Communication fault troubleshooting method of energy storage system

Abstract

The invention provides a communication fault troubleshooting method for an energy storage system, which comprises the following steps of: acquiring a plurality of transmission data between communication equipment, caching the plurality of transmission data to edge equipment, controlling an edge computing unit to detect whether abnormal data exists in the plurality of transmission data, and receiving a detection result sent by the edge computing unit; when the detection result represents that the abnormal data exists, extracting a first identifier of the abnormal data, and screening out target communication equipment from the plurality of communication equipment based on the first identifier; and inputting the abnormal data into a preset fault prediction model, receiving a prediction result output by the fault prediction model, and carrying out troubleshooting on the target communication equipment based on the prediction result.

Description

Technical Field

[0001] The present invention relates to the technical field of fault troubleshooting, and in particular to a communication fault troubleshooting method for an energy storage system. Background Art

[0002] In the operation and maintenance of electrochemical energy storage power stations, the stability of the communication network is crucial to ensure the safe and efficient operation of the power station. Electrochemical energy storage power stations usually contain large-scale sensors and control equipment, which are interconnected through complex communication networks. These networks are responsible for transmitting key monitoring and control signals, and any communication failure may cause the electrochemical energy storage power station to reduce operating efficiency or even shut down.

[0003] At present, communication fault troubleshooting for electrochemical energy storage power stations usually involves identifying the occurrence of faults through status indicator lights on monitoring equipment or simple alarm systems. Based on the alarm information and experience, a preliminary judgment is made on the area where the fault may have occurred, and operation and maintenance personnel are dispatched to the site. The operation and maintenance personnel manually check the equipment and lines to locate the fault point, repair the fault point, and record the fault and repair process.

[0004] However, traditional troubleshooting methods take a long time from fault occurrence to detection, location and repair, which affects the operating efficiency of the power station. In addition, they rely on the experience and intuition of operation and maintenance personnel, which may lead to the risk of misjudgment. At the same time, since the troubleshooting and repair process is mostly performed manually by operation and maintenance personnel, the efficiency of handling communication failures is low. Summary of the invention

[0005] The embodiment of the present invention provides a communication fault troubleshooting method for an energy storage system to solve the problem that the traditional troubleshooting and repair process relies on the experience and intuition of operation and maintenance personnel, has the risk of misjudgment, and has low efficiency in handling communication faults.

[0006] An embodiment of the present invention discloses a communication fault troubleshooting method for an energy storage system, which is applied to a control center. The control center is connected to an energy storage system. The energy storage system includes at least a plurality of communication devices and a plurality of edge devices. The communication devices are connected to the edge devices. The edge devices include edge computing units. The method includes:

[0007] Collecting a plurality of transmission data between the communication devices, and caching the plurality of transmission data to the edge device, wherein the transmission data carries an identifier;

[0008] Control the edge computing unit to detect whether there is abnormal data in the plurality of transmission data, and receive the detection result sent by the edge computing unit;

[0009] In the case where the detection result is characterized as the presence of the abnormal data, extracting a first identifier of the abnormal data, and screening out a target communication device from the plurality of communication devices based on the first identifier;

[0010] The abnormal data is input into a preset fault prediction model, and a prediction result output by the fault prediction model is received, and the target communication device is troubleshooted based on the prediction result.

[0011] Optionally, before collecting a plurality of transmission data between the communication devices, the method includes:

[0012] Initializing the communication device and assigning a device identifier to the communication device, where the device identifier is used to uniquely identify the communication device;

[0013] Screening out a target communication device from a plurality of the communication devices based on the first identifier includes:

[0014] The first identifier is matched with the device identifier, and a communication device having the same device identifier as the first identifier is determined as a target communication device.

[0015] Optionally, the edge device is configured with a short-term cache database, and the step of caching the plurality of transmission data to the edge device comprises:

[0016] The transmission data is cached in the short-term cache database.

[0017] Optionally, the energy storage system further includes a cloud, and the cloud is configured with a long-term cache database. The method further includes:

[0018] Setting a first cache duration for the short-term cache database;

[0019] Periodically obtaining a second cache duration of the transmission data in the short-term cache database;

[0020] In a case where the second cache time length is greater than the first cache time length, the transmission data is uploaded from the short-term cache database to the long-term cache database, and the transmission data is removed from the short-term cache database.

[0021] Optionally, uploading the transmission data from the short-term cache database to the long-term cache database includes:

[0022] The transmission data is encrypted, and the encrypted transmission data is uploaded from the short-term cache database to the long-term cache database.

[0023] Optionally, the energy storage system records a corresponding fault log, and the fault prediction model is trained by the following method:

[0024] Acquire historical fault data of the communication device from the fault log, the historical fault data including at least a first fault operation parameter, and a first fault type and a first fault cause corresponding to the first fault operation parameter;

[0025] Extracting a first fault operation parameter feature from the first fault operation parameter;

[0026] Inputting the first fault operation parameter characteristic into a preset initial model for fault prediction, and obtaining a second fault type and a second fault cause output by the initial model;

[0027] Calculating a first loss function between the first fault type and the second fault type, and a second loss function between the first fault type and the second fault type;

[0028] The first loss function and the second loss function are used to adjust the initial model to generate a fault prediction model.

