Data center monitoring system, device, medium and program product

Abstract

The invention provides a data center monitoring system which can be applied to the technical field of big data and artificial intelligence. The data center monitoring system comprises a user-defined monitoring item module which is used for providing a graphical configuration interface and enabling a user to add, edit or delete monitoring items in a user-defined mode; the automatic sensing module is used for scanning a target network through an address resolution protocol, judging whether new monitored equipment exists or not, responding to the detected new monitored equipment, and automatically triggering a new monitored equipment identification process; the data acquisition module is used for generating and executing an acquisition task according to the monitoring item; the intelligent operation and maintenance module is used for performing early warning by using the monitoring item prediction model and the equipment prediction model, and generating a safety setting interval of the configuration item in response to the occurrence of monitoring item early warning; and the three-dimensional machine room display module is used for generating a three-dimensional model according to the distribution of the monitored equipment. The invention further provides data center monitoring system equipment, a medium and a program product.

Description

Technical Field

[0001] This application relates to the fields of big data and artificial intelligence technologies, and more specifically to a data center monitoring system, equipment, media, and program products. Background Technology

[0002] With the rapid development of information technology, the scale and complexity of data centers are constantly increasing. Data centers contain a large number of critical facilities such as servers, storage devices, and network equipment, and the stable operation of these devices is crucial for the normal functioning of the data center. To ensure the efficient operation of the data center, it is necessary to monitor the operating status of various devices in real time.

[0003] While existing data center monitoring systems can monitor common equipment parameters such as temperature, humidity, CPU utilization, and memory utilization, they have significant limitations when facing increasingly diverse business needs and constantly evolving equipment types. On one hand, existing monitoring systems have relatively fixed monitoring items, making it difficult to quickly add new items based on the specific needs of different data centers. For example, when a data center introduces new energy-saving equipment or servers with special performance indicators, existing systems cannot easily monitor the key parameters of these new devices. On the other hand, different data centers have different focuses on monitoring indicators due to differences in business priorities and equipment configurations. Some data centers may be more concerned with network transmission latency and packet loss rate, while others may place greater emphasis on the I / O performance of storage devices. Existing general-purpose monitoring systems cannot adequately meet these personalized monitoring needs.

[0004] Therefore, developing a data center monitoring system that allows users to customize and extend monitoring items according to their own needs is of great practical significance. Summary of the Invention

[0005] In view of the above problems, embodiments of this application provide a data center monitoring system, device, media, and program product that can improve scalability and personalization.

[0006] According to the first aspect of this application, a data center monitoring system is provided, comprising: a custom monitoring item module for providing a graphical configuration interface, allowing users to add, edit, or delete monitoring items in response to user operations, wherein the monitoring item includes at least the device category, device number, monitoring item name, data source, data acquisition frequency, data processing algorithm, and data alarm threshold of the monitored device; an automatic sensing module for scanning the target network via address resolution protocol to determine whether a new monitored device exists, and automatically triggering a new monitored device identification process in response to the detection of a new monitored device; a data acquisition module for generating and executing acquisition tasks based on the monitoring items, wherein the acquisition tasks are used to acquire monitoring data from a specified data source; an intelligent operation and maintenance module for providing early warnings using a pre-trained monitoring item prediction model and a pre-trained device prediction model, and generating a security setting range for configuration items associated with the monitoring item in response to a monitoring item early warning, wherein the monitoring item prediction model and the device prediction model are constructed based on a long short-term memory network model; and a three-dimensional data center display module for generating a three-dimensional model based on the distribution of the monitored devices, wherein the three-dimensional model displays at least the basic information and status information of the monitored devices.

[0007] According to an embodiment of this application, using a pre-trained device prediction model for early warning includes: acquiring all monitoring items of the monitored device to generate a first monitoring item set; calculating the mutual information value between each monitoring item in the first monitoring item set and the device anomaly based on a mutual information algorithm, wherein the mutual information value represents the degree of correlation between the monitoring item and the device anomaly, and the higher the mutual information value, the greater the correlation; based on the mutual information value, selecting monitoring items related to the device anomaly from the first monitoring item set to generate a second monitoring item set; calculating the correlation degree between monitoring items in the second monitoring item set based on the Spearman rank correlation coefficient, wherein the correlation degree is used to represent the strength of the relationship between monitoring items; in response to identifying a monitoring item group with a correlation degree greater than a preset threshold, selecting the monitoring item with the highest mutual information value with the device anomaly from the monitoring item group to generate a third monitoring item set; inputting the historical time series monitoring data of the third monitoring item set into the pre-trained device prediction model to obtain a device anomaly prediction probability value, wherein the device prediction model is constructed based on a long short-term memory network model; and issuing an early warning in response to the device anomaly prediction probability value being greater than a preset alarm threshold.

