Vehicle pile data communication transmission method and system of alternating current charging pile

Abstract

The invention relates to the field of vehicle pile data transmission, in particular to a vehicle pile data communication transmission method and system for an alternating current charging pile, and the method comprises the steps: constructing a vehicle pile anomaly detection data set, training an anomaly detection model, detecting the anomaly degree of vehicle pile data in real time, and calculating the structural importance and performance importance of a transmission node. Obtaining the importance of the nodes according to the structure importance and the performance importance, obtaining a transmission path by using a path search algorithm, calculating the importance of the transmission path according to the importance of the nodes on the path, performing matching according to the importance of the path and the abnormality of the bicycle pile data, and performing transmission according to the maximum matching of the bicycle pile data and the path. The method has the effect of improving the overall transmission efficiency and the transmission success rate of the bicycle pile data.

Description

Technical Field

[0001] This application relates to the field of vehicle-charging pile data transmission, and in particular to a method and system for vehicle-charging pile data communication transmission for AC charging piles. Background Technology

[0002] With the rapid development of new energy vehicles, the intelligent and networked nature of charging infrastructure has become crucial. As the most widely used charging equipment, AC charging piles directly impact user experience and grid efficiency through the real-time performance, reliability, and security of their data communication transmission. During vehicle-charging pile operation, anomalies such as overload, short circuits, and communication interruptions may occur. However, traditional transmission methods typically employ fixed paths or simple polling strategies, resulting in high-priority abnormal data (such as emergency stop commands) failing to be uploaded in a timely manner, leading to safety hazards. Existing vehicle-charging pile networks usually rely on a single communication link, lacking dynamic assessment of real-time path quality (latency, packet loss rate) and node importance (load, security level). Therefore, how to dynamically select the transmission path for vehicle-charging pile data through intelligent data anomaly detection and dynamic path importance assessment is an urgent problem to be solved. Summary of the Invention

[0003] To address the issue of dynamically selecting transmission paths for vehicle-charging pile data, this application provides a method and system for vehicle-charging pile data communication transmission for AC charging piles.

[0004] Firstly, this application provides a method for vehicle-charging pile data communication transmission in AC charging piles, employing the following technical solution: A method for vehicle-charging pile data communication transmission in AC charging piles includes the following steps: Construct a dataset for detecting anomalies in vehicle-to-pile data, collect data on the transmission performance of communication transmission nodes, and build a communication transmission network; An anomaly detection model is trained based on the dataset. The structural importance of nodes is calculated based on the transmission network. The performance importance of nodes is calculated based on the transmission performance of the transmission nodes. The importance of a node is obtained by weighted summation of its structural importance and performance importance. Multiple data transmission paths are obtained using a path search algorithm, and the importance of the transmission path is calculated based on the importance of the nodes on the transmission path. Real-time vehicle-pile data is input into the anomaly detection model to obtain the anomaly degree of the vehicle-pile data. The anomaly degree of the vehicle-pile data is multiplied by the importance of the transmission path to obtain the edge weight when the two are matched. The transmission path of the vehicle-pile data is obtained by using a matching algorithm based on the edge weight.

[0005] The beneficial effects are as follows: By calculating the structural and performance importance of transmission nodes, the importance of each node is determined. A path search algorithm is used to obtain multiple transmission paths, and the importance of each path is calculated. This avoids the problem of all vehicle-to-pile data being transmitted through a single path, resulting in high transmission latency, and also prevents all data from being transmitted if a transmission node fails. Furthermore, during vehicle-to-pile data transmission, higher-priority data is transmitted through important paths, and data with greater anomaly is transmitted with higher priority. Therefore, an anomaly detection model is established to detect anomalies in real-time vehicle-to-pile data. The edge weights for matching are calculated based on the anomaly degree of the vehicle-to-pile data and the importance of the transmission path. A matching algorithm is used to obtain the maximum match between the vehicle-to-pile data and the transmission path. Data is then transmitted based on the optimal match, improving the success rate and rationality of data transmission.

[0006] Optionally, the vehicle-pile data anomaly detection dataset includes the vehicle-pile's temperature, humidity, voltage, current, power, and corresponding anomaly tags; the transmission performance includes latency, packet loss rate, and load rate.

