Electric vehicle energy flow edge device and method

Abstract

The invention belongs to the technical field of electric vehicle energy flow intelligent edge sensing in a power distribution network area, and particularly relates to an electric vehicle energy flow edge device and method. The device is connected into a power grid through a charging pile, an electric vehicle is connected into the charging pile to be charged, and the electric vehicle energy flow edge device is connected with the charging pile and comprises a sensing unit, an edge calculation unit, a communication unit, a monitoring evaluation unit, an energy flow bidirectional intelligent control unit and an application unit. Data of electric vehicles in the charging station are collected, processed and analyzed, information is transmitted to the cloud platform, the efficiency and stability of energy flow are monitored, the electric energy quality of a line node where the charging station is located is monitored in real time, bidirectional flow of energy is controlled, the load of the charging station is adjusted in real time, and the power supply capacity of weak links of a power grid is enhanced; transmission quantity of invalid data is reduced, operation pressure of an operation center and power supply pressure of weak links of an urban power grid are relieved, and power supply quality of the power grid is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent edge perception of electric vehicle energy flow in a distribution network area, and in particular relates to an electric vehicle energy flow edge device and method, and more specifically to an electric vehicle energy flow edge device and method for enhancing power supply in weak links of a power grid. Background Art

[0002] Edge computing is a method that combines geographic distribution with cloud technology to bring computing and storage resources closer to where the data is generated, shortening the distance that data is transmitted. Edge data centers can help solve latency issues by being geographically closer to the data source you need, thereby greatly improving system response speed.

[0003] The weak links of the power grid refer to the parts of the power system that have insufficient power transmission and distribution capabilities due to aging equipment, backward technology, and load growth. These weak links often manifest themselves in low power supply reliability, large voltage fluctuations, frequent accidents, etc., and often occur in old residential areas, high-load industrial areas, newly developed areas, and remote areas, posing challenges to the stability and security of the power system.

[0004] Weak links in the power grid can have a significant impact on social and economic development. First, unstable power supply will lead to interruptions in industrial production, affecting the normal operation and economic benefits of enterprises. Secondly, residential electricity consumption will be affected, and power outages or voltage instability may occur, affecting the quality of life. In addition, weak power grids may also lead to waste of power resources and environmental pollution, increase the operating costs of the power system, and restrict the access and use of renewable energy, thereby affecting the optimization of the overall energy structure.

[0005] The following solutions are usually adopted to address the vulnerable power supply capacity and poor power quality of the weak links in the power grid: planning the location and number of charging stations, introducing fast charging and ultra-fast charging technologies, and improving charging efficiency. However, traditional solutions often consume a lot of manpower and material resources, and the system has poor shock resistance and low flexibility, making it difficult to adapt to the rapid development of the power system. Summary of the invention

[0006] In view of the shortcomings of the above-mentioned prior art, the present invention provides an electric vehicle energy flow edge device and method. The purpose is to reduce the amount of invalid data transmission, relieve the computing pressure of the computing center, and improve the response speed of the system; reduce manpower consumption, improve the robustness and power supply quality of the weak links of the distribution network, and promote the safe and efficient operation of the distribution network.

[0007] The technical solution adopted by the present invention to achieve the above-mentioned purpose is:

[0008] An electric vehicle energy flow edge device comprises: a power grid, a charging pile and an electric vehicle, wherein the charging pile is incorporated into the power grid, the electric vehicle is connected to the charging pile for charging, the electric vehicle energy flow edge device is connected to the charging pile, and the electric vehicle energy flow edge device comprises: a sensing unit, an edge computing unit, a communication unit, a monitoring and evaluation unit, an energy flow bidirectional intelligent control unit and an application unit; wherein the sensing unit is connected to the edge computing unit, the edge computing unit is connected to the communication unit, the communication unit is connected to a cloud platform, the cloud platform is connected to the monitoring and evaluation unit, the cloud platform is connected to the application unit, the application unit is connected to a user, and the application unit is connected to the energy flow bidirectional intelligent control unit.