[0008] According to an embodiment of this application, using a pre-trained monitoring item prediction model for early warning includes: inputting historical time series monitoring data of the monitoring item into the pre-trained monitoring item prediction model to obtain a prediction result, wherein the monitoring item prediction model is generated based on a long short-term memory network model; and issuing an early warning in response to the prediction result being greater than a data alarm threshold.

[0009] According to an embodiment of this application, in response to a monitoring item warning, generating a security setting range for configuration items associated with the monitoring item includes: acquiring all configuration items of the monitored device and generating a first configuration item set; in response to a monitoring item warning, using a mutual information algorithm to calculate the mutual information value between the monitoring item and each configuration item in the first configuration item set; based on the mutual information value, filtering out a second configuration item set associated with the monitoring item; acquiring the historical normal setting value of each configuration item in the second configuration item set; calculating the mean and standard deviation based on the historical normal setting value of each configuration item; and generating a security setting range for the configuration item according to a preset rule based on the mean and standard deviation of each configuration item.

[0010] According to an embodiment of this application, the data acquisition task for obtaining monitoring data from a specified data source includes: in response to obtaining a data packet from the specified data source, performing protocol matching on the data packet using a pre-built protocol parsing database, wherein the protocol parsing database contains multiple protocol parsing plugins for parsing different protocols, wherein each protocol parsing plugin corresponds to a communication protocol; in response to successful protocol matching, using the successfully matched protocol parsing plugin to parse the data packet to obtain monitoring data.

[0011] According to an embodiment of this application, in response to the detection of a new monitored device, the automatic triggering of the new monitored device identification process includes: pre-setting multiple device categories, wherein each device category corresponds to a device type; pre-setting at least one initial monitoring item under each device category; in response to the detection of a new monitored device accessing the network, automatically matching the device category of the new monitored device; in response to the successful matching of the device category, obtaining the initial monitoring item under the device category; and monitoring the new monitored device according to the initial monitoring item.

[0012] According to embodiments of this application, scanning a target network using Address Resolution Protocol (ARP) to determine whether a new monitored device exists includes: maintaining a list of known devices on the target network, wherein the list of known devices contains the network protocol addresses and corresponding media access control addresses of known devices; sending an ARP request to the target network according to a preset broadcast triggering policy; in response to a response message indicating the existence of an ARP request, parsing and obtaining the network protocol address and corresponding media access control address of the response message; comparing the current device identified by the target network protocol address and the corresponding media access control address with the list of known devices; and in response to the existence of a device not recorded in the list of known devices, identifying the device as a new device and updating the list of known devices.

[0013] According to an embodiment of this application, sending an address resolution protocol request to a target network according to a preset broadcast triggering strategy includes: detecting changes in the power parameters of at least one target socket in real time through an intelligent power distribution unit; and sending an address resolution protocol request to the target network in response to detecting changes in the power parameters of the target socket.

[0014] According to an embodiment of this application, the system further includes: a data processing module, used to process data based on the data processing algorithm in the monitoring item to obtain processed monitoring data; a process approval module, used for the application review process for new monitored devices and the application review process for pre-embedded monitored devices, wherein the application for pre-embedded monitored devices is an application for the early inclusion of monitored devices; a data storage module, used to store the data generated by each module; and a monitoring display module, used to display the monitoring data of the monitoring item, and to generate and display alarm information in response to the data alarm threshold triggered by the monitoring data of the monitoring item.

[0015] A second aspect of this application provides an electronic device, comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the system described above.

[0016] A third aspect of this application also provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a processor, implement the system described above.

[0017] A fourth aspect of this application also provides a computer program product, including a computer program or instructions that, when executed by a processor, implement the system described above. Attached Figure Description

[0018] The above-mentