The data acquisition module, energy management module and fault diagnosis module are all connected to the charging pile, the edge algorithm module is deployed on the edge computing node, the edge algorithm module and the fault diagnosis module are both connected to the user interface module, the energy management module is connected to the user interface module and the edge computing node, and the data sharing and collaboration module is connected to the edge computing node;

[0061] The data processed by the edge computing node is sent to the data sharing and collaboration module, which integrates and analyzes the data to obtain more comprehensive charging pile status and information, prompting different charging piles to share data and work together to maximize resource utilization efficiency.

[0062] The user interface module is used to display the intelligent scheduling results, and to display the real-time status and availability information of charging piles in an intuitive way, which is convenient for users to query and use. In addition, users can make charging reservations, set preferences, and view charging history to enhance user experience and participation.

[0063] The energy management module is used to monitor, count and analyze the energy consumption of charging piles, provide support for the energy management of the system, and help optimize energy management and save energy;

[0064] The fault diagnosis module is responsible for monitoring and diagnosing faults in charging pile equipment, timely discovering and handling equipment faults, ensuring the stable operation of the charging pile system, automatically triggering the early warning mechanism to alarm and remind personnel when a fault occurs, and transmitting the fault information to the user interface module for display, so that users can intuitively know the fault situation.

[0065] This embodiment also proposes a charging pile intelligent scheduling method based on edge computing, including the following steps:

[0066] S1: The data acquisition module obtains real-time data from each charging pile device, including the location of the charging pile, charging status, and battery charging status, and transmits the collected data to the edge computing node through a low-latency, high-bandwidth edge network;

[0067] S2: The edge computing node processes and analyzes the collected data in real time, and uses the support vector machine intelligent algorithm in combination with the edge algorithm module to make local scheduling decisions;

[0068] The local scheduling decisions it makes are as follows;

[0069] ① Charging pile resource allocation: According to user needs and the real-time status of charging piles, decide which charging piles will be allocated to which users for charging to maximize resource utilization efficiency. The mathematical expression used is:

[0070] Among them C ij represents the cost of assigning vehicle i to charging station j (including distance and waiting time), X ij ∈{0,1}, represents the allocation variable. If vehicle i is assigned to charging station j, then X ij =1, otherwise 0;

[0071] ② Priority sorting of charging piles: Prioritize the charging piles according to user needs, load conditions of the charging piles, and performance indicators of the charging piles, and give priority to allocating charging pile resources to important users or users who are in urgent need of charging. The mathematical expression used is:

[0072]

[0073] Where λ is the arrival rate (the rate at which vehicle requests arrive), μ is the service rate (the rate at which charging piles process requests), and T - is the average waiting time. By optimizing λ and μ, the waiting time of vehicles in queue can be reduced;

[0074] ③. Optimize charging speed: By adjusting the charging power and charging time of each charging pile, the charging speed is optimized to make the charging process more efficient and reduce user waiting time;

[0075] ④. Consider the grid load: Combined with the local grid load situation, avoid excessive consumption of grid resources and maintain the smooth operation of the grid;

[0076] ⑤. Real-time optimization scheduling: Dynamically adjust the scheduling strategy based on real-time monitoring data and user needs to maximize the efficiency and performance of the system;

[0077] S3: The edge computing node sends the local scheduling decision in S2 to the charging pile and user equipment, and each charging pile responds to the adjustment command of the edge computing node in real time;

[0078] S4: Send the data processed by the edge computing node in S2 to the data sharing and collaboration module, which integrates and analyzes the data to obtain more comprehensive charging pile status and information, promotes data sharing and collaboration between different charging piles, and transmits the acquired information to the edge computing node for further analysis to maximize resource utilization efficiency;

[0079] The specific steps for data integration and analysis in the data sharing and collaboration module are as follows:

[0080] S401: Collect real-time data from different charging pile devices and systems, integrate the data into a unified platform, and unify the data formats from different sources to make the data consistent. At the same time, clean and process the collected data to remove duplicate, erroneous or incomplete data to ensure data quality;

[0081] S402: Aggregate and summarize the integrated data, aggregate data for different dimensions and indicators, obtain a comprehensive picture of the global data, and discover the correlation patterns and potential connections between the data by analyzing the correlations and common features between different charging piles;

