Fault early warning method, device and equipment

Abstract

The invention relates to a fault early warning method, device and equipment, which are applied to a first server, and the method comprises the following steps: responding to an indication of fault detection of a power supply unit (PSU) in a second server, and performing fault early warning on the PSU through a plurality of communication interfaces between the PSU and the second server at intervals of a first preset period; respectively obtaining the state information of the PSU in the second server; comparing the state information obtained through each communication interface, and when a comparison result is determined to meet a first preset condition, storing each piece of state information into a first storage file; the state information included in the first storage file is clustered every second preset period, whether the PSU is abnormal or not is determined based on the clustering result, and the PSU fault detection efficiency and accuracy are improved.

Description

Technical Field

[0001] The present application relates to the technical field of equipment detection, and in particular to a fault warning method, device and equipment. Background Art

[0002] As one of the key components of a server, the stability and reliability of the PSU (Power Supply Unit) are very important for the system operation of the server. Therefore, accurate detection and timely warning of PSU failures are one of the important measures to ensure stable system operation.

[0003] In the related art, when performing fault detection on PSU, on-site operation and maintenance is usually adopted, that is, fault detection and early warning are achieved through manual inspections, regular maintenance, etc., but this method cannot perform real-time detection of PSU, resulting in difficulty in timely discovery and handling of PSU faults, low operation and maintenance efficiency, and the accuracy of fault detection cannot be guaranteed under this method. Summary of the invention

[0004] The present invention provides a fault warning method for solving the problem that the related art performs PSU fault detection through on-site operation and maintenance, but the operation and maintenance efficiency is low and the accuracy cannot be guaranteed.

[0005] In a first aspect, the present application provides a fault warning method, which is applied to a first server, and the method includes:

[0006] In response to an instruction to detect a fault of a power supply unit (PSU) in the second server, at intervals of a first preset period, respectively obtain status information of the PSU in the second server through a plurality of communication interfaces with the second server;

[0007] Comparing the above-mentioned state information obtained through each communication interface, and when it is determined that the comparison result meets the first preset condition, storing each state information in a first storage file;

[0008] At intervals of a second preset period, each state information included in the first storage file is clustered, and whether the PSU is abnormal is determined based on the clustering result.

[0009] The above method obtains status information based on multiple communication interfaces and performs data analysis based on a clustering algorithm, thereby realizing all-round monitoring of the PSU status on the second server. At the same time, the present application supports a first server to detect and warn the information of multiple PSUs on multiple second servers, and supports capacity expansion based on the premise of already being deployed. It can realize online capacity expansion without affecting the first server and the second servers, greatly improving the operation and maintenance efficiency and quality, and saving a lot of labor costs and time consumption.

[0010] In a possible implementation manner, the first preset condition is: the difference between the same state information obtained through each communication interface is within a first preset value range;

[0011] If the comparison result does not meet the first preset condition, the method further includes:

[0012] At intervals of a third preset period, the following operations are cyclically performed until the comparison result satisfies the first preset condition or the number of cycles reaches a preset threshold: respectively obtaining the status information of the PSU in the second server through the multiple communication interfaces between the second server and the second server; comparing the status information obtained through each communication interface, and determining whether the comparison result satisfies the first preset condition;

[0013] If the comparison result is executed in a loop until it satisfies the first preset condition, each state information obtained in the last loop is stored in the first storage file.

[0014] In the above method, when the comparison result does not meet the first preset condition, the process of obtaining the status information of the PSU through multiple communication interfaces and performing the comparison is executed repeatedly in a loop; when the number of cycles does not reach the preset threshold but the comparison result meets the first preset condition, the subsequent operations are continued. By verifying the comparison result, errors in the comparison result caused by accidental factors can be avoided, and the accuracy of fault detection can be further improved.

[0015] In a possible implementation manner, after responding to the indication of performing fault detection on the power supply unit PSU in the second server, the method further includes:

[0016] Obtaining attribute information of the PSU in the second server respectively through a plurality of communication interfaces with the second server;

[0017] Compare the attribute information obtained through each communication interface, and when it is determined that the comparison result meets the second preset condition, store any attribute information in the second storage file; and obtain the attribute information of the PSU in the second server through any communication interface and store it in the second storage file at intervals of a fourth preset period;

[0018] Before clustering the state information included in the first storage file, the method further includes:

[0019] Clustering is performed on each piece of attribute information included in the second storage file, and based on the clustering result, it is determined that there is no abnormality in the attribute information of the PSU.

[0020] The above method collects PSU attribute information for comparison and clusters the collected attribute information to determine whether there is any abnormality in the attribute information of the PSU. When there is no abnormality, clustering operation on the status information is performed. Fault warning is performed through the dual collection of status information and attribute information, thereby further ensuring the accuracy of fault detection.

[0021] In a possible implementation manner, the first server includes at least one reference center point, and the clustering of each state information included in the first storage file includes:

[0022] For each reference center point, based on the distance between each state information and the reference center point, the state information whose distance is less than a preset distance threshold is screened out from the state information, and a cluster corresponding to the reference center point is generated;

[0023] The above-mentioned determination of whether the above-mentioned PSU is abnormal based on the clustering result includes:

[0024] If the above-mentioned state information includes state information that is not located in each cluster, it is determined that the above-mentioned PSU is abnormal.

[0025] The above method can filter abnormal data from each state information based on the distance between each state information and the reference center point, thereby achieving efficient and accurate early warning of faults.

[0026] In a possible implementation, if the current clustering operation is the first operation, the reference center point is a pre-configured initial center point; if the current clustering operation is not the first operation, the reference center point is determined based on the following method:

[0027] For each cluster generated in the last clustering operation, respectively determine the sum of the distances between each state information included in the cluster and other state information;

[0028] Based on the sum of the distances corresponding to the respective state information, a reference center point is selected from the plurality of state information included in the cluster.