[0029] Optionally, inputting the abnormal data into a preset fault prediction model and receiving a prediction result output by the fault prediction model includes:

[0030] Inputting the abnormal data into a preset fault prediction model, and receiving a third fault type and a third fault cause output by the fault prediction model;

[0031] The target risk level of the target communication device is determined from a preset risk level table according to the third fault type and the third fault cause.

[0032] Optionally, the energy storage system records a corresponding fault log, and the risk level table is generated by the following method:

[0033] Acquire historical fault data of the communication device from the fault log, the historical fault data including at least a first fault operation parameter, and a first fault type and a first fault cause corresponding to the first fault operation parameter;

[0034] A risk level table is set according to the first fault type and the first fault cause.

[0035] Optionally, the control center includes a display screen, and after troubleshooting the target communication device based on the prediction result, the method further includes:

[0036] Generate a troubleshooting result of the target communication device, and record the troubleshooting result in the fault log;

[0037] Generate alarm information for the target communication device based on the troubleshooting result, send the alarm information to the display screen, and control the display screen to display the alarm information.

[0038] Optionally, when the detection result indicates that the abnormal data does not exist, the method includes:

[0039] Inputting the transmission data into a preset diagnosis model, and receiving the diagnosis result output by the diagnosis model;

[0040] Based on the diagnosis result, it is determined whether the communication device corresponding to the transmission data contains a potential fault.

[0041] An embodiment of the present invention discloses a communication fault troubleshooting method for an energy storage system, which is applied to an edge device, wherein the edge device is connected to a communication device, the edge device is located in an energy storage system, the energy storage system is connected to a control center, the edge device includes an edge computing unit, and an anomaly detection algorithm is configured in the edge computing unit. The method includes:

[0042] Receiving the transmission data sent by the control center, and filtering out target operation data from the transmission data according to preset operation status indicators;

[0043] Extracting operating status indicator characteristics of the target operating data;

[0044] Using the anomaly detection algorithm to detect the operating status indicator characteristics to obtain a detection result;

[0045] The detection result is sent to the control center.

[0046] The embodiment of the present invention discloses a communication fault troubleshooting device for an energy storage system, which is applied to a control center. The control center is connected to an energy storage system. The energy storage system includes at least a plurality of communication devices and a plurality of edge devices. The communication devices are connected to the edge devices. The edge devices include edge computing units. The device includes:

[0047] A data collection module, used for collecting a plurality of transmission data between the communication devices, and caching the plurality of transmission data to the edge device, wherein the transmission data carries an identifier;

[0048] A result receiving module, used to control the edge computing unit to detect whether there is abnormal data in the plurality of transmission data, and receive the detection result sent by the edge computing unit;

[0049] A first extraction module, configured to extract a first identifier of the abnormal data when the detection result indicates that the abnormal data exists, and screen out a target communication device from the plurality of communication devices based on the first identifier;

[0050] The fault detection module is used to input the abnormal data into a preset fault prediction model, receive the prediction result output by the fault prediction model, and perform fault detection on the target communication device based on the prediction result.

[0051] Optionally, before the data acquisition module, the device includes:

[0052] An initialization module, used to initialize the communication device and assign a device identifier to the communication device, where the device identifier is used to uniquely identify the communication device;

[0053] The first extraction module is specifically configured to match the first identifier with the device identifier, and determine the communication device having the same device identifier as the first identifier as the target communication device.

[0054] Optionally, the edge device is configured with a short-term cache database, and the fault troubleshooting module is specifically configured to cache the transmission data into the short-term cache database.

[0055] Optionally, the energy storage system further includes a cloud, the cloud is configured with a long-term cache database, and the device further includes:

[0056] A cache duration setting module, used to set a first cache duration for the short-term cache database;

[0057] A cache duration acquisition module, used for periodically acquiring a second cache duration of the transmission data in the short-term cache database;

[0058] A data storage module is used to upload the transmission data from the short-term cache database to the long-term cache database and remove the transmission data from the short-term cache database when the second cache time length is greater than the first cache time length.

[0059] Optionally, the data storage module is further used to encrypt the transmission data, and upload the encrypted transmission data from the short-term cache database to the long-term cache database.

[0060] Optionally, the energy storage system records a corresponding fault log, and the fault prediction model is trained by the following devices:

[0061] A historical data acquisition module, used to acquire historical fault data of the communication device from the fault log, wherein the historical fault data at least includes a first fault operation parameter, and a first fault type and a first fault cause corresponding to the first fault operation parameter;

[0062] A parameter feature extraction module, used to extract a first fault operation parameter feature from the first fault operation parameter;

[0063] A parameter feature input module, used for inputting the first fault operation parameter feature into a preset initial model for fault prediction, and obtaining a second fault type and a second fault cause output by the initial model;

[0064] a loss function calculation module, configured to calculate a first loss function between the first fault type and the second fault type, and a second loss function between the first fault type and the second fault type;

[0065] The loss function adjustment module is used to adjust the initial model using the first loss function and the second loss function to generate a fault prediction model.

[0066] Optionally, the fault troubleshooting module includes:

[0067] An abnormal data input module, used for inputting the abnormal data into a preset fault prediction model, and receiving a third fault type and a third fault cause output by the fault prediction model;

[0068] The risk level determination module is used to determine the target risk level of the target communication device from a preset risk level table according to the third fault type and the third fault cause.