[0009] Furthermore, the perception unit includes: a sensor module and an environmental perception module. The sensor module and the environmental perception module are in a parallel relationship. The sensor module is used to monitor the energy status of the electric vehicle, and the environmental perception module is used to monitor the surrounding environmental conditions that may affect energy efficiency. The perception unit transmits the collected data of the electric vehicle to the edge computing unit in real time to provide status information and basic data support for the system.

[0010] Furthermore, the edge computing unit includes: a data processing module and a real-time decision module, the data processing module and the real-time decision module are in a parallel relationship, wherein the data processing module is responsible for real-time processing and analysis of the data obtained from the sensing unit, and the real-time decision module makes real-time decisions to adjust and optimize the energy flow based on the processed data;

[0011] The edge computing unit receives the raw data from the sensing unit, performs real-time data processing and preliminary analysis, reduces data transmission delay and network load, performs local optimization and control tasks, and uploads processing results and key data to the cloud platform;

[0012] The computing method of the edge computing unit includes:

[0013] Step 1. Adaptive data cleaning and normalization;

[0014] Step 2. Joint dimensionality reduction and feature extraction;

[0015] Combine principal component analysis (PCA) with time series feature extraction to extract the main components and statistical eigenvalues ​​of time series data;

[0016] The PCA dimensionality reduction formula is as follows:

[0017] Z=XW

[0018] Where X is the input data matrix; W is the feature vector matrix; Z is the data matrix after dimensionality reduction;

[0019] Combining autoencoders with PCA for nonlinear dimensionality reduction:

[0020]

[0021] Where X is the input data matrix; W is the feature vector matrix; λ is the regularization parameter that controls feature sparsity; f θ (X) is the combined function of the encoder and decoder, W PCA is the eigenvector matrix obtained by the PCA method;

[0022] Step 3. Lightweight deep learning model compression;

[0023] Combining model compression with edge intelligence, using knowledge distillation technology, the complex deep learning model is compressed into a lightweight model; the knowledge distillation loss is as follows:

[0024]

[0025] Among them, L distill is the total distillation loss, α is the weight parameter, L CE is the cross entropy loss, y student is the output probability distribution of the model, y true is the distribution of the true label, T is the temperature coefficient; L KL is the Kullback-Leibler divergence; softmax() is a function;

[0026] Combining the two losses, a model with good performance is trained by adjusting the weight parameter α and the temperature coefficient T, and efficient data preprocessing and analysis are achieved in the edge computing layer;

[0027] Step 4. Adaptive clustering and anomaly detection;

[0028] Combine K-means clustering and anomaly detection to cluster data and identify and process abnormal data points.

[0029] Furthermore, the communication unit includes: a communication interface module and a security protection module; wherein the communication interface module is responsible for data exchange and communication with the vehicle internal system and the external network, and the security protection module ensures the security and reliability of communication;

[0030] The communication unit realizes uplink communication, local communication and downlink communication, provides data transmission channels between units, and adopts multiple communication protocols; among them, uplink communication uses 4G / 5G as a wide area network, facing the cloud platform database, local communication uses RS485 as a communication means, and downlink communication uses CAN bus and Wi-Fi as a communication means, realizing interconnection and interoperability between edge devices, cloud platforms and application units, real-time communication, adjusting electric vehicle charging behavior or responding to instructions from power grid managers.

[0031] Furthermore, the monitoring and evaluation unit includes: a performance monitoring module, a fault diagnosis module and a power quality detection module; wherein the performance monitoring module is used to monitor the efficiency and stability of the energy flow, the fault diagnosis module is used to identify and respond to possible faults or abnormal conditions; the power quality detection module is used to detect the power quality of the line node where the charging station is located;

[0032] The monitoring and evaluation unit obtains real-time data from the cloud platform, applies an outlier detection algorithm to identify and diagnose equipment failures and abnormal charging behaviors in real time, and promptly issues warnings and handles them.

[0033] Furthermore, the energy flow bidirectional intelligent control unit includes: a charging management module, a discharging management module and an energy flow intelligent controller; wherein the charging management module is used to manage the charging process of the electric vehicle, adjust the charging rate and charging strategy; the discharging management module is used to manage the discharging process of the electric vehicle, optimize energy use and feedback; the energy flow intelligent controller is responsible for controlling the bidirectional flow of energy;

[0034] The application unit includes: an application interface module and an energy management application module; wherein the application interface module is integrated and interacts with the vehicle user interface and other application programs; and the energy management application module provides user energy management functions.