[0007] Optionally, the structural importance is calculated as follows: the frequency of a node appearing in the shortest path between other nodes and the average path length from a node to other nodes are calculated. The negative of the average path length is exponentially normalized. The exponentially normalized average path length is multiplied by the frequency to obtain the structural importance. The frequency is the ratio of the number of times a node appears in the shortest path between other nodes to the number of shortest paths between other nodes. The average path length is the average of the connection orders between the node and other nodes.

[0008] The beneficial effects are as follows: structural importance reflects the efficiency of the transmission node; the more frequently a node appears in the shortest path of other nodes, the higher its transmission efficiency; and the shorter the average path length between a node and other nodes, the higher its transmission efficiency.

[0009] Optionally, the performance importance is calculated as follows: the difference between 1 and the mean latency rate is calculated to obtain the first difference, the difference between 1 and the mean packet loss rate is calculated to obtain the second difference, and the difference between 1 and the mean load rate is calculated to obtain the third difference. The geometric mean of the first difference, the second difference, and the third difference is taken as the performance importance.

[0010] The beneficial effects are: performance importance reflects the transmission performance of a node. The lower the node's latency, packet loss rate, and load rate, the better the node's performance and the greater its performance importance. Using the geometric mean can calculate a low performance importance when a node has poor performance.

[0011] Optionally, the performance importance is calculated as follows: the ratio of latency kurtosis to latency mean is calculated to obtain a first ratio, the ratio of packet loss kurtosis to packet loss mean is calculated to obtain a second ratio, and the ratio of load kurtosis to load mean is calculated to obtain a third ratio. The product of the first ratio, the second ratio, and the third ratio is normalized to obtain the performance importance.

[0012] The beneficial effect is that when calculating the importance of node performance, not only are the average values ​​of the node's historical latency, packet loss rate, and load rate considered, but also the data distribution of latency, packet loss rate, and load rate. The more concentrated the distribution, the more stable the node's performance.

[0013] Optionally, the anomaly detection model is a BP neural network model, with the inputs being the temperature, humidity, voltage, current, and power of the vehicle and the pile, and the output being the anomaly degree of the vehicle and pile data.

[0014] Optionally, the matching algorithm is KM matching.

[0015] Secondly, this application provides a vehicle-charging pile data communication transmission system for AC charging piles, which adopts the following technical solution: A vehicle-to-charging-pile data communication transmission system for an AC charging pile includes a processor and a memory. The memory stores computer program instructions, which, when executed by the processor, implement the vehicle-to-charging-pile data communication transmission method for an AC charging pile as described above.

[0016] The beneficial effect is that the above-mentioned method for transmitting vehicle-charging pile data communication is used to generate a computer program and stored in a memory, so that it can be loaded and executed by a processor. Thus, a system can be made based on the memory and processor, which is convenient to use.

[0017] This application has the following technical effects: 1. The importance of each transmission node is obtained by calculating the structural and performance importance of the transmission nodes. Then, multiple paths are obtained by using a path search algorithm. The average importance of all nodes on the path is used as the importance of the path. The importance of the path not only considers the transmission efficiency but also the transmission success rate, which has the effect of improving the transmission efficiency and transmission success rate.

[0018] 2. Train the vehicle-pile data anomaly detection model to detect the anomaly degree of vehicle-pile data in real time. Calculate the weight of matching vehicle-pile data and transmission path based on the anomaly degree of vehicle-pile data and the importance of the path, so as to maximize the overall matching degree of all vehicle-pile data and transmission path. Attached Figure Description

[0019] The above and other objects, features, and advantages of exemplary embodiments of this application will become readily understood by reading the following detailed description with reference to the accompanying drawings. Several embodiments of this application are illustrated in the drawings by way of example and not limitation, and the same or corresponding reference numerals denote the same or corresponding parts.

[0020] Figure 1 This is a flowchart illustrating steps S1-S4 of a vehicle-charging pile data communication transmission method for an AC charging pile according to this application.

[0021] Figure 2 This is a structural block diagram of a vehicle-charging pile data communication transmission system for an AC charging pile according to this application. Detailed Implementation

[0022] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] It should be understood that when the terms "first," "second," etc., are used in the claims, description, and drawings of this application, they are only used to distinguish different objects and not to describe a specific order. The terms "comprising" and "including" used in the description and claims of this application indicate the presence of the described features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or collections thereof.