[0069] Optionally, the energy storage system records a corresponding fault log, and the risk level table is generated by the following device:

[0070] A historical data acquisition module, which acquires historical fault data of the communication device from the fault log, wherein the historical fault data at least includes a first fault operation parameter, and a first fault type and a first fault cause corresponding to the first fault operation parameter;

[0071] A risk level table setting module is used to set a risk level table according to the first fault type and the first fault cause.

[0072] Optionally, the control center includes a display screen, and after the fault troubleshooting module, the device further includes:

[0073] A fault recording module, used to generate a fault troubleshooting result of the target communication device and record the fault troubleshooting result in the fault log;

[0074] An alarm display module is used to generate alarm information for the target communication device according to the troubleshooting result, send the alarm information to the display screen, and control the display screen to display the alarm information.

[0075] Optionally, when the detection result indicates that the abnormal data does not exist, the device includes:

[0076] A transmission data diagnosis module, used for inputting the transmission data into a preset diagnosis model and receiving a diagnosis result output by the diagnosis model;

[0077] A potential fault judgment module is used to judge whether the communication device corresponding to the transmission data contains a potential fault based on the diagnosis result.

[0078] An embodiment of the present invention discloses a communication fault troubleshooting device for an energy storage system, which is applied to an edge device, wherein the edge device is connected to a communication device, the edge device is located in an energy storage system, the energy storage system is connected to a control center, the edge device includes an edge computing unit, and an anomaly detection algorithm is configured in the edge computing unit. The device includes:

[0079] A data screening module, used for receiving the transmission data sent by the control center, and screening out target operation data from the transmission data according to a preset operation status indicator;

[0080] A second extraction module, used to extract the operating status indicator characteristics of the target operating data;

[0081] An anomaly detection module, used to detect the operating status indicator characteristics using the anomaly detection algorithm to obtain a detection result;

[0082] The result sending module is used to send the detection result to the control center.

[0083] The embodiment of the present invention further discloses an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0084] The memory is used to store computer programs;

[0085] The processor is used to implement the method described in the embodiment of the present invention when executing the program stored in the memory.

[0086] The embodiment of the present invention further discloses a computer-readable storage medium on which instructions are stored. When the instructions are executed by one or more processors, the processors execute the method described in the embodiment of the present invention.

[0087] The embodiments of the present invention include the following advantages:

[0088] The present invention collects multiple transmission data between communication devices, caches the multiple transmission data to edge devices, controls the edge computing unit to detect whether there is abnormal data in the multiple transmission data, and receives the detection result sent by the edge computing unit; when the detection result is characterized as the presence of abnormal data, extracts the first identifier of the abnormal data, and screens out the target communication device from a number of communication devices based on the first identifier; inputs the abnormal data into a preset fault prediction model, receives the prediction result output by the fault prediction model, and performs troubleshooting on the target communication device based on the prediction result. The identifier carried by the abnormal data of the present invention can quickly and accurately locate the source of the fault, and at the same time, the abnormal data is deeply analyzed through the fault prediction model, which reduces the misjudgment rate of manual inspection and improves the accuracy and work efficiency of troubleshooting. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] Figure 1 is a flowchart of a method for troubleshooting communication faults in an energy storage system provided in an embodiment of the present invention;

[0090] Figure 2 is a flowchart of a method for troubleshooting communication faults in an energy storage system provided in an embodiment of the present invention;

[0091] Figure 3 is a structural block diagram of a communication fault troubleshooting device for an energy storage system provided in an embodiment of the present invention;

[0092] Figure 4 is a structural block diagram of a communication fault troubleshooting device for an energy storage system provided in an embodiment of the present invention;

[0093] Figure 5 It is a block diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0094] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0095] Reference Figure 1 , shows a flow chart of the steps of a communication fault troubleshooting method for an energy storage system provided in an embodiment of the present invention. The method is applied to a control center, the control center is connected to an energy storage system, the energy storage system includes at least a number of communication devices and a number of edge devices, the communication devices are connected to the edge devices, the edge devices include edge computing units, and specifically may include the following steps:

[0096] Step 101 , collect multiple transmission data between communication devices, and cache the multiple transmission data to an edge device, where the transmission data carries an identifier.

[0097] The energy storage system is an integrated energy management system that includes at least communication equipment, edge equipment and cloud. Through the collaborative work of communication equipment, edge equipment and cloud platform, the intelligent management of energy storage system is realized, energy utilization efficiency is improved, equipment life is extended, and the safety and reliability of the system are ensured. Among them, communication equipment includes wireless communication modules (such as 4G / 5G, low-power wide area network, narrowband Internet of Things) and wired communication modules (such as Ethernet, optical fiber), and communication equipment is used for data transmission. The edge device includes an edge computing unit and a short-term cache database, which can perform preliminary analysis and processing on the data transmitted by the communication equipment, and can also respond quickly to the energy storage system according to the instructions sent locally or in the cloud (such as charge and discharge control, fault protection, etc.). The short-term cache database can cache data when communication is interrupted, and upload the data to the cloud after the communication is restored. The cloud includes a long-term cache database, which is used to store various historical data of the storage system.