[0082] S403: Integrate data to the operational level, integrating real-time data and historical data of charging pile operations to form a more comprehensive analysis result;

[0083] S5: Send the local scheduling decision made in S2 and the response results of each charging pile in S3 to the user interface module for display, and display the real-time status and availability information of the charging pile in an intuitive way to facilitate user query and use;

[0084] S6: The fault diagnosis module monitors and diagnoses the fault conditions of the charging pile equipment in real time, discovers and handles equipment faults in a timely manner, ensures the stable operation of the charging pile system, automatically triggers the early warning mechanism to alarm and remind personnel when a fault occurs, and transmits the fault information to the user interface module for display. The user can intuitively know the fault condition. The mathematical expression used when triggering the early warning mechanism is: D = || XX ref ||2, where X is real-time data, X ref is the normal state parameter, ||.||2 represents the Euclidean distance, and if D>threshold, the alarm mechanism is triggered;

[0085] This embodiment can reduce data transmission delays and improve real-time performance by transferring data processing tasks to edge devices for processing, thereby improving scheduling timeliness and retrieval efficiency. In addition, through the combination of edge computing nodes and edge algorithm modules, it can realize intelligent scheduling and management according to various situations and factors, make local scheduling decisions, optimize the utilization efficiency of charging pile resources, and make users experience smoother when using charging piles, reduce user waiting time, and improve user satisfaction.

[0086] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A charging pile intelligent scheduling system based on edge computing, characterized in that: It includes data acquisition module, edge computing node, edge algorithm module, data sharing and collaboration module, user interface module, energy management module and fault diagnosis module; The data acquisition module, energy management module and fault diagnosis module are all connected to the charging pile, the edge algorithm module is deployed on the edge computing node, the edge algorithm module and the fault diagnosis module are both connected to the user interface module, the energy management module is connected to the user interface module and the edge computing node, and the data sharing and collaboration module is connected to the edge computing node.

2. According to the edge computing-based charging pile intelligent scheduling system of claim 1, it is characterized in that: The data acquisition module is used to collect data from each charging pile in real time, including the status of the charging pile, user charging needs and charging speed information. The collected information is transmitted to the edge computing node, which uses a low-latency, high-bandwidth edge network to transmit the information.

3. According to the edge computing-based charging pile intelligent scheduling system of claim 1, it is characterized in that: The edge computing node is a computing and data processing unit located on the edge device, responsible for real-time processing and analysis of the collected data, and executing intelligent algorithms in conjunction with the edge algorithm module to make local scheduling decisions; The specific logical steps are as follows: (1) The edge computing node cleans, formats, and removes noise from the collected data to ensure data quality; (2) The edge computing node combines with the edge algorithm module to extract useful feature data from the data using the support vector machine intelligent algorithm, train the feature data, generate a support vector machine model, input the real-time collected data into the trained support vector machine model, and use the trained support vector machine model to classify the real-time collected data and find out the patterns and features in the data; (3) Based on the analysis results of the support vector machine, predictions about the status of charging piles and user needs can be obtained, and local scheduling decisions can be made based on the prediction results; (4) The edge computing node allocates and schedules charging pile resources based on the local scheduling decisions made to optimize resource utilization efficiency.

4. According to the edge computing-based charging pile intelligent scheduling system of claim 3, it is characterized in that: In (3), the local scheduling decision is as follows: ① Charging pile resource allocation: According to user needs and the real-time status of charging piles, decide which charging piles will be allocated to which users for charging to maximize resource utilization efficiency. The mathematical expression used is: Among them C ij represents the cost of assigning vehicle i to charging station j, X ij ∈{0,1}, represents the allocation variable. If vehicle i is assigned to charging station j, then X ij =1, otherwise 0; ② Priority sorting of charging piles: Prioritize the charging piles according to user needs, load conditions of the charging piles, and performance indicators of the charging piles, and give priority to allocating charging pile resources to important users or users who are in urgent need of charging. The mathematical expression used is: Where λ is the arrival rate, μ is the service rate, T - is the average waiting time. By optimizing λ and μ, the waiting time of vehicles in queue can be reduced. ③. Optimize charging speed: By adjusting the charging power and charging time of each charging pile, the charging speed is optimized to make the charging process more efficient and reduce user waiting time; ④. Consider the grid load: Combined with the local grid load situation, avoid excessive consumption of grid resources and maintain the smooth operation of the grid; ⑤. Real-time optimization scheduling: Dynamically adjust the scheduling strategy based on real-time monitored data and user needs to maximize the efficiency and performance of the system.