[0029] The above method can ensure the real-time accuracy of the reference center point and further ensure the accuracy of subsequent clustering results by continuously updating the reference center point in multiple clustering operations, that is, determining the reference center point used currently based on the clustering result obtained in the previous clustering operation.

[0030] In a possible implementation manner, the initial center point is determined based on the following method:

[0031] Obtaining each historical status information of the PSU, determining the distance between each historical status information and other historical status information respectively, and summing up each distance to obtain a reference value corresponding to the historical status information;

[0032] Determine a candidate center point from each of the historical state information based on the reference values ​​corresponding to each of the historical state information;

[0033] If the difference between the candidate center point and the average value of each historical state information is within a second preset value range, the candidate center point is used as the initial center point.

[0034] The above method, when determining the initial center point used for the first clustering operation, verifies whether the currently determined center point meets the requirements based on the difference between the center point of the historical status data and the average value, which can ensure the accuracy of the initial center point and avoid the inaccuracy of the initial center point caused by the historical status data.

[0035] In a possible implementation manner, after responding to the indication of performing fault detection on the power supply unit PSU in the second server and before respectively acquiring the status information of the PSU in the second server, the method further includes:

[0036] Based on the identification and access list of the second server, determine that the second server belongs to the server to be detected, and obtain the target login information of the second server from the access list; the access list stores the identification and login information of each server to be detected;

[0037] A network connection is established between the first server and the second server based on the target login information.

[0038] The above method, by pre-configuring the access list and storing the identification and login information of each server to be detected, can quickly establish a network connection between the first server and the second server, thereby accelerating the efficiency of fault detection. At the same time, it can continue to expand the capacity based on the existing deployment by adding server information to the access list.

[0039] In a second aspect, an embodiment of the present application provides a fault warning device, which is applied to a first server, and the device includes:

[0040] an acquisition module, configured to, in response to an instruction to perform fault detection on a power supply unit PSU in the second server, acquire status information of the PSU in the second server through a plurality of communication interfaces with the second server at intervals of a first preset period;

[0041] A comparison module, used to compare the above-mentioned state information obtained through each communication interface, and when it is determined that the comparison result meets the first preset condition, store each state information in a first storage file;

[0042] The determination module is used to cluster the various status information included in the first storage file at intervals of a second preset period, and determine whether the PSU has an abnormality based on the clustering result.

[0043] In a possible implementation manner, the first preset condition is: the difference between the same state information obtained through each communication interface is within a first preset value range;

[0044] If the comparison result does not meet the first preset condition, the comparison module is further configured to:

[0045] At intervals of a third preset period, the following operations are cyclically performed until the comparison result satisfies the first preset condition or the number of cycles reaches a preset threshold: respectively obtaining the status information of the PSU in the second server through the multiple communication interfaces between the second server and the second server; comparing the status information obtained through each communication interface, and determining whether the comparison result satisfies the first preset condition;

[0046] If the comparison result is executed in a loop until it satisfies the first preset condition, each state information obtained in the last loop is stored in the first storage file.

[0047] In a possible implementation manner, after responding to an instruction to perform fault detection on the power supply unit PSU in the second server, the acquisition module is further configured to:

[0048] Obtaining attribute information of the PSU in the second server respectively through a plurality of communication interfaces with the second server;

[0049] Compare the attribute information obtained through each communication interface, and when it is determined that the comparison result meets the second preset condition, store any attribute information in the second storage file; and obtain the attribute information of the PSU in the second server through any communication interface and store it in the second storage file at intervals of a fourth preset period;

[0050] Before the determination module clusters each state information included in the first storage file, it is also used to:

[0051] Clustering is performed on each piece of attribute information included in the second storage file, and based on the clustering result, it is determined that there is no abnormality in the attribute information of the PSU.

[0052] In a possible implementation manner, the first server includes at least one reference center point, and the determination module is specifically configured to:

[0053] For each reference center point, based on the distance between each state information and the reference center point, the state information whose distance is less than a preset distance threshold is screened out from the state information, and a cluster corresponding to the reference center point is generated;

[0054] If the above-mentioned state information includes state information that is not located in each cluster, it is determined that the above-mentioned PSU is abnormal.

[0055] In a possible implementation, if the current clustering operation is the first operation, the reference center point is a pre-configured initial center point; if the current clustering operation is not the first operation, the reference center point is determined based on the following method:

[0056] For each cluster generated in the last clustering operation, respectively determine the sum of the distances between each state information included in the cluster and other state information;

[0057] Based on the sum of the distances corresponding to the respective state information, a reference center point is selected from the plurality of state information included in the cluster.

[0058] In a possible implementation manner, the initial center point is determined based on the following method:

[0059] Obtaining each historical status information of the PSU, determining the distance between each historical status information and other historical status information respectively, and summing up each distance to obtain a reference value corresponding to the historical status information;

[0060] Determine a candidate center point from each of the historical state information based on the reference values ​​corresponding to each of the historical state information;

[0061] If the difference between the candidate center point and the average value of each historical state information is within a second preset value range, the candidate center point is used as the initial center point.

[0062] In a possible implementation manner, after the acquisition module responds to the instruction to perform fault detection on the power supply PSU in the second server and before respectively acquiring the status information of the PSU in the second server, it is further configured to:

[0063] Based on the identification and access list of the second server, determine that the second server belongs to the server to be detected, and obtain the target login information of the second server from the access list; the access list stores the identification and login information of each server to be detected;

[0064] A network connection is established between the first server and the second server based on the target login information.

[0065] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the fault warning method when executing the computer program.

[0066] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps in the above-mentioned fault warning method of the present application are implemented.

[0067] In the fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which is stored in a computer-readable storage medium; when the processor of a memory access device reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the memory access device executes the steps in the above-mentioned fault warning method of the present application.