[0098] The embodiment of the present invention can install sensors such as voltage, current, temperature, and gas to collect multiple transmission data between communication devices in the energy storage system. The communication protocols used between the communication devices may include Modbus, MQTT (Message Queuing Telemetry Transport, lightweight Internet of Things communication protocol), OPC UA (Open Platform Communications Unified Architecture, open platform communication protocol), etc.

[0099] In the embodiment of the present invention, the edge device is configured with a short-term cache database, so after the transmission is collected, the transmission data is stored in the short-term cache database of the edge device.

[0100] The energy storage system of the present invention also includes a cloud, and a long-term cache database is configured in the cloud. When the energy storage system communicates normally, the transmission data is directly uploaded to the long-term cache database in the cloud. When the energy storage system fails and the communication is disconnected, the transmission data is first uploaded to the short-term cache database of the edge device. After the communication of the energy storage system is restored, the transmission data is uploaded from the short-term cache database to the long-term cache database, and the uploaded transmission data is deleted from the short-term cache database. The embodiment of the present invention also includes another method for backing up transmission data. During normal communication, the transmission data can be first uploaded to the short-term cache database of the edge device. When the storage time of the transmission data in the short-term cache database meets the preset storage time, the transmission data whose storage time meets the preset storage time is uploaded from the short-term cache database to the long-term cache database in the cloud, and the uploaded transmission data is deleted from the short-term cache database. The specific implementation steps are as follows:

[0101] Set the first cache duration for the short-term cache database;

[0102] Periodically obtain the second cache duration of the transmission data in the short-term cache database;

[0103] When the second cache time length is greater than the first cache time length, the transmission data is uploaded from the short-term cache database to the long-term cache database, and the transmission data is removed from the short-term cache database.

[0104] In an embodiment of the present invention, the transmission data is first preliminarily processed and cached on the edge device, which reduces frequent cloud interactions, thereby alleviating the processing pressure on the cloud server. In addition, the transmission data is uploaded to the cloud in batches, avoiding network congestion caused by uploading a large amount of data at one time, and improving the stability and reliability of data upload.

[0105] A third cache time period may also be set for the cloud. When the fourth cache time period of the transmission data in the cloud is greater than the third cache time period, the operation and maintenance personnel may choose to clear out this part of the transmission data to free up storage space in the cloud, or may choose to retain this part of the transmission data but generate cache information for this part of the transmission data, and periodically send the cache information to the control center to remind the operation and maintenance personnel that there is transmission data in the cloud that has been stored for too long. The operation and maintenance personnel may decide whether to clear out this part of the transmission data, and the present invention does not make any specific limitation to this.

[0106] Before uploading the transmission data from the short-term cache database to the long-term cache database, in order to ensure the security of data transmission, the transmission data can be encrypted first, and then the encrypted transmission data can be uploaded from the short-term cache database to the long-term cache database. Before encrypting the transmission data, in order to reduce the amount of encrypted data and improve efficiency, the transmission data can be compressed first, and then the compressed transmission data can be encrypted.

[0107] Specifically, symmetric encryption can be used, that is, the same key is used for encryption and decryption, such as AES (Advanced Encryption Standard). Symmetric encryption is fast and suitable for encryption of large amounts of data. Alternatively, asymmetric encryption can be used, that is, public and private keys are used for encryption and decryption. Symmetric encryption can also be combined with asymmetric encryption, for example, symmetric encryption is used to encrypt transmission data, and then asymmetric encryption is used to protect the symmetric key, which ensures both speed and security. In addition, the SSL (Secure Sockets Layer) / TLS (Transport Layer Security) protocol can be used to encrypt the upload channel during the process of uploading the transmission data from the short-term cache database to the long-term cache database. In addition to encryption during transmission, the transmission data should also be encrypted when stored. In other words, the transmission data in the short-term cache database and the long-term cache database should be stored in an encrypted form to prevent unauthorized access. Even if an attacker obtains access rights to the database, the data content stored in the database cannot be read.

[0108] Step 102, control the edge computing unit to detect whether there is abnormal data in multiple transmission data, and receive the detection result sent by the edge computing unit.

[0109] The edge device refers to a device deployed at the edge side of the energy storage system. The edge device of the present invention includes an edge computing unit, and the edge computing unit includes a variety of anomaly detection algorithms.

[0110] In the energy storage system, the edge device can monitor the operating data of the communication equipment, such as voltage, current, temperature, etc. These operating data will be transmitted to the edge computing unit for processing. If a communication device fails, some parameters will be abnormal, such as a sudden increase in current or a sharp rise in temperature. The mean and standard deviation of these parameters can be calculated by statistical methods, and an operating parameter threshold can be set. Data exceeding the operating parameter threshold is marked as abnormal data. Machine learning models (such as cluster analysis, support vector machines, and isolation forests) can also be used to learn data patterns under normal operating conditions, and then detect data that deviates from these patterns. In addition, considering the limitations of computing resources, it may be necessary to select lightweight models, such as some simplified versions of neural networks. The present invention does not specifically limit the selection of anomaly detection algorithms in edge computing units. In addition, since the transmitted data may come from different sensors with different units and dimensions, it may be necessary to perform pre-processing such as denoising and normalization on the transmitted data before detection.