[0035] An electric vehicle energy flow edge method is implemented using any one of the electric vehicle energy flow edge devices described above, comprising:

[0036] Install sensors at weak links in the power grid and at electric vehicle charging stations to collect real-time data on electric vehicles, battery energy SOC, charging and discharging status, and location;

[0037] Deploy edge computing nodes at weak links in the power grid and charging stations to clean, normalize and extract features from collected real-time data;

[0038] Based on the collected real-time data, the charging and discharging power of electric vehicles is predicted, and the charging and discharging strategy is dynamically adjusted according to the prediction results, so as to dispatch electric vehicles to charge and discharge near the weak links of the power grid;

[0039] Real-time monitoring and electric vehicle charging and discharging data will be fed back to the power grid dispatching center and electric vehicle users to enhance the power supply capacity of weak links in the power grid.

[0040] Furthermore, the electric vehicle energy flow edge device comprises:

[0041] The acquisition module is used to install sensors at weak links in the power grid and electric vehicle charging stations to collect real-time data of electric vehicles, battery energy SOC, charging and discharging status, and location;

[0042] The computing module deploys edge computing nodes at weak links in the power grid and charging stations to clean, normalize, and extract features from the collected real-time data;

[0043] The adjustment module is used to dynamically adjust the charging and discharging strategy based on the collected real-time data and prediction results, and dispatch electric vehicles to charge and discharge near the weak links of the power grid;

[0044] Feedback module, used to feed back real-time monitoring and control data to the power grid dispatch center and electric vehicle users, so as to enhance the power supply capacity of weak links in the power grid;

[0045] The electric vehicle energy flow edge device is used to implement the electric vehicle energy flow edge method.

[0046] A computer device comprises a storage medium, a processor and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the steps of an electric vehicle energy flow edge method when executing the computer program.

[0047] A computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of an electric vehicle energy flow edge method.

[0048] The present invention has the following beneficial effects and advantages:

[0049] The present invention first collects the SOC, current and voltage data of electric vehicles in the charging station through the sensing unit; then processes and analyzes the real-time acquired data through the edge computing unit, and makes real-time decisions to adjust and optimize the energy flow locally; then transmits the above information to the cloud platform through the communication unit; monitors the efficiency and stability of the energy flow through the monitoring and evaluation unit, and monitors the power quality of the line node where the charging station is located in real time; then controls the bidirectional flow of energy through the energy flow bidirectional intelligent control unit, adjusts the charging station load in real time, and realizes the enhancement of the power supply capacity of the weak links of the power grid. The present invention can greatly reduce the transmission amount of invalid data, relieve the computing pressure of the computing center; relieve the power supply pressure of the weak links of the urban power grid, and improve the power supply quality of the power grid.

[0050] The present invention uses edge computing to greatly reduce the transmission volume of invalid data, alleviating the computing pressure of the computing center while also improving the response speed of the system; on the other hand, the present invention has developed an electric vehicle energy flow edge device that enhances the power supply capacity of weak links in the power grid, which can greatly reduce manpower consumption. At the same time, it also improves the robustness and stability of the distribution network, improves the voltage quality of weak links, and is conducive to the safe and efficient operation of the distribution network.

[0051] The present invention adds a bidirectional intelligent energy flow control unit to manage the charging and discharging process of electric vehicles, obtain real-time data from the cloud platform and the monitoring and evaluation unit, dynamically adjust the charging and discharging strategy according to the real-time data and the evaluation results of the power supply quality status of the power grid, dispatch electric vehicles to charge and discharge at the weak links of the power grid, flexibly adjust the load of the charging station, and actively reduce the charging load when the power grid load is tight, so as to provide support for the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0053] Figure 1 It is the overall structural block diagram of the electric vehicle energy flow edge device of the present invention;

[0054] Figure 2 It is a system structure block diagram of the electric vehicle energy flow edge device of the present invention;

[0055] Figure 3 is a flow chart of data processing of the edge computing unit of the device of the present invention;

[0056] Figure 4 This is a structural block diagram of the energy flow bidirectional intelligent control unit of the device of the present invention;

[0057] Figure 5 It is a flow chart of the steps of the method of the present invention. DETAILED DESCRIPTION

[0058] In order to more clearly understand the above-mentioned objectives, features and advantages of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0059] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0060] Refer to the following Figure 1-Figure 5 The technical solutions of some embodiments of the present invention are described.