[0068] For each of the above-mentioned second to fifth aspects and the technical effects that may be achieved by each of the above-mentioned aspects, please refer to the above-mentioned description of the technical effects that can be achieved by the first aspect or various possible schemes in the first aspect, and no further details will be given here. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0070] Figure 1 A flowchart of a fault warning method provided in an embodiment of the present application;

[0071] Figure 2 A schematic diagram of a fault warning process provided in an embodiment of the present application;

[0072] Figure 3 A schematic diagram of a fault warning device provided in an embodiment of the present application;

[0073] Figure 4 A schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical solution and advantages of the present application more clear, the present application will be further described in detail below in conjunction with the accompanying drawings. The specific operation method in the method embodiment can also be applied to the device embodiment or the system embodiment.

[0075] In the description of this application, "multiple" is understood to be "at least two". "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent three situations: A exists alone, A and B exist at the same time, and B exists alone. A is connected to B, which can represent two situations: A is directly connected to B and A is connected to B through C. In addition, in the description of this application, words such as "first" and "second" are only used for the purpose of distinguishing descriptions, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying order.

[0076] In order to facilitate those skilled in the art to better understand the technical solutions provided by the embodiments of the present application, the following is a brief description of the professional terms involved:

[0077] (1) BMC (Baseboard Management Controller): An independent management microcontroller dedicated to servers. It provides a set of standard interfaces and management tools for system monitoring, management, and maintenance. BMC monitors the hardware status of devices and performs remote management operations through the hardware manager integrated in servers, network devices, and other computer systems.

[0078] (2) SNMP (Simple Network Management Protocol): It is an application layer protocol used for network management on IP (Internet Protocol) networks. SNMP allows NMS (Network Management Station, also known as management station) to collect status information of network devices and perform remote configuration and troubleshooting.

[0079] (3) Redfish: An open standard interface for hardware management. It is based on the RESTful API design style and uses HTTP (Hypertext Transfer Protocol) or HTTPS (Hypertext Transfer Protocol Secure) protocols for communication. It supports operations such as GET, POST, PUT, and DELETE. It uses JSON (JavaScript Object Notation) as the data exchange format and supports the OData (Open Data Protocol) protocol to facilitate querying and filtering resources.

[0080] As one of the key components of a server, the stability and reliability of the PSU (Power Supply Unit) are very important for the system operation of the server. Therefore, accurate detection and timely warning of PSU failures are one of the important measures to ensure stable system operation.

[0081] With the continuous development of science and technology, the methods for operation and maintenance detection of servers are becoming more and more automated. In related technologies, the following two methods are usually used to detect PSU faults:

[0082] The first is the on-site operation and maintenance method, which is to detect and warn of faults through manual inspections and regular maintenance. This method is more common among server information manufacturers and suppliers, but this method cannot perform real-time detection of the PSU, making it difficult to detect and handle PSU faults in a timely manner, resulting in low operation and maintenance efficiency. In addition, the accuracy of fault detection cannot be guaranteed under this method.

[0083] The other is conceptual operation and maintenance, which is to establish a complete PSU fault diagnosis expert system, set up log collection, fault inspection, status detection and other modules in the system to achieve all-round fault diagnosis. However, this method has not yet appeared in actual products, and due to the complex system design functions, the system takes a long time to implement and requires huge computing power as support.

[0084] In this regard, in order to ensure that under the premise of reducing the computing power requirements, the early warning of faults is accurately and efficiently realized, and the user's experience of using the server, the stability of the model and the competitiveness of the product are improved, this application provides a fault warning method for PSU, using the characteristics and advantages of SNMP and Redfish interface tools, designing corresponding monitoring modules and interface circuits, and realizing real-time monitoring of key components or parameter indicators of PSU; Specifically, the operation and maintenance server (i.e., the first server) can communicate with the PSU of the server to be detected (i.e., the second server) through SNMP and Redfish interface tools, obtain the key parameter information such as the operating status, temperature, and voltage of the PSU, and analyze and judge; if an abnormal situation or failure is found in the PSU, an early warning signal can be immediately issued or corresponding processing measures can be taken to avoid the expansion of the fault or cause the system to shut down. The method is easy to deploy, simple and practical, and can monitor PSU faults efficiently and in real time, improving the stability and reliability of the system.

[0085] In some embodiments, the fault warning method provided by the present application supports fault detection and warning for common standard PSUs, and specifically involves the following implementation tools:

[0086] In terms of hardware, a small server is required as an operation and maintenance server (i.e., the first server in this application) to execute the fault warning method of this application. Optionally, the server can be configured as a low-profile one.

[0087] In terms of software, in the embodiment of the present application, two scripts (i.e., information comparison script and cluster analysis script) and an access list need to be pre-configured, where:

[0088] The information comparison script is used to obtain relevant information of the PSU in the second server through multiple communication interfaces with the second server, and compare the status information obtained by each communication interface; optionally, the script can be generated using Linux (operating system kernel) code instructions.

[0089] In some embodiments, the above process can be implemented by various functions. Specifically, the information comparison script includes the following functions: psu_static_info_snmpget function part, psu_static_info_redfishget function part, psu_dynamic_info_snmpget function part, psu_dynamic_info_redfishget function part, data_collect function part, data_comparison function part and main function part.

[0090] The psu_static_info_snmpget function part and the psu_static_info_redfishget function part are respectively used to: collect static information (i.e., attribute information) of the PSU of the second server through SNMP and Redfish interface tools, where the attribute information includes at least one of a serial number, a product name, a part number, a firmware version, a manufacturer, and a production date;

[0091] The psu_dynamic_info_snmpget function part and the psu_dynamic_info_redfishget function part are respectively used to collect dynamic information (i.e., status information) of the PSU of the second server through SNMP and Redfish interface tools, wherein the status information includes at least one of core temperature, ambient temperature, input voltage, output voltage, input current, output current, input power, output power, fan load, and fan speed;

[0092] The data_comparison function is used to compare the same type of information collected through SNMP and Redfish, and execute the corresponding strategy based on the comparison results;

[0093] The data_collect function is used to process the same type of information collected through SNMP and Redfish (such as calculating the average value, etc.) and save it to the storage file corresponding to the information;

[0094] The main function part is used to process the execution order of the above functions and the overall execution logic. In some embodiments, the psu_static_info_snmpget function part and the psu_dynamic_info_snmpget function part can obtain the relevant information of the PSU of the second server through the same format instructions. Similarly, the psu_static_info_redfishget function part and the psu_dynamic_info_redfishget function part can obtain the relevant information of the PSU of the second server through the same format instructions.