[0024] This application discloses a vehicle-charging pile data communication transmission method for AC charging piles, referring to... Figure 1 This includes the following steps: S1: Construct a dataset for detecting anomalies in vehicle-to-pile data, collect data on the transmission performance of communication transmission nodes, and construct a communication transmission network.

[0025] In one embodiment, a temperature sensor is used to collect the temperature of the charging pile, a humidity sensor is used to collect the humidity of the charging pile (inside or around the pile), a voltage sensor is used to collect the voltage of the charging pile, a current sensor is used to collect the current of the charging pile, and a power sensor is used to collect the power of the charging pile. Those skilled in the art assign a label to each collected data point based on the actual situation. The label is abnormal / normal. The data collected multiple times and the labels of the data constitute a vehicle-charging pile data anomaly detection dataset.

[0026] Collect historical latency, packet loss rate, and load rate of each communication transmission node. Construct a communication transmission network based on the connection relationship of the communication transmission nodes. The communication transmission nodes in the transmission network can be gateways or base stations. Their role is to act as "transfer stations" or "hubs" for data from the source (vehicle-to-grid) to the target (cloud server). In reality, if there is a connection between transmission nodes, then there is a connecting edge between the two nodes in the network. Conversely, if there is no connection, then there is no connecting edge between the two nodes in the network.

[0027] Thus, the performance of the vehicle-pile data anomaly detection dataset, communication transmission network, and transmission nodes is obtained.

[0028] S2: Train an anomaly detection model based on the dataset, calculate the structural importance of nodes based on the transmission network, calculate the performance importance of nodes based on the transmission performance of the transmission nodes, and obtain the importance of nodes by weighted summation of the structural importance and performance importance of nodes.

[0029] In one embodiment, an anomaly detection model is trained based on a vehicle-pile data anomaly detection dataset. The model's inputs are the temperature, humidity, voltage, current, and power of the vehicle and pile. The model's outputs are the probability of the vehicle and pile being abnormal and the probability of being normal. The model's loss is the cross-entropy loss. The model parameters are updated using the gradient descent algorithm. The model stops training when it reaches a preset maximum number of training iterations or when the model's loss is less than a set loss threshold. The best model is selected based on the model's accuracy as an evaluation metric. For example, the optimal number of training iterations is 1000, and the model's loss threshold is 0.001.

[0030] In one embodiment, based on the importance of nodes in the transmission network, the higher the frequency of a node appearing in the shortest path to other nodes in the transmission network, the greater the structural importance of the node and the shorter the distance from the node to other nodes. Structural importance reflects transmission efficiency and network connectivity assurance capabilities. Specifically, the formula for calculating the frequency of a node appearing in the shortest path to other nodes is as follows:

[0031] in, This represents the frequency of the i-th node appearing in the shortest paths of other nodes. Indicates the number of nodes. It is used for normalization. This represents the number of shortest paths from the s-th node to the t-th node. This represents the number of times the i-th node is passed through in the shortest path from the s-th node to the t-th node. The more frequently a node appears in the shortest paths of other nodes, the more important that node is.

[0032] Calculating the average distance from a node to other nodes requires counting the number of other nodes connected to the node at different orders. A first-order connection means two nodes are directly connected, a second-order connection means two nodes are connected by another node, and so on, to obtain the connection relationships of nodes at other orders. Based on the order of the connection between the target node and other nodes, the average path length from the target node to other nodes is calculated using the following formula:

[0033] in, This represents the average path length from the i-th node to all other nodes. Indicates the number of nodes. This represents the number of nodes with a j-th order connection to the i-th node. A lower average path length indicates higher transmission efficiency and greater node importance.

[0034] The structural importance of a node is calculated based on its frequency of occurrence in the shortest paths to other nodes and the average path length from the node to other nodes. The specific calculation formula is as follows:

[0035] in, Indicate the structural importance of the i-th node. This represents the frequency of the i-th node appearing in the shortest paths of other nodes. This represents the average path length from the i-th node to all other nodes. The base of the exponential function is... .

[0036] The performance importance of each node is calculated based on its latency, packet loss rate, and load rate. The specific calculation formula is as follows:

[0037] in, This indicates the performance importance of the i-th node. This represents the average latency of the i-th node in history. This represents the average packet loss rate of the i-th node in history. This represents the average load rate of the i-th node in history. When any one of the node's latency, packet loss rate, and load rate is relatively large, the probability of multiplying the three together is relatively small, and the performance importance is also smaller. This avoids the situation where the arithmetic average of the three results in a small value, but one of them is relatively large, and the calculated result does not match the reality.