[0111] Step 103: When the detection result indicates that abnormal data exists, extract a first identifier of the abnormal data, and select a target communication device from a plurality of communication devices based on the first identifier.

[0112] Before collecting multiple transmission data between communication devices, in order to facilitate the location of the communication device with communication failure, the embodiment of the present invention first allocates a device identifier to each communication device in the energy storage system. When the communication devices send data to each other, they will attach their own device identifiers to the sent data. Therefore, when abnormal data is detected, the faulty communication device can be quickly located based on the device identifier carried by the abnormal data. The specific steps are as follows:

[0113] Initialize the communication device and assign a device identifier to the communication device, where the device identifier is used to uniquely identify the communication device;

[0114] Screening out a target communication device from a plurality of communication devices based on the first identifier includes:

[0115] The first identifier is matched with the device identifier, and a communication device having the same device identifier as the first identifier is determined as a target communication device.

[0116] Step 104: input the abnormal data into a preset fault prediction model, receive the prediction result output by the fault prediction model, and perform fault troubleshooting on the target communication device based on the prediction result.

[0117] The traditional troubleshooting method relies on the experience and intuition of the operation and maintenance personnel from the occurrence of the fault to detection, location and repair, and there may be a risk of misjudgment. Therefore, the embodiment of the present invention pre-trains the fault prediction model. Since the energy storage system records the corresponding fault log, the fault log records the historical fault data of the energy storage system. The fault prediction model is trained by the following method:

[0118] The historical fault data of the communication device is obtained from the fault log, and the historical fault data at least includes the first fault operating parameter (such as voltage, current, temperature, communication delay, etc.), and the first fault type (such as hardware fault, software fault, communication interruption, etc.) and the first fault cause (such as overheating, short circuit, software crash, etc.) corresponding to the first fault operating parameter. In addition, the historical fault data may also include the first fault time, the first fault duration, and the first fault solution corresponding to the first fault operating parameter, so as to improve the accuracy of fault detection and fault repair.

[0119] Extract the first fault operation parameter feature from the first fault operation parameter, such as statistical feature, time series feature and combination feature, wherein the statistical feature may include mean, variance, maximum value, minimum value, etc., the time series feature may include trend change, periodicity feature, etc., and the combination feature may include a combination relationship of multiple parameters.

[0120] The first fault operation parameter feature is input into a preset initial model for fault prediction, and a second fault type and a second fault cause are obtained as output by the initial model. The initial model of the present invention can be a deep learning model, a random forest, a support vector machine, etc. After the initial model performs fault prediction on the first fault operation parameter feature, the predicted second fault type and the second fault cause can be output.

[0121] A first loss function between the first fault type and the second fault type, and a second loss function between the first fault type and the second fault type are calculated; the first loss function and the second loss function are used to adjust the initial model to generate a fault prediction model.

[0122] Evaluate the difference between the model's predictions and the actual results, and adjust the parameters of the initial model based on the difference to generate a high-precision fault prediction model. Use gradient descent or other optimization algorithms to adjust the model parameters based on the gradient of the loss function. Repeat the above steps until the model's loss function reaches the expected value or converges, thus generating a fault prediction model.

[0123] Among them, the first loss function and the second loss function can be cross-entropy loss (Cross-Entropy Loss), logarithmic loss (Log Loss), mean squared error (Mean Squared Error, MSE), mean absolute error (Mean Absolute Error, MAE), weighted loss function, joint loss function, etc. The present invention does not specifically limit the choice of loss function.

[0124] When training the fault prediction model, the present invention can also pre-divide the historical fault data in the fault log into a training set and a verification set, use the historical fault data in the training set to train the model, and use the historical fault data in the verification set to verify the generalization ability of the model to ensure that it can accurately make predictions.

[0125] In an embodiment of the present invention, the abnormal data is input into a preset fault prediction model, and the prediction result output by the fault prediction model is received, including:

[0126] Inputting the abnormal data into a preset fault prediction model, and receiving a third fault type and a third fault cause output by the fault prediction model;

[0127] A target risk level of the target communication device is determined from a preset risk level table according to the third fault type and the third fault cause.

[0128] In the embodiment of the present invention, the energy storage system records a corresponding fault log, and the risk level table is generated by the following method:

[0129] Acquire historical fault data of the communication device from the fault log, where the historical fault data at least includes a first fault operation parameter, and a first fault type and a first fault cause corresponding to the first fault operation parameter;

[0130] A risk level table is set according to the first fault type and the first fault cause.

[0131] For the historical fault data in the fault log, the risk level corresponding to each type of fault can be marked. In fault prediction and maintenance management, setting up a risk level table can help operation and maintenance personnel quickly identify and prioritize high-risk faults, as shown in Table 1:

[0132]

[0133] Table 1

[0134] By setting up a risk level table, you can quickly assess the risk level of a fault based on the fault type and cause, and determine the priority of handling. This helps operation and maintenance personnel to efficiently manage faults, reduce the risk of equipment downtime, and thus improve system reliability and stability.

[0135] In an embodiment of the present invention, the control center also includes a display screen. Therefore, after troubleshooting the target communication device based on the prediction results, it is also possible to generate troubleshooting results for the target communication device, record the troubleshooting results in a fault log, and generate alarm information for the target communication device based on the troubleshooting results, and send the alarm information to the display screen to control the display screen to display the alarm information.