[0095] It should be noted that the above-mentioned SNMP and Redfish communication interfaces in the embodiment of the present application are only examples. In the specific implementation, the present application is not limited to the above-mentioned two types of communication interfaces. Other communication interfaces between the first server and the second server can also be used to obtain relevant information of the PSU in the second server and execute the fault warning method.

[0096] The cluster analysis script is used to analyze the collected PSU related information based on the clustering algorithm, identify abnormal data, and implement fault warning and location.

[0097] In some embodiments, the cluster analysis script includes: a data_average function for calculating the average values ​​of multiple data; a data_center function for calculating the center points of multiple data; and pre-configured threshold distances, whose values ​​represent the distance limit from the pre-configured average value to the center point.

[0098] Access list: A user name access list configured based on a fixed format. The list includes at least the pre-configured identification and login information of each server to be detected. The login information includes the IP address, login username, and login password of the corresponding server to be detected. The format can be set based on demand, such as setting the format to: server IP address; login username; login password; and each server to be detected occupies one line. It should be noted that the information in the access list supports users to add, modify, and delete in real time to meet the needs of various scenarios and businesses.

[0099] In some embodiments, the fault warning method in the present application needs to meet the following operating environment requirements: the server to be detected (the second server) and the operation and maintenance server (the first server) need to be located in the same local area network, and the operation and maintenance server can access each server to be detected through the network so as to obtain relevant information of the PSU from each server to be detected. The operation and maintenance server is configured with the system and environment required for the fault warning method, such as a Linux system, a telnet tool, and a python environment.

[0100] In combination with the above-mentioned implementation tools, the working principle of the fault warning method provided in the embodiment of the present application is: first, the first server and each second server are configured in a local area network, an operation and maintenance environment is deployed on the first server, and a system corresponding to the fault warning method is installed, such as a Linux system with a telnet tool and a python environment, and an access list is configured on the first server, and the IP address, login user name, login password and other information of each server to be detected are stored in the access list; then, a connection is established between the first server and each second server through the network, and the first server uses the telnet tool and the oid command of the Linux system to obtain relevant information of the PSU from each second server. Finally, information verification and clustering algorithms are used to perform data analysis on the obtained relevant information to achieve fault warning and preliminary positioning. In addition, the method only needs to be deployed once during the operation of the first server and each second server, and only needs to receive the feedback results from the second server to achieve the fault warning function of the PSU.

[0101] The present application is further described in detail below in conjunction with the accompanying drawings. Figure 1 FIG. 1 is a flow chart of a fault warning method provided in an embodiment of the present application. The method is applied to a first server, and the specific implementation process is as follows:

[0102] Step S101, in response to an instruction to perform fault detection on a power supply unit PSU in a second server, obtaining status information of the PSU in the second server through a plurality of communication interfaces with the second server at intervals of a first preset period;

[0103] In some embodiments, the above indication may be generated by a user through a touch operation on the interface of the first server. The trigger operation may be click, input, drag, etc., which is not limited in the embodiments of the present application.

[0104] In some embodiments, the present application is pre-configured with an access list that stores the identification and login information of each server to be detected, and the login information includes information such as the IP address, login username, and login password of the corresponding server to be detected; the user identification can be set based on demand, such as using the login username in the login information as the identification of the server; the user can configure the information in the access list and store the login information of each server that needs to be fault-detected in the list, so as to facilitate the subsequent establishment of a network connection between servers based on the login information.

[0105] In some embodiments, after responding to the instruction to detect a fault on the power supply unit PSU in the second server and before respectively obtaining the status information of the PSU in the second server, it is also necessary to perform:

[0106] Based on the identifier of the second server and the access list, determine that the second server belongs to the server to be detected, and obtain the target login information of the second server from the access list;

[0107] A network connection is established between the first server and the second server based on the target login information.

[0108] Possibly, when the identifier of the second server exists in the access list, it can be determined that the second server is the server that needs to be fault-detected, and the login information of the server is pre-configured, and a network connection relationship between the first server and the second server can be established subsequently based on the login information; if the identifier of the second server does not exist, it can be determined that the login information of the server is not configured, and a prompt message can be sent to the user at this time, prompting him or her whether to add the login information of the second server to the access list, or to cancel the fault detection of the second server.

[0109] In some embodiments, after the network connection between the first server and the second server is established, data transmission or message feedback can be used to detect whether the first server and the second server are connected again.

[0110] Possibly, the state data of the PSU may include at least one of core temperature, ambient temperature, input voltage, output voltage, input current, output current, input power, output power, fan load and fan speed. The value of the first preset period may be set based on demand, for example, set to 6 minutes.

[0111] Step S102, comparing the status information obtained through each communication interface, and when it is determined that the comparison result meets the first preset condition, storing each status information in a first storage file;

[0112] In some embodiments, the first preset condition may be: the difference between the same state information obtained through each communication interface is within a first preset value range; the first preset value range may be set based on demand.

[0113] Specifically, if the status information includes multiple parameters, the above process of comparing the status information is: for any parameter, determine the difference between the parameters obtained through each communication interface, and determine whether the difference is within the first preset value range corresponding to the parameter. It should be noted that if the status information includes multiple parameters, a first preset value range corresponding to each parameter can be set, and the values ​​of the first preset value ranges between different parameters can be the same or different.