[0038] In another embodiment, the formula for calculating the performance importance of each node is as follows:

[0039] in, This indicates the performance importance of the i-th node. This represents the average latency of the i-th node in history. This represents the average packet loss rate of the i-th node in history. This represents the average load rate of the i-th node in history. The kurtosis represents the latency rate of the i-th historical node. The kurtosis represents the packet loss rate of the i-th historical node. This represents the kurtosis of the load rate of the i-th historical node. Compared to the formula above, this formula considers the distribution of historical node transmission characteristics. The larger the kurtosis, the more concentrated the distribution, the more stable the node's transmission, and the greater the importance of the node's performance.

[0040] The importance of a node is calculated based on its structural importance and its performance importance, using the following formula:

[0041] in, Indicates the importance of the i-th node. Indicate the structural importance of the i-th node. This indicates the performance importance of the i-th node. , These represent the importance of the two factors, respectively. Based on the actual needs of the vehicle-to-pile data, the structural importance of a node reflects its efficiency during transmission; the greater the structural importance, the higher the transmission efficiency through that node. The performance importance of a node reflects the probability of successful transmission; the greater the performance importance, the greater the probability of successful transmission. For example, when the success rate of transmission is high and the real-time performance requirement is low, [the following is a possible interpretation:] ... .

[0042] Thus, we have grasped the importance of each node.

[0043] S3: Use a path search algorithm to obtain multiple data transmission paths, and calculate the importance of the transmission path based on the importance of the nodes on the transmission path.

[0044] In one embodiment, when there is a large amount of vehicle-to-pile data, it needs to be transmitted through multiple transmission paths. Therefore, a path search algorithm is used to obtain multiple transmission paths. The number of transmission paths is generally selected based on the size of the vehicle-to-pile data; the more vehicle-to-pile data, the more transmission paths are needed. An exemplary path search algorithm is the Disjoint Path algorithm. This algorithm can find multiple paths in the transmission network that do not share any nodes or edges. The importance of the transmission path is calculated based on the importance of the nodes on the path. The calculation method is to sum the importance of all nodes on the path and then take the average value to obtain the importance of the transmission path. Using the average value of the importance of transmission nodes as the importance of the path can avoid the problem that longer paths with more nodes have higher importance, while shorter paths with fewer nodes have lower importance.

[0045] This demonstrates the importance of each transmission path.

[0046] S4: Input the real-time vehicle-pile data into the anomaly detection model to obtain the anomaly degree of the vehicle-pile data. Multiply the anomaly degree of the vehicle-pile data and the importance of the transmission path to obtain the edge weight when the two are matched. Use the matching algorithm based on the edge weight to obtain the transmission path of the vehicle-pile data.

[0047] In one embodiment, real-time vehicle-to-pile (VPC) data is collected and input into an anomaly detection model. The model outputs the anomaly score of the real-time VPC data and then matches it with the transmission path. The edge weight during matching is the product of the anomaly score of the VPC data and the importance of the transmission path. Matching is performed based on the edge weights, and the model obtains the maximum match between the VPC data and the transmission path. The VPC data is then transmitted based on the maximum match. This embodiment is suitable when there is a small amount of VPC data, and the computational load for directly matching the VPC data with the transmission path is not large.

[0048] In another embodiment, real-time vehicle-pile data is collected and input into an anomaly detection model. The model outputs the anomaly score of the real-time vehicle-pile data. The anomaly scores of each real-time vehicle-pile data point are then clustered to obtain individual clusters. The mean anomaly score of the vehicle-pile data in each cluster is used as the anomaly score of the data in that cluster. An exemplary clustering algorithm is k-means.

[0049] The KM matching algorithm is used to match vehicle-pile data with transmission paths. During matching, the edge weights between the vehicle-pile data and the transmission paths need to be calculated. Since vehicle-pile data within a cluster have similar anomalies and the same transmission priority, they are transmitted via the same path. Therefore, matching only requires matching the cluster and the transmission path. The edge weight is calculated by multiplying the anomaly of the cluster's vehicle-pile data by the importance of the transmission path. Matching is then completed based on the edge weights, and the vehicle-pile data is transmitted based on the matching results. This embodiment is suitable for situations with a large amount of vehicle-pile data where directly matching all vehicle-pile data with the transmission paths would be computationally intensive.