[0136] In another embodiment of the present invention, when the detection result indicates that there is no abnormal data, a preset diagnostic model can be used to detect whether the transmission data at this time has a potential fault, so that the communication device with the potential fault can be repaired in time. The specific steps are as follows:

[0137] Inputting the transmission data into a preset diagnosis model and receiving the diagnosis result output by the diagnosis model;

[0138] Based on the diagnosis result, it is determined whether the communication device corresponding to the transmission data contains a potential fault.

[0139] The present invention collects multiple transmission data between communication devices, caches the multiple transmission data to edge devices, controls the edge computing unit to detect whether there is abnormal data in the multiple transmission data, and receives the detection result sent by the edge computing unit; when the detection result is characterized as the presence of abnormal data, extracts the first identifier of the abnormal data, and screens out the target communication device from a number of communication devices based on the first identifier; inputs the abnormal data into a preset fault prediction model, receives the prediction result output by the fault prediction model, and performs troubleshooting on the target communication device based on the prediction result. The identifier carried by the abnormal data of the present invention can quickly and accurately locate the source of the fault, and at the same time, the abnormal data is deeply analyzed through the fault prediction model, which reduces the misjudgment rate of manual inspection and improves the accuracy and work efficiency of troubleshooting.

[0140] Reference Figure 2 , shows a flow chart of the steps of a communication fault troubleshooting method for an energy storage system provided in an embodiment of the present invention, the method is applied to an edge device, the edge device is connected to a communication device, the edge device is located in an energy storage system, the energy storage system is connected to a control center, the edge device includes an edge computing unit, and an anomaly detection algorithm is configured in the edge computing unit, which may specifically include the following steps:

[0141] Step 201, receiving transmission data sent by the control center, and filtering target operation data from the transmission data according to preset operation status indicators;

[0142] Step 202, extracting the operating status indicator characteristics of the target operating data;

[0143] Step 203, using an abnormality detection algorithm to detect the characteristics of the operating status indicators to obtain a detection result;

[0144] Step 204, sending the detection result to the control center.

[0145] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but the operation and maintenance personnel in this field should be aware that the embodiments of the present invention are not limited by the described action sequence, because according to the embodiments of the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, the operation and maintenance personnel in this field should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0146] Reference Figure 3 , shows a structural block diagram of a communication fault troubleshooting device provided in an embodiment of the present invention, the device is applied to a control center, the control center is connected to an energy storage system, the energy storage system includes at least a number of communication devices and a number of edge devices, the communication devices are connected to the edge devices, the edge devices include edge computing units, and specifically may include the following modules:

[0147] The data collection module 301 is used to collect multiple transmission data between communication devices and cache the multiple transmission data to the edge device, where the transmission data carries an identifier;

[0148] A result receiving module 302 is used to control the edge computing unit to detect whether there is abnormal data in the multiple transmission data, and receive the detection result sent by the edge computing unit;

[0149] A first extraction module 303 is used to extract a first identifier of the abnormal data when the detection result indicates that abnormal data exists, and to select a target communication device from a plurality of communication devices based on the first identifier;

[0150] The fault troubleshooting module 304 is used to input abnormal data into a preset fault prediction model, receive the prediction result output by the fault prediction model, and perform fault troubleshooting on the target communication device based on the prediction result.

[0151] Optionally, before the data acquisition module 301, the device includes:

[0152] An initialization module, used to initialize the communication device and assign a device identifier to the communication device, where the device identifier is used to uniquely identify the communication device;

[0153] The first extraction module is specifically used to match the first identifier with the device identifier, and determine the communication device with the same device identifier as the first identifier as the target communication device.

[0154] Optionally, the edge device is configured with a short-term cache database, and the fault troubleshooting module 304 is specifically configured to cache the transmission data into the short-term cache database.

[0155] Optionally, the energy storage system further includes a cloud, the cloud is configured with a long-term cache database, and the device further includes:

[0156] A cache duration setting module, used to set a first cache duration for a short-term cache database;

[0157] A cache duration acquisition module is used to periodically acquire the second cache duration of the transmission data in the short-term cache database;

[0158] The data storage module is used to upload the transmission data from the short-term cache database to the long-term cache database and remove the transmission data from the short-term cache database when the second cache time length is greater than the first cache time length.

[0159] Optionally, the data storage module is further used to encrypt the transmission data and upload the encrypted transmission data from the short-term cache database to the long-term cache database.

[0160] Optionally, the energy storage system records corresponding fault logs, and the fault prediction model is trained by the following devices:

[0161] A historical data acquisition module, used to acquire historical fault data of the communication device from the fault log, the historical fault data at least including a first fault operation parameter, and a first fault type and a first fault cause corresponding to the first fault operation parameter;

[0162] A parameter feature extraction module, used to extract a first fault operation parameter feature from the first fault operation parameter;

[0163] A parameter feature input module, used to input the first fault operation parameter feature into a preset initial model for fault prediction, and obtain a second fault type and a second fault cause output by the initial model;

[0164] A loss function calculation module, used to calculate a first loss function between a first fault type and a second fault type, and a second loss function between the first fault type and the second fault type;

[0165] The loss function adjustment module is used to adjust the initial model using the first loss function and the second loss function to generate a fault prediction model.