[0061] Example 1

[0062] The present invention provides an embodiment, which is an electric vehicle energy flow edge device. Figure 1 As shown, Figure 1The overall structural block diagram of the electric vehicle energy flow edge device of the present invention. In the overall structural block diagram of the electric vehicle energy flow edge device for enhancing the power supply of the weak links of the power grid, the external device includes: a power grid, a charging pile and an electric vehicle, which is an existing product, wherein the charging pile is incorporated into the power grid, the electric vehicle is connected to the charging pile for charging, and the electric vehicle energy flow edge device is connected to the charging pile.

[0063] like Figure 2 As shown, Figure 2 This is a system structure block diagram of the electric vehicle energy flow edge device of the present invention, which includes: a sensing unit, an edge computing unit, a communication unit, a monitoring and evaluation unit, a bidirectional intelligent control unit for energy flow, and an application unit, a total of six units. The sensing unit is connected to the edge computing unit, the edge computing unit is connected to the communication unit, the communication unit is connected to the cloud platform, the cloud platform is connected to the monitoring and evaluation unit, the cloud platform is connected to the application unit, the application unit is connected to the user, and the application unit is connected to the bidirectional intelligent control unit for energy flow.

[0064] (1) The sensing unit includes: a sensor module and an environment sensing module. The sensor module and the environment sensing module are in parallel, wherein the sensor module is used to monitor the energy status of the electric vehicle, such as SOC, current, voltage, etc.; the environment sensing module is used to monitor the surrounding environmental conditions that may affect energy efficiency, such as temperature, humidity, air pressure, etc.

[0065] The perception unit transmits the collected data such as the electric vehicle's battery energy SOC, charging status, vehicle location and ambient temperature to the edge computing unit in real time through sensors installed on electric vehicles and charging piles, providing the system with detailed status information and basic data support.

[0066] The sensing unit collects current, voltage, temperature, humidity analog signals and electric vehicle motion status signals through sensors, and converts the analog signals into corresponding digital signals through analog-to-digital conversion. The power and status data extracted in real time are recorded using recording equipment.

[0067] (2) The edge computing unit includes: a data processing module and a real-time decision module. The data processing module and the real-time decision module are in a parallel relationship, wherein the data processing module is responsible for real-time processing and analysis of the data obtained from the sensing unit; the real-time decision module makes real-time decisions to adjust and optimize the energy flow based on the processed data.

[0068] The edge computing unit receives raw data from the sensing unit, performs preprocessing, filtering, and aggregation operations to reduce the need to transmit data to the cloud, and predicts the impact of electric vehicle charging and discharging behavior on local grid load based on preset algorithms and models. The unit formulates local charging plans or response measures to minimize the negative impact on the grid and maximize energy efficiency.

[0069] like Figure 3 As shown, Figure 3 It is a flow chart of data processing of the edge computing unit of the device of the present invention. The algorithm flow adopted by the edge computing specifically includes the following steps:

[0070] Step 1. Adaptive data cleaning and normalization;

[0071] Combining data cleaning and normalization methods, an adaptive algorithm is created to dynamically select appropriate missing value filling and normalization methods based on the characteristics of the data;

[0072] Step 2. Joint dimensionality reduction and feature extraction;

[0073] Combine principal component analysis (PCA) with time series feature extraction to extract the main components and statistical eigenvalues ​​of time series data;

[0074] The PCA dimensionality reduction formula is as follows:

[0075] Z=XW

[0076] Among them, X is the input data matrix; W is the feature vector matrix; Z is the data matrix after dimensionality reduction.