5. According to the edge computing-based charging pile intelligent scheduling system of claim 1, it is characterized in that: The data processed by the edge computing node is sent to the data sharing and collaboration module, which integrates and analyzes the data to obtain more comprehensive charging pile status and information, promotes data sharing and collaborative work between different charging piles, and maximizes resource utilization efficiency.

6. The charging pile intelligent scheduling system based on edge computing according to claim 1 is characterized in that: The user interface module is used to display the intelligent scheduling results, and to display the real-time status and availability information of the charging piles in an intuitive way, so as to facilitate user query and use. In addition, users can make charging reservations, set preferences, and view charging history to enhance user experience and participation; The energy management module is used to monitor, count and analyze the energy consumption of charging piles, provide support for the energy management of the system, and help optimize energy management and save energy; The fault diagnosis module is responsible for monitoring and diagnosing faults in the charging pile equipment, timely discovering and handling equipment faults, ensuring the stable operation of the charging pile system, automatically triggering the early warning mechanism to alarm and remind personnel when a fault occurs, and transmitting the fault information to the user interface module for display, so that the user can intuitively know the fault situation.

7. A charging pile intelligent scheduling method based on edge computing, characterized in that: The following steps are involved: S1: The data acquisition module obtains real-time data from each charging pile device, including the location of the charging pile, charging status, and battery charging status, and transmits the collected data to the edge computing node through a low-latency, high-bandwidth edge network; S2: The edge computing node processes and analyzes the collected data in real time, and uses the support vector machine intelligent algorithm in combination with the edge algorithm module to make local scheduling decisions; S3: The edge computing node sends the local scheduling decision in S2 to the charging pile and user equipment, and each charging pile responds to the adjustment command of the edge computing node in real time; S4: Send the data processed by the edge computing node in S2 to the data sharing and collaboration module, which integrates and analyzes the data to obtain more comprehensive charging pile status and information, promotes data sharing and collaboration between different charging piles, and transmits the acquired information to the edge computing node for further analysis to maximize resource utilization efficiency; S5: Send the local scheduling decision made in S2 and the response results of each charging pile in S3 to the user interface module for display, and display the real-time status and availability information of the charging pile in an intuitive way to facilitate user query and use; S6: The fault diagnosis module monitors and diagnoses the fault conditions of the charging pile equipment in real time, promptly discovers and handles equipment faults, ensures the stable operation of the charging pile system, automatically triggers the early warning mechanism to alarm and remind personnel when a fault occurs, and transmits the fault information to the user interface module for display, so that the user can intuitively know the fault condition.

8. The method for intelligent scheduling of charging piles based on edge computing according to claim 7 is characterized in that: In S6, the mathematical expression used when triggering the early warning mechanism is: D = || XX ref ||2, where X is real-time data, X ref is the normal state parameter, ||.||2 represents the Euclidean distance, and when D>threshold, the alarm mechanism is triggered.

9. The method for intelligent scheduling of charging piles based on edge computing according to claim 7 is characterized in that: In S4, the specific steps of data integration and analysis by the data sharing and collaboration module are as follows: S401: Collect real-time data from different charging pile devices and systems, integrate the data into a unified platform, and unify the data formats from different sources to make the data consistent. At the same time, clean and process the collected data to remove duplicate, erroneous or incomplete data to ensure data quality; S402: Aggregate and summarize the integrated data, aggregate data for different dimensions and indicators, obtain a comprehensive picture of the global data, and discover the correlation patterns and potential connections between the data by analyzing the correlations and common features between different charging piles; S403: Integrate data to the operational level, integrating real-time data and historical data of charging pile operations to form a more comprehensive analysis result.

Images