[0166] Optionally, the fault troubleshooting module 304 includes:

[0167] An abnormal data input module, used to input the abnormal data into a preset fault prediction model, and receive a third fault type and a third fault cause output by the fault prediction model;

[0168] The risk level determination module is used to determine the target risk level of the target communication device from a preset risk level table according to the third fault type and the third fault cause.

[0169] Optionally, the energy storage system records a corresponding fault log, and the risk level table is generated by the following device:

[0170] A historical data acquisition module, which acquires historical fault data of the communication device from the fault log, wherein the historical fault data at least includes a first fault operation parameter, and a first fault type and a first fault cause corresponding to the first fault operation parameter;

[0171] The risk level table setting module is used to set the risk level table according to the first fault type and the first fault cause.

[0172] Optionally, the control center includes a display screen. After the fault troubleshooting module 304, the device further includes:

[0173] A fault recording module is used to generate a fault troubleshooting result of the target communication device and record the fault troubleshooting result in a fault log;

[0174] The alarm display module is used to generate alarm information for the target communication equipment according to the troubleshooting results, send the alarm information to the display screen, and control the display screen to display the alarm information.

[0175] Optionally, when the detection result indicates that there is no abnormal data, the device includes:

[0176] A transmission data diagnosis module, used to input the transmission data into a preset diagnosis model and receive the diagnosis result output by the diagnosis model;

[0177] The potential fault judgment module is used to judge whether the communication device corresponding to the transmission data contains a potential fault based on the diagnosis result.

[0178] Reference Figure 4 , shows a structural block diagram of a communication fault troubleshooting device for an energy storage system provided in an embodiment of the present invention, the device is applied to an edge device, the edge device is connected to a communication device, the edge device is located in an energy storage system, the energy storage system is connected to a control center, the edge device includes an edge computing unit, and an anomaly detection algorithm is configured in the edge computing unit, which may specifically include the following modules:

[0179] The data screening module 401 is used to receive the transmission data sent by the control center and screen the target operation data from the transmission data according to the preset operation status index;

[0180] The second extraction module 402 is used to extract the operating status indicator characteristics of the target operating data;

[0181] The anomaly detection module 403 is used to detect the characteristics of the operating status indicators using an anomaly detection algorithm to obtain a detection result;

[0182] The result sending module 404 is used to send the detection result to the control center.

[0183] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0184] Reference Figure 5 The embodiment of the present invention further provides an electronic device, including a processor 501, a communication interface 502, a memory 503 and a communication bus 504, wherein the processor 501, the communication interface 502 and the memory 503 communicate with each other through the communication bus 504.

[0185] Memory 503, used for storing computer programs;

[0186] The processor 501 is used to execute the program stored in the memory 503 to implement the communication fault troubleshooting method of the energy storage system as described above:

[0187] Collect multiple transmission data between communication devices, and cache the multiple transmission data to edge devices, where the transmission data carries an identifier;

[0188] Control the edge computing unit to detect whether there is abnormal data in the multiple transmission data, and receive the detection result sent by the edge computing unit;

[0189] When the detection result indicates that abnormal data exists, extracting a first identifier of the abnormal data, and screening out a target communication device from a plurality of communication devices based on the first identifier;

[0190] The abnormal data is input into a preset fault prediction model, and the prediction results output by the fault prediction model are received, and the target communication equipment is troubleshooted based on the prediction results.

[0191] The communication bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0192] The communication interface is used for communication between the above terminal and other devices.

[0193] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0194] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0195] In another embodiment provided by the present invention, a computer-readable storage medium is provided, on which instructions are stored. When the instructions are executed by a processor, the communication fault troubleshooting method for the energy storage system described in any of the above embodiments is implemented.

[0196] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0197] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0198] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0199] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A communication fault troubleshooting method for an energy storage system, characterized in that: Applied to a control center, the control center is connected to an energy storage system, the energy storage system includes at least a plurality of communication devices and a plurality of edge devices, the communication devices are connected to the edge devices, the edge devices include edge computing units, and the method includes: Collecting a plurality of transmission data between the communication devices, and caching the plurality of transmission data to the edge device, wherein the transmission data carries an identifier; Control the edge computing unit to detect whether there is abnormal data in the plurality of transmission data, and receive the detection result sent by the edge computing unit; In the case where the detection result is characterized as the presence of the abnormal data, extracting a first identifier of the abnormal data, and screening out a target communication device from the plurality of communication devices based on the first identifier; The abnormal data is input into a preset fault prediction model, and a prediction result output by the fault prediction model is received, and the target communication device is troubleshooted based on the prediction result.

2. The method according to claim 1, characterized in that Before collecting a plurality of transmission data between the communication devices, the method includes: Initializing the communication device and assigning a device identifier to the communication device, where the device identifier is used to uniquely identify the communication device; Screening out a target communication device from a plurality of the communication devices based on the first identifier includes: The first identifier is matched with the device identifier, and a communication device having the same device identifier as the first identifier is determined as a target communication device.

3. The method according to claim 1, characterized in that The edge device is configured with a short-term cache database, and the caching of the plurality of transmission data to the edge device includes: The transmission data is cached in the short-term cache database.

4. The method according to claim 3, characterized in that The energy storage system further includes a cloud, wherein the cloud is configured with a long-term cache database, and the method further includes: Setting a first cache duration for the short-term cache database; Periodically obtaining a second cache duration of the transmission data in the short-term cache database; In a case where the second cache time length is greater than the first cache time length, the transmission data is uploaded from the short-term cache database to the long-term cache database, and the transmission data is removed from the short-term cache database.

5. The method according to claim 4, characterized in that The uploading of the transmission data from the short-term cache database to the long-term cache database comprises: The transmission data is encrypted, and the encrypted transmission data is uploaded from the short-term cache database to the long-term cache database.

6. The method according to claim 1, characterized in that The energy storage system records the corresponding fault log, and the fault prediction model is trained by the following method: Acquire historical fault data of the communication device from the fault log, the historical fault data including at least a first fault operation parameter, and a first fault type and a first fault cause corresponding to the first fault operation parameter; Extracting a first fault operation parameter feature from the first fault operation parameter; Inputting the first fault operation parameter characteristic into a preset initial model for fault prediction, and obtaining a second fault type and a second fault cause output by the initial model; Calculating a first loss function between the first fault type and the second fault type, and a second loss function between the first fault type and the second fault type; The first loss function and the second loss function are used to adjust the initial model to generate a fault prediction model.

7. The method according to claim 1, characterized in that The step of inputting the abnormal data into a preset fault prediction model and receiving a prediction result output by the fault prediction model comprises: Inputting the abnormal data into a preset fault prediction model, and receiving a third fault type and a third fault cause output by the fault prediction model; The target risk level of the target communication device is determined from a preset risk level table according to the third fault type and the third fault cause.

8. The method according to claim 7, characterized in that The energy storage system records the corresponding fault log, and the risk level table is generated by the following method: Acquire historical fault data of the communication device from the fault log, the historical fault data including at least a first fault operation parameter, and a first fault type and a first fault cause corresponding to the first fault operation parameter; A risk level table is set according to the first fault type and the first fault cause.

9. The method according to claim 8, characterized in that The control center includes a display screen. After troubleshooting the target communication device based on the prediction result, the method further includes: Generate a troubleshooting result of the target communication device, and record the troubleshooting result in the fault log; Generate alarm information for the target communication device based on the troubleshooting result, send the alarm information to the display screen, and control the display screen to display the alarm information.

10. The method according to claim 1, characterized in that When the detection result indicates that the abnormal data does not exist, the method includes: Inputting the transmission data into a preset diagnosis model, and receiving the diagnosis result output by the diagnosis model; Based on the diagnosis result, it is determined whether the communication device corresponding to the transmission data contains a potential fault.

11. A communication fault troubleshooting method for an energy storage system, characterized in that: Applied to an edge device, the edge device is connected to a communication device, the edge device is located in an energy storage system, the energy storage system is connected to a control center, the edge device includes an edge computing unit, and an anomaly detection algorithm is configured in the edge computing unit. The method includes: Receiving the transmission data sent by the control center, and filtering out target operation data from the transmission data according to preset operation status indicators; Extracting operating status indicator characteristics of the target operating data; Using the anomaly detection algorithm to detect the operating status indicator characteristics to obtain a detection result; The detection result is sent to the control center.

12. A communication fault troubleshooting device for an energy storage system, characterized in that: Applied to a control center, the control center is connected to an energy storage system, the energy storage system includes at least a plurality of communication devices and a plurality of edge devices, the communication devices are connected to the edge devices, the edge devices include an edge computing unit, and the device includes: A data collection module, used for collecting a plurality of transmission data between the communication devices, and caching the plurality of transmission data to the edge device, wherein the transmission data carries an identifier; A result receiving module, used to control the edge computing unit to detect whether there is abnormal data in the plurality of transmission data, and receive the detection result sent by the edge computing unit; A first extraction module, configured to extract a first identifier of the abnormal data when the detection result indicates that the abnormal data exists, and screen out a target communication device from the plurality of communication devices based on the first identifier; The fault detection module is used to input the abnormal data into a preset fault prediction model, receive the prediction result output by the fault prediction model, and perform fault detection on the target communication device based on the prediction result.

13. A communication fault troubleshooting device for an energy storage system, characterized in that: Applied to an edge device, the edge device is connected to a communication device, the edge device is located in an energy storage system, the energy storage system is connected to a control center, the edge device includes an edge computing unit, and an anomaly detection algorithm is configured in the edge computing unit. The device includes: A data screening module, used for receiving the transmission data sent by the control center, and screening out target operation data from the transmission data according to a preset operation status indicator; A second extraction module, used to extract the operating status indicator characteristics of the target operating data; An anomaly detection module, used to detect the operating status indicator characteristics using the anomaly detection algorithm to obtain a detection result; The result sending module is used to send the detection result to the control center.

14. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; The memory is used to store computer programs; The processor is used to execute the program stored in the memory to implement the communication fault troubleshooting method of the energy storage system according to any one of claims 1 to 11. 15 . A computer-readable storage medium having instructions stored thereon, which, when executed by one or more processors, causes the processors to execute the communication fault troubleshooting method for an energy storage system according to any one of claims 1 to 11.

Images