[0077] Combining autoencoders with PCA for nonlinear dimensionality reduction:

[0078]

[0079] Where X is the input data matrix; W is the feature vector matrix; λ is the regularization parameter that controls feature sparsity; f θ (X) is the combined function of the encoder and decoder, W PCA It is the eigenvector matrix obtained by the PCA method, that is, the principal component matrix.

[0080] Step 3. Lightweight deep learning model compression;

[0081] Combining model compression with edge intelligence, using knowledge distillation technology to compress complex deep learning models into lightweight models to fit edge computing devices;

[0082] The knowledge distillation loss is as follows:

[0083] Step 3 uses knowledge distillation technology to compress the complex deep learning model into a lightweight model. The following formula is a formula for solving the "knowledge distillation loss" alone. Solving the knowledge distillation loss is a link in the knowledge distillation technology, as shown below:

[0084]

[0085] Among them, L distill is the total distillation loss, which is the objective function of model training; α is a weight parameter used to balance between the true label loss and the soft label loss, with a value range of [0,1]; L CE is the cross entropy loss, where the true label loss is the CE loss and the soft label loss is the KL divergence loss; student is the output probability distribution of the model; y true is the distribution of the true label; T is the temperature coefficient, which is used to adjust the smoothness of the model output; L KL The Kullback-Leibler Divergence is used to measure the difference between the output probability distribution of the student model and the teacher model; the softmax() function is used to calculate the probability distribution.

[0086] By combining the two parts of the loss and adjusting the weight parameter α and the temperature coefficient T, a model with better performance can be effectively trained, which can achieve more efficient data preprocessing and analysis in the edge computing layer and improve the overall performance and reliability of the system.

[0087] Step 4. Adaptive clustering and anomaly detection;

[0088] Combine K-means clustering and anomaly detection to cluster the data and then identify and process abnormal data points.

[0089] (3) The communication unit includes: a communication interface module and a security protection module. The communication interface module is responsible for data exchange and communication with the vehicle's internal system and external network; the security protection module ensures the security and reliability of communication;

[0090] The communication unit realizes uplink communication, local communication and downlink communication, provides data transmission channels between units, ensures reliable data transmission and security, and adopts multiple communication protocols. Specifically, uplink communication uses 4G / 5G as a wide area network, facing the cloud platform database; local communication uses RS485 as a communication means; downlink communication uses CAN bus and Wi-Fi as a communication means, thereby realizing the interconnection between edge devices, cloud platforms and application units.

[0091] The communication unit is responsible for data transmission and communication between edge devices and between edge devices and central systems such as cloud platforms. The data processed by the edge computing unit is transmitted to the central system or other related devices to support deeper analysis and decision-making. Coordinate with other edge devices or smart grid components to coordinate the charging behavior of electric vehicles to avoid overloading the grid during peak hours. In the event of changes in the grid state or emergency, communicate with the central system in real time to adjust the charging behavior of electric vehicles or respond to the instructions of the grid manager.

[0092] (4) The monitoring and evaluation unit includes: a performance monitoring module, a fault diagnosis module and a power quality detection module. The performance monitoring module is responsible for monitoring the efficiency and stability of the energy flow; the fault diagnosis module is responsible for identifying and responding to possible faults or abnormal conditions; and the power quality detection module detects the power quality of the line node where the charging station is located.

[0093] The monitoring and evaluation unit obtains real-time data from the cloud platform, including: electric vehicle charging and discharging status, SOC, SOH and battery temperature. The outlier detection algorithm (isolation forest algorithm, deep autoencoder) is used to identify and diagnose equipment failures, abnormal charging behaviors, etc. in real time, and timely warn and handle them. The information flow and power flow fusion technology in the edge intelligent device is used to intelligently perceive the power supply quality status of the distribution network nodes of the electric vehicle charging station in real time, aiming to improve the power supply quality of the weak links of the power grid.

[0094] (5) The energy flow bidirectional intelligent control unit, such as Figure 4 As shown, Figure 4 The present invention is a structural block diagram of the energy flow bidirectional intelligent control unit of the device.