[0114] Possibly, when the number of the above-mentioned multiple communication interfaces is greater than two, when determining the difference between the same state information obtained by each communication interface, the state information obtained by each two communication interfaces is subtracted; when determining whether the difference between the same state information obtained through each communication interface is within a first preset value range, if the maximum value of the multiple differences corresponding to the same state information is within the first preset value range, it is determined that the first preset condition is met; otherwise, it is determined that the first preset condition is not met.

[0115] In some embodiments, if the comparison result does not meet the first preset condition, the following operations are performed:

[0116] At intervals of a third preset period, the following operations are cyclically performed until the comparison result meets the first preset condition, or the number of cycles reaches a preset threshold: respectively obtaining status information of the PSU in the second server through multiple communication interfaces with the second server; comparing the status information obtained through each communication interface, and determining whether the comparison result meets the first preset condition;

[0117] If the loop is executed until the comparison result meets the first preset condition, each state information obtained in the last loop is stored in the first storage file.

[0118] Possibly, the value of the third preset period may be set based on demand, and in some embodiments, may be set to be the same as the value of the first preset period.

[0119] In a specific implementation, when the comparison result does not meet the first preset condition, the above comparison process is executed repeatedly. If the comparison result meets the first preset condition before the number of cycles reaches the preset threshold, it can be considered that there is no abnormality in the status information of the PSU, and the status information obtained in the last cycle is stored in the first storage file. At this time, a corresponding record log can be generated based on the status information obtained in multiple cycles and the comparison results, and reported for subsequent query reference.

[0120] If the loop is executed to the preset threshold and the comparison result still does not meet the first preset condition, it can be determined that there is an abnormality in the status information of the PSU, and a fault warning is triggered.

[0121] In some embodiments, when storing each state information in the first storage file, an average value can be calculated for each state information and the average value can be stored in the first storage file. It should be noted that if the state information includes multiple parameters, the first storage file needs to be divided into different areas according to the parameters to store the data corresponding to different parameters separately, so as to facilitate subsequent clustering.

[0122] In some embodiments, the status information in the first storage file may be aligned in a timestamp (storage time) manner to avoid data confusion.

[0123] In some embodiments, after responding to an indication of fault detection of a power supply PSU in the second server, attribute information of the PSU in the second server can also be obtained every fourth preset period; the attribute information includes at least one of a serial number, a product name, a part number, a firmware version, a manufacturer, and a production date.

[0124] In a specific implementation, when the attribute information is obtained for the first time, the attribute information of the PSU in the second server is obtained respectively through multiple communication interfaces with the second server; except for the first time, the attribute information of the PSU in the second server is obtained through any communication interface.

[0125] In some embodiments, after acquiring the attribute information for the first time, it is necessary to compare the attribute information acquired through each communication interface. When it is determined that the comparison result meets the second preset condition, any attribute information is stored in the second storage file; except for the first time, after acquiring the attribute information of the PSU in the second server through any communication interface, it can be directly stored in the second storage file.

[0126] Possibly, the second preset condition is that the same attribute information obtained through each communication interface is consistent; if the attribute information includes multiple parameters, the second preset condition is that for any parameter, the value of the parameter obtained through each communication interface is consistent.

[0127] In some embodiments, if the comparison result does not meet the second preset condition, the following operations are performed:

[0128] At every fifth preset period, the following operations are cyclically performed until the comparison result meets the second preset condition, or the number of cycles reaches a preset threshold (the set threshold can be set to be different from the threshold value of the state parameter, for example, set to 2 times): through multiple communication interfaces with the second server, respectively obtain the attribute information of the PSU in the second server; compare the attribute information obtained through each communication interface, and determine whether the comparison result meets the second preset condition;

[0129] If the loop is executed until the comparison result meets the second preset condition, any attribute information obtained in the last loop will be stored in the second storage file; if the loop is executed to the preset threshold and the comparison result still does not meet the second preset condition, it can be determined that there is an abnormality in the attribute information of the PSU, and a fault warning is triggered.

[0130] Possibly, the value of the fifth preset period may be set based on demand, and in some embodiments, may be set to be the same as the value of the fourth preset period.

[0131] In some embodiments, the attribute information in the second storage file may be aligned in a timestamp (storage time) manner to avoid data confusion.

[0132] In some embodiments, the multiple communication interfaces between the first server and the second server may be SNMP interfaces and Redfish interfaces; the value of the fourth preset period may be set based on demand, for example, set to 60 minutes.

[0133] Step S103: clustering the status information included in the first storage file at intervals of a second preset period, and determining whether the PSU is abnormal based on the clustering result.

[0134] In some embodiments, since the PSU health data (data corresponding to the same parameter) should be concentrated near a central point after multiple collections, rather than randomly and disorderly arranged, a central point can be determined based on the historical data of the normal operation of the PSU, and then the multiple collected data can be clustered based on the central point, that is, the distance between the real-time collected data and the central point is determined. The farther the distance, the worse the health status. Conversely, the closer the distance, the healthier the health status. The health threshold can be set to the distance between the average value of the historical data and the central data point, or other forms, for early warning. Furthermore, the fault location can be specifically determined based on the abnormal or outlier data to achieve the purpose of reducing the fault location.

[0135] In some embodiments, the clustering process of the present application can be implemented based on clustering algorithms such as the k-means clustering algorithm or the K-medoids clustering algorithm (preferred).

[0136] In some embodiments, if a second storage file is configured, before clustering the status information in the first storage file, it is also necessary to cluster the attribute information included in the second storage file, and determine whether there is any abnormality in the attribute information of the PSU based on the clustering result.

[0137] In a specific implementation, since the attribute information generally does not change, when clustering the attribute information, the center point corresponding to the attribute parameter can be pre-set, and the distance threshold can be set to 0 or a smaller value. Then, based on the distance between each attribute information and the center point, the attribute information whose distance is less than the distance threshold is filtered out from the attribute information to generate a cluster corresponding to the center point; if the attribute information does not include attribute information that is not located in each cluster, it is determined that there is no abnormality in the attribute information of the PSU, and the subsequent steps can be executed, that is, clustering the various status information included in the first storage file.