[0050] This application also discloses a vehicle-charging pile data communication transmission system for AC charging piles, referring to... Figure 2 It includes a processor and a memory, the memory storing computer program instructions, which, when executed by the processor, implement a vehicle-charging pile data communication transmission method according to this application.

[0051] The system also includes other components well known to those skilled in the art, such as communication buses and communication interfaces, the settings and functions of which are known in the art and will not be described in detail here.

[0052] In this application, the aforementioned memory can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store required information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device.

[0053] While this specification has shown and described numerous embodiments of the present application, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will arise for those skilled in the art without departing from the spirit and intent of the present application. It should be understood that various alternatives to the embodiments of the present application described herein may be employed in the practice of this application.

[0054] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A method for vehicle-charging pile data communication transmission in AC charging piles, characterized in that, Includes the following steps: Construct a dataset for detecting anomalies in vehicle-to-pile data, collect data on the transmission performance of communication transmission nodes, and build a communication transmission network; An anomaly detection model is trained based on the dataset. The structural importance of nodes is calculated based on the transmission network. The performance importance of nodes is calculated based on the transmission performance of the transmission nodes. The importance of a node is obtained by weighted summation of its structural importance and performance importance. Multiple data transmission paths are obtained using a path search algorithm, and the importance of the transmission path is calculated based on the importance of the nodes on the transmission path. Real-time vehicle-pile data is input into the anomaly detection model to obtain the anomaly degree of the vehicle-pile data. The anomaly degree of the vehicle-pile data is multiplied by the importance of the transmission path to obtain the edge weight when the two are matched. The transmission path of the vehicle-pile data is obtained by using a matching algorithm based on the edge weight.

2. The method for vehicle-charging pile data communication transmission of an AC charging pile according to claim 1, characterized in that, The vehicle-pile data anomaly detection dataset includes the vehicle-pile's temperature, humidity, voltage, current, power, and corresponding anomaly tags; the transmission performance includes latency, packet loss rate, and load rate.

3. The method for vehicle-charging pile data communication transmission of an AC charging pile according to claim 1, characterized in that, The structural importance is calculated as follows: the frequency of a node appearing in the shortest path between other nodes and the average path length from the node to other nodes are calculated. The negative of the average path length is exponentially normalized. The structural importance is obtained by multiplying the exponentially normalized average path length by the frequency. The frequency is the ratio of the number of times a node appears in the shortest path between other nodes to the number of shortest paths between other nodes. The average path length is the average of the connection order between the node and other nodes.

4. The method for vehicle-charging pile data communication transmission of an AC charging pile according to claim 1, characterized in that, The performance importance is calculated as follows: the difference between 1 and the mean latency rate is calculated to obtain the first difference, the difference between 1 and the mean packet loss rate is calculated to obtain the second difference, and the difference between 1 and the mean load rate is calculated to obtain the third difference. The geometric mean of the first difference, the second difference, and the third difference is taken as the performance importance.

5. The method for vehicle-charging pile data communication transmission of an AC charging pile according to claim 1, characterized in that, The performance importance is calculated as follows: the ratio of latency kurtosis to latency mean is calculated to obtain the first ratio, the ratio of packet loss kurtosis to packet loss mean is calculated to obtain the second ratio, and the ratio of load kurtosis to load mean is calculated to obtain the third ratio. The product of the first ratio, the second ratio, and the third ratio is normalized to obtain the performance importance.

6. The method for vehicle-charging pile data communication transmission of an AC charging pile according to claim 1, characterized in that, The anomaly detection model is a BP neural network model. The input of the model is the on / off status of the vehicle and the charging pile, temperature, humidity, voltage, current and power. The output of the model is the anomaly degree of the vehicle and charging pile data.

7. The method for vehicle-charging pile data communication transmission of an AC charging pile according to claim 1, characterized in that, The matching algorithm is KM matching.

8. A vehicle-charging pile data communication transmission system for AC charging piles, characterized in that, include: A processor and a memory, wherein the memory stores computer program instructions that, when executed by the processor, implement a vehicle-charging pile data communication transmission method according to any one of claims 1-7.

Images