[0095] The energy flow bidirectional intelligent control unit includes: a charging management module, a discharging management module and an energy flow intelligent controller. The charging management module manages the charging process of the electric vehicle, adjusts the charging rate and charging strategy; the discharging management module manages the discharging process of the electric vehicle, optimizes energy use and feedback; the energy flow intelligent controller is responsible for controlling the bidirectional flow of energy;

[0096] The energy flow bidirectional intelligent control unit is connected to the application unit, receives user instructions and strategy suggestions from the application unit, and adjusts the charging power and time period based on them. Dynamically schedule charging and discharging operations, respond to changes in grid load, fluctuations in electricity prices, and user demand preferences, coordinate energy flow and information exchange between layers, and ensure the safety, reliability, and economy of the charging and discharging process.

[0097] The energy flow bidirectional intelligent control unit manages the charging and discharging process of the electric vehicle, obtains real-time data from the cloud platform and the monitoring and evaluation unit, dynamically adjusts the charging and discharging strategy according to the real-time data and the evaluation results of the power supply quality status of the power grid, dispatches the electric vehicle to charge and discharge at the weak links of the power grid, flexibly adjusts the load of the charging station, and actively reduces the charging load when the power grid load is tight, so as to provide support for the power grid.

[0098] (6) The application unit includes: an application interface module and an energy management application module. The application interface module integrates and interacts with the vehicle user interface and other applications; the energy management application module provides user energy management functions, such as energy consumption prediction, energy optimization suggestions, etc.

[0099] The corresponding APP can be downloaded on the car owner's mobile phone, and a local calculation plan can be formulated according to the car owner's needs. The APP can be used to reserve an idle charging pile in advance within 5 minutes and obtain the detailed location of the charging pile, fill in the current SOC value and the expected SOC value, and formulate an efficient charging plan; in addition, the APP will formulate corresponding discharge rewards for the car owner, realizing two-way V2G technology on the premise of fully respecting the car owner's wishes.

[0100] Example 2

[0101] The present invention provides an embodiment, which is an electric vehicle energy flow edge method, specifically an electric vehicle energy flow edge method for enhancing power supply in weak links of a power grid by using an electric vehicle energy flow edge device as described in Example 1, such as Figure 5 As shown, the specific steps are as follows:

[0102] Step 1. Install sensors at weak links in the power grid and electric vehicle charging stations to collect real-time current, voltage, frequency and load data, and obtain the battery energy SOC, charging and discharging status and location of electric vehicles.

[0103] Step 2. Deploy edge computing nodes at weak links in the power grid and charging stations with data processing and computing capabilities to clean, normalize and extract features of the real-time data collected in step 1 to ensure the accuracy and applicability of the data.

[0104] Step 3. Based on the real-time data collected in step 1, predict the charging and discharging power of electric vehicles, dynamically adjust the charging and discharging strategy according to the prediction results, and dispatch electric vehicles to charge and discharge near the weak links of the power grid to provide support for the stability of the power grid.

[0105] Step 4. Feedback real-time monitoring and electric vehicle charging and discharging data to the grid dispatch center and electric vehicle users, providing transparent information and optimization suggestions to enhance the power supply capacity of weak links in the grid.

[0106] The electric vehicle charging and discharging data includes the electric vehicle charging and discharging power, the charging status of the charging station and the location data of the electric vehicle.

[0107] Example 3

[0108] The present invention further provides an embodiment, which is an electric vehicle energy flow edge device, based on the electric vehicle energy flow edge method described in Embodiment 2.

[0109] An electric vehicle energy flow edge device, comprising:

[0110] The acquisition module is used to install sensors in weak links of the power grid and electric vehicle charging stations to collect real-time current, voltage, frequency and load data, and obtain the battery energy SOC, charging and discharging status and location of electric vehicles.

[0111] The computing module is used to deploy edge computing nodes at weak links in the power grid and charging stations, and has data processing and computing capabilities. It performs data cleaning, normalization and feature extraction on the real-time data collected in step 1 in Example 2 to ensure the accuracy and applicability of the data.