[0138] If each attribute information includes attribute information that is not located in each cluster, it is determined that the attribute information of the PSU is abnormal. At this time, the attribute information of the PSU can be obtained again through multiple communication interfaces connected to the second server, and compared to verify whether the attribute information of the PSU is abnormal in a double way. If it is determined that the comparison results are inconsistent, or any attribute information obtained again is inconsistent with the center point, the corresponding fault alarm is triggered; otherwise, it is determined that there is no abnormality in the attribute information of the PSU.

[0139] In some embodiments, the above-mentioned first server includes at least one reference center point (corresponding to the status information). When clustering the status information included in the first storage file, for each reference center point, based on the distance between each status information and the reference center point, the status information whose distance is less than a preset distance threshold is filtered out from the status information, and a cluster cluster corresponding to the reference center point is generated; if each status information includes status information that is not located in each cluster cluster, it is determined that there is an abnormality in the PSU.

[0140] In a specific implementation, the number of the above-mentioned reference center points is consistent with the number of parameters included in the status information, that is, each parameter corresponds to a reference center point; if the status information includes multiple parameters, then when performing clustering, a possible implementation method is, for each reference center point, to filter out candidate information corresponding to the reference center point from each state information in the first storage file, and based on the distance between each candidate information and the reference center point, to filter out candidate information whose distance is less than a preset distance threshold from each candidate information, to generate a clustering cluster corresponding to the reference center point.

[0141] In some embodiments, if the current clustering operation is the first operation, the reference center point is a pre-configured initial center point; if the current clustering operation is not the first operation, the reference center point is determined based on the following method: for each cluster generated in the last clustering operation, the sum of the distances between each state information included in the cluster and other state information is determined; based on the sum of the distances corresponding to each state information, the reference center point is filtered out from the multiple state information included in the cluster.

[0142] In a specific implementation, when screening the reference center point, the state information with the smallest sum of corresponding distances in each state information may be used as the reference center point.

[0143] In some embodiments, the initial center point is determined based on the following method:

[0144] Obtain each historical status information of the PSU, determine the distance between each historical status information and other historical status information respectively, and sum up each distance to obtain a reference value corresponding to the historical status information; based on the reference value corresponding to each historical status information, determine a candidate center point from each historical status information; if the difference between the candidate center point and the average value of each historical status information is within a second preset value range, use the candidate center point as the initial center point.

[0145] In some embodiments, if the difference between the candidate center point and the average value of each historical state information is not within the second preset value range, it means that the selection of historical state information is inappropriate. At this time, the historical state information is re-acquired and the above process is performed based on the acquired historical state information.

[0146] It should be noted that the above historical status information is obtained when the PSU is operating normally, and the above second preset value range can be set based on demand.

[0147] In one possible implementation, if it is determined that the PSU has an abnormality, a fault alarm is triggered, and relevant personnel can be reminded to perform fault repair by generating a fault log and reporting it, or by various means such as an alarm reminder. Possibly, different levels of alarm mechanisms can also be set based on the number of abnormal data, such as the number of status information that is not located in the cluster, and the number of attribute information that is not located in the cluster. For example, if the number is lower than a first value, a fault alarm is issued by way of a message reminder; if the number is not lower than the first value but lower than the second value, a fault alarm is issued by way of an alarm reminder; and if the number is higher than the second value, some functions of the second server are directly suspended to avoid greater losses.

[0148] The above method obtains status information based on multiple communication interfaces respectively, and performs data analysis based on a clustering algorithm, thereby realizing all-round monitoring of the PSU status on the second server, and performing fault warning by calculating the distance between real-time data and healthy data, thereby improving the efficiency and accuracy of fault detection. At the same time, the present application supports capacity expansion based on the premise of being deployed, and can achieve online capacity expansion without affecting the first server and each second server, thus meeting the needs of a small data center, and is particularly suitable for scenarios such as server testing manufacturers. In addition, the present application can be adapted to scenarios where a second server includes multiple PSUs, and a data reading method based on a single PSU can be added, supporting a first server to detect and warn the information of multiple PSUs on multiple second servers, greatly improving the efficiency and quality of operation and maintenance, and saving a lot of labor costs and time consumption.

[0149] The following combination Figure 2 The above fault warning process is described in detail with a specific example. The process specifically includes the following steps:

[0150] Step S201, configuring the first server and the second server in a local area network, and configuring a Linux system, a telnet tool and a python environment in the first server;

[0151] Step S202, determining whether the first server is connected to the second server, if so, it means that the second server can be logged in through the local area network to obtain relevant data, and then executing step S203, if not, it means that the second server cannot be accessed, and executing step S208;

[0152] Step S203, calling the psu_static_info_snmpget function part or the psu_static_info_redfishget function part to obtain the attribute information of the PSU in the second server, and storing it in the second storage file;

[0153] It should be noted that the acquisition method given in the above step S203 is a method for acquiring attribute information other than the first time. When the acquisition process is the first time, it is necessary to call the psu_static_info_snmpget function part and the psu_static_info_redfishget function part to respectively acquire the attribute information of the PSU, and input the attributes acquired by the two methods into the data_comparison function part. After being parsed by the function, they are compared one by one. If the comparison is consistent, the next step is performed. If it is inconsistent, the information is acquired again to perform the comparison process. If it is repeated until the preset threshold is still inconsistent, an early warning signal is generated for reporting. The specific process can be found in the above step S102, which will not be repeated here.