[0112] The adjustment module is used to dynamically adjust the charging and discharging strategy according to the real-time data collected in step 1 in Example 2 and the electric vehicle charging and discharging power prediction result in step 3, and dispatch electric vehicles to charge and discharge near the weak links of the power grid to provide support for the stability of the power grid.

[0113] The feedback module is used to feed back the real-time monitoring and the electric vehicle charging and discharging data in step 3 to the power grid dispatch center and electric vehicle users, providing transparent information and optimization suggestions to enhance the power supply capacity of weak links in the power grid. The electric vehicle charging and discharging data includes the electric vehicle charging and discharging power, the charging status of the charging station and the location data of the electric vehicle.

[0114] The electric vehicle energy flow edge device described in this embodiment is used to implement the electric vehicle energy flow edge method described in Example 2.

[0115] Example 4

[0116] Based on the same inventive concept, an embodiment of the present invention further provides a computer device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor. When the processor executes the computer program, the steps of an electric vehicle energy flow edge method described in embodiment 2 are implemented.

[0117] Example 5

[0118] Based on the same inventive concept, an embodiment of the present invention further provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of an electric vehicle energy flow edge method described in Example 2 are implemented.

[0119] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0120] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0121] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0122] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0123] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. An electric vehicle energy flow edge device, comprising: A power grid, a charging pile and an electric vehicle, wherein the charging pile is incorporated into the power grid, and the electric vehicle is connected to the charging pile for charging, wherein the electric vehicle energy flow edge device is connected to the charging pile, and the electric vehicle energy flow edge device comprises: a sensing unit, an edge computing unit, a communication unit, a monitoring and evaluation unit, an energy flow bidirectional intelligent control unit and an application unit; wherein the sensing unit is connected to the edge computing unit, the edge computing unit is connected to the communication unit, the communication unit is connected to the cloud platform, the cloud platform is connected to the monitoring and evaluation unit, the cloud platform is connected to the application unit, the application unit is connected to the user, and the application unit is connected to the energy flow bidirectional intelligent control unit.

2. The electric vehicle energy flow edge device according to claim 1, characterized in that: The perception unit includes: a sensor module and an environmental perception module. The sensor module and the environmental perception module are in a parallel relationship. The sensor module is used to monitor the energy status of the electric vehicle, and the environmental perception module is used to monitor the surrounding environmental conditions that may affect energy efficiency. The perception unit transmits the collected data of the electric vehicle to the edge computing unit in real time to provide status information and basic data support for the system.

3. The electric vehicle energy flow edge device according to claim 1, characterized in that: The edge computing unit includes: a data processing module and a real-time decision module, the data processing module and the real-time decision module are in a parallel relationship, wherein the data processing module is responsible for real-time processing and analysis of the data obtained from the sensing unit, and the real-time decision module makes real-time decisions to adjust and optimize the energy flow based on the processed data; The edge computing unit receives the raw data from the sensing unit, performs real-time data processing and preliminary analysis, reduces data transmission delay and network load, performs local optimization and control tasks, and uploads processing results and key data to the cloud platform; The computing method of the edge computing unit includes: Step 1. Adaptive data cleaning and normalization; Step 2. Joint dimensionality reduction and feature extraction; Combine principal component analysis (PCA) with time series feature extraction to extract the main components and statistical eigenvalues ​​of time series data; The PCA dimensionality reduction formula is as follows: Z=XW Where X is the input data matrix; W is the feature vector matrix; Z is the data matrix after dimensionality reduction; Combining autoencoders with PCA for nonlinear dimensionality reduction: Where X is the input data matrix; W is the feature vector matrix; λ is the regularization parameter that controls feature sparsity; f θ (X) is the combined function of the encoder and decoder, W PCA is the eigenvector matrix obtained by the PCA method; Step 3. Lightweight deep learning model compression; Combining model compression with edge intelligence, using knowledge distillation technology, the complex deep learning model is compressed into a lightweight model; the knowledge distillation loss is as follows: Among them, L distill is the total distillation loss, α is the weight parameter, L CE is the cross entropy loss, y student is the output probability distribution of the model, y true is the distribution of the true label, T is the temperature coefficient; L KL is the Kullback-Leibler divergence; softmax() is a function; Combining the two losses, a model with good performance is trained by adjusting the weight parameter α and the temperature coefficient T, and efficient data preprocessing and analysis are achieved in the edge computing layer; Step 4. Adaptive clustering and anomaly detection; Combine K-means clustering and anomaly detection to cluster data and identify and process abnormal data points.

4. The electric vehicle energy flow edge device according to claim 1, characterized in that: The communication unit includes: a communication interface module and a security protection module; wherein the communication interface module is responsible for data exchange and communication with the vehicle internal system and the external network, and the security protection module ensures the security and reliability of communication; The communication unit realizes uplink communication, local communication and downlink communication, provides data transmission channels between units, and adopts multiple communication protocols; among them, uplink communication uses 4G / 5G as a wide area network, facing the cloud platform database, local communication uses RS485 as a communication means, and downlink communication uses CAN bus and Wi-Fi as a communication means, realizing interconnection and interoperability between edge devices, cloud platforms and application units, real-time communication, adjusting electric vehicle charging behavior or responding to instructions from power grid managers.

5. The electric vehicle energy flow edge device according to claim 1, characterized in that: The monitoring and evaluation unit includes: a performance monitoring module, a fault diagnosis module and a power quality detection module; wherein the performance monitoring module is used to monitor the efficiency and stability of the energy flow, the fault diagnosis module is used to identify and respond to possible faults or abnormal conditions; the power quality detection module is used to detect the power quality of the line node where the charging station is located; The monitoring and evaluation unit obtains real-time data from the cloud platform, applies an outlier detection algorithm to identify and diagnose equipment failures and abnormal charging behaviors in real time, and promptly issues warnings and handles them.

6. The electric vehicle energy flow edge device according to claim 1, characterized in that: The energy flow bidirectional intelligent control unit includes: a charging management module, a discharging management module and an energy flow intelligent controller; wherein the charging management module is used to manage the charging process of the electric vehicle, adjust the charging rate and charging strategy; the discharging management module is used to manage the discharging process of the electric vehicle, optimize energy use and feedback; the energy flow intelligent controller is responsible for controlling the bidirectional flow of energy; The application unit includes: an application interface module and an energy management application module; wherein the application interface module is integrated and interacts with the vehicle user interface and other application programs; and the energy management application module provides user energy management functions.

7. An electric vehicle energy flow edge method, implemented by using an electric vehicle energy flow edge device according to any one of claims 1 to 6, characterized in that: include: Install sensors at weak links in the power grid and at electric vehicle charging stations to collect real-time data on electric vehicles, battery energy SOC, charging and discharging status, and location; Deploy edge computing nodes at weak links in the power grid and charging stations to clean, normalize and extract features from collected real-time data; Based on the collected real-time data, the charging and discharging power of electric vehicles is predicted, and the charging and discharging strategy is dynamically adjusted according to the prediction results, so as to dispatch electric vehicles to charge and discharge near the weak links of the power grid; Real-time monitoring and electric vehicle charging and discharging data will be fed back to the power grid dispatching center and electric vehicle users to enhance the power supply capacity of weak links in the power grid.

8. The electric vehicle energy flow edge device according to claim 7, characterized in that: include: The acquisition module is used to install sensors at weak links in the power grid and electric vehicle charging stations to collect real-time data of electric vehicles, battery energy SOC, charging and discharging status, and location; The computing module deploys edge computing nodes at weak links in the power grid and charging stations to clean, normalize, and extract features from the collected real-time data; The adjustment module is used to dynamically adjust the charging and discharging strategy based on the collected real-time data and prediction results, and dispatch electric vehicles to charge and discharge near the weak links of the power grid; Feedback module, used to feed back real-time monitoring and control data to the power grid dispatch center and electric vehicle users, so as to enhance the power supply capacity of weak links in the power grid; The electric vehicle energy flow edge device is used to implement the electric vehicle energy flow edge method described in claim 7.

9. A computer device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the electric vehicle energy flow edge method described in claim 7 are implemented.

10. A computer storage medium, characterized in that: The computer storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the electric vehicle energy flow edge method described in claim 7 are implemented.

Images