[0154] Step S204, calling the psu_dynamic_info_snmpget function part and the psu_dynamic_info_redfishget function part to respectively obtain the status information of the PSU in the second server;

[0155] Step S205, calling the data_comparison function to compare the state information obtained in the two ways, and if the comparison result meets the first preset condition, storing the average value of the state information in the first storage file;

[0156] Specifically, the average value of the status information is first stored in the specified array, and then the data_collect function is called to save the data in the array into the first storage file;

[0157] It should be noted that the present application does not limit the execution order of the above-mentioned step S203 and step S204-205, and step S204-205 may be executed first, and then step S203.

[0158] Step S206, based on the cluster analysis script, performing cluster analysis on the information in the first storage file and the second storage file respectively;

[0159] The specific process can be found in the above step S103, which will not be described again here.

[0160] Step S207, determine whether the PSU is abnormal based on the clustering result, if so, execute step S208; if not, execute step S209.

[0161] Step S208, triggering a fault alarm.

[0162] Step S209, end fault detection.

[0163] Based on the same inventive concept, the present application also provides a fault warning device, see Figure 3 , the device comprises:

[0164] The acquisition module 301 is used for, in response to an instruction to perform fault detection on a power supply unit PSU in the second server, acquiring status information of the PSU in the second server through a plurality of communication interfaces with the second server at intervals of a first preset period;

[0165] The comparison module 302 is used to compare the above-mentioned state information obtained through each communication interface, and when it is determined that the comparison result meets the first preset condition, store each state information in a first storage file;

[0166] The determination module 303 is used to cluster the status information included in the first storage file at intervals of a second preset period, and determine whether the PSU is abnormal based on the clustering result.

[0167] In a possible implementation manner, the first preset condition is: the difference between the same state information obtained through each communication interface is within a first preset value range;

[0168] If the comparison result does not meet the first preset condition, the comparison module 302 is further configured to:

[0169] At intervals of a third preset period, the following operations are cyclically performed until the comparison result satisfies the first preset condition or the number of cycles reaches a preset threshold: respectively obtaining the status information of the PSU in the second server through the multiple communication interfaces between the second server and the second server; comparing the status information obtained through each communication interface, and determining whether the comparison result satisfies the first preset condition;

[0170] If the comparison result is executed in a loop until it satisfies the first preset condition, each state information obtained in the last loop is stored in the first storage file.

[0171] In a possible implementation manner, after responding to an instruction to perform fault detection on the power supply unit PSU in the second server, the acquisition module 301 is further configured to:

[0172] Obtaining attribute information of the PSU in the second server respectively through a plurality of communication interfaces with the second server;

[0173] Compare the attribute information obtained through each communication interface, and when it is determined that the comparison result meets the second preset condition, store any attribute information in the second storage file; and obtain the attribute information of the PSU in the second server through any communication interface and store it in the second storage file at intervals of a fourth preset period;

[0174] Before clustering the state information included in the first storage file, the determination module 303 is further used to:

[0175] Clustering is performed on each piece of attribute information included in the second storage file, and based on the clustering result, it is determined that there is no abnormality in the attribute information of the PSU.

[0176] In a possible implementation manner, the first server includes at least one reference center point, and the determination module 303 is specifically configured to:

[0177] For each reference center point, based on the distance between each state information and the reference center point, the state information whose distance is less than a preset distance threshold is screened out from the state information, and a cluster corresponding to the reference center point is generated;

[0178] If the above-mentioned state information includes state information that is not located in each cluster, it is determined that the above-mentioned PSU is abnormal.

[0179] In a possible implementation, if the current clustering operation is the first operation, the reference center point is a pre-configured initial center point; if the current clustering operation is not the first operation, the reference center point is determined based on the following method:

[0180] For each cluster generated in the last clustering operation, respectively determine the sum of the distances between each state information included in the cluster and other state information;

[0181] Based on the sum of the distances corresponding to the respective state information, a reference center point is selected from the plurality of state information included in the cluster.

[0182] In a possible implementation manner, the initial center point is determined based on the following method:

[0183] Obtaining each historical status information of the PSU, determining the distance between each historical status information and other historical status information respectively, and summing up each distance to obtain a reference value corresponding to the historical status information;

[0184] Determine a candidate center point from each of the historical state information based on the reference values ​​corresponding to each of the historical state information;

[0185] If the difference between the candidate center point and the average value of each historical state information is within a second preset value range, the candidate center point is used as the initial center point.

[0186] In a possible implementation manner, after responding to an instruction to perform fault detection on the power supply PSU in the second server and before respectively acquiring status information of the PSU in the second server, the acquisition module 301 is further configured to:

[0187] Based on the identification and access list of the second server, determine that the second server belongs to the server to be detected, and obtain the target login information of the second server from the access list; the access list stores the identification and login information of each server to be detected;

[0188] A network connection is established between the first server and the second server based on the target login information.

[0189] Based on the same inventive concept, an electronic device is also provided in the embodiment of the present application, and the electronic device can realize the function of the aforementioned fault warning device, referring to Figure 4 , the electronic device comprises:

[0190] At least one processor 401, and a memory 402 connected to the at least one processor 401. The specific connection medium between the processor 401 and the memory 402 is not limited in the embodiment of the present application. Figure 4 In the example, the processor 401 and the memory 402 are connected via the bus 400. The bus 400 is Figure 4 The connection between other components is shown by bold lines, and is not intended to be limiting. The bus 400 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 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. Alternatively, the processor 401 can also be called a controller, and there is no limitation on the name.

[0191] In the embodiment of the present application, the memory 402 stores instructions that can be executed by at least one processor 401. The at least one processor 401 can execute the fault warning method discussed above by executing the instructions stored in the memory 402. The processor 401 can implement Figure 3 The functions of each module in the device shown.

[0192] Among them, the processor 401 is the control center of the device, and can use various interfaces and lines to connect the various parts of the entire control device. By running or executing instructions stored in the memory 402 and calling the data stored in the memory 402, the various functions of the device and process data, the device can be monitored as a whole.

[0193] In one possible design, the processor 401 may include one or more processing units, and the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the modem processor may not be integrated into the processor 401. In some embodiments, the processor 401 and the memory 402 may be implemented on the same chip, and in some embodiments, they may also be implemented separately on separate chips.

[0194] Processor 401 can be a general-purpose processor, such as a central processing unit (CPU), a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the fault warning method disclosed in the embodiments of the present application can be directly embodied as a hardware processor to be executed, or a combination of hardware and software modules in the processor can be executed.

[0195] The memory 402 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The memory 402 may include at least one type of storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory, a random access memory (Random Access Memory, RAM), a static random access memory (Static Random Access Memory, SRAM), a programmable read-only memory (Programmable Read Only Memory, PROM), a read-only memory (Read Only Memory, ROM), an electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), a magnetic memory, a disk, an optical disk, etc. The memory 402 is any other medium that can be used to carry or store a desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 402 in the embodiment of the present application can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0196] By designing and programming the processor 401, the code corresponding to the application anomaly detection method described in the above embodiment can be fixed into the chip, so that the chip can execute the code when running. Figure 1 The steps of the fault warning method of the embodiment shown are as follows: How to design and program the processor 401 is a technique known to those skilled in the art and will not be described in detail here.

[0197] An embodiment of the present application also provides a computer-readable storage medium that stores computer-executable instructions required to execute the above-mentioned processor, which includes a program required to execute the above-mentioned processor.

[0198] In some possible implementations, various aspects of the fault warning method provided in the present application may also be implemented in the form of a program product, which includes a program code. When the above-mentioned program product is run on an electronic device, the above-mentioned program code is used to enable the above-mentioned electronic device to execute the steps of the fault warning method according to various exemplary implementations of the present application described above in this specification.

[0199] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, devices, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt 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.) that contain computer-usable program code.

[0200] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (apparatus), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 generate 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.

[0201] 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 including 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.

[0202] 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.

[0203] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0204] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A fault warning method, characterized in that: Applied to a first server, the method comprises: In response to an instruction to detect a fault of a power supply unit (PSU) in a second server, obtaining status information of the PSU in the second server through a plurality of communication interfaces with the second server at intervals of a first preset period; Comparing the state information obtained through each communication interface, and storing each state information in a first storage file when it is determined that the comparison result meets a first preset condition; At intervals of a second preset period, each state information included in the first storage file is clustered, and whether the PSU is abnormal is determined based on the clustering result.

2. The method according to claim 1, characterized in that The first preset condition is that the difference between the same state information obtained through each communication interface is within a first preset value range; If the comparison result does not meet the first preset condition, the method further includes: At intervals of a third preset period, the following operations are cyclically performed until the comparison result meets the first preset condition, or the number of cycles reaches a preset threshold: respectively obtaining status information of the PSU in the second server through multiple communication interfaces with the second server; comparing the status information obtained through each communication interface, and determining whether the comparison result meets the first preset condition; If the loop is executed until the comparison result meets the first preset condition, each state information obtained in the last loop is stored in the first storage file.

3. The method according to claim 1, characterized in that After responding to the indication of detecting a fault in the power supply unit (PSU) in the second server, the method further comprises: Obtaining attribute information of the PSU in the second server respectively through a plurality of communication interfaces with the second server; Compare the attribute information obtained through each communication interface, and when it is determined that the comparison result meets the second preset condition, store any attribute information in the second storage file; and obtain the attribute information of the PSU in the second server through any communication interface and store it in the second storage file at intervals of a fourth preset period; Before clustering each state information included in the first storage file, the method further includes: Clustering is performed on each piece of attribute information included in the second storage file, and based on the clustering result, it is determined that there is no abnormality in the attribute information of the PSU.

4. The method according to claim 1, characterized in that: The first server includes at least one reference center point, and clustering each state information included in the first storage file includes: For each reference center point, based on the distance between each state information and the reference center point, the state information whose distance is less than a preset distance threshold is screened out from the state information, and a cluster corresponding to the reference center point is generated; The determining whether the PSU is abnormal based on the clustering result includes: If the various status information include status information that is not located in each cluster, it is determined that the PSU is abnormal.

5. The method according to claim 4, characterized in that If the current clustering operation is the first operation, the reference center point is a pre-configured initial center point; if the current clustering operation is not the first operation, the reference center point is determined based on the following method: For each cluster generated in the last clustering operation, respectively determine the sum of the distances between each state information included in the cluster and other state information; Based on the sum of the distances corresponding to the respective state information, a reference center point is screened out from the plurality of state information included in the cluster.

6. The method according to claim 5, characterized in that The initial center point is determined based on the following method: Acquire each historical status information of the PSU, determine the distance between each historical status information and other historical status information respectively, and sum each distance to obtain a reference value corresponding to the historical status information; Determining a candidate center point from each piece of historical state information based on reference values ​​corresponding to each piece of historical state information; If the difference between the candidate center point and the average value of each historical state information is within a second preset value range, the candidate center point is used as the initial center point.

7. The method according to any one of claims 1 to 6, characterized in that: After responding to the indication of detecting a fault of the power supply unit PSU in the second server and before respectively acquiring status information of the PSU in the second server, the method further includes: Based on the identifier of the second server and the access list, determine that the second server belongs to the server to be detected, and obtain the target login information of the second server from the access list; the access list stores the identifier and login information of each server to be detected; A network connection is established between the first server and the second server based on the target login information.

8. A fault warning device, characterized in that: Applied to a first server, the device comprises: an acquisition module, configured to, in response to an instruction to perform fault detection on a power supply unit PSU in a second server, respectively acquire status information of the PSU in the second server through a plurality of communication interfaces with the second server at intervals of a first preset period; A comparison module, used for comparing the state information obtained through each communication interface, and storing each state information in a first storage file when it is determined that the comparison result meets a first preset condition; The determination module is used to cluster the status information included in the first storage file at intervals of a second preset period, and determine whether the PSU is abnormal based on the clustering result.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to implement the method according to any one of claims 1 to 7 when executing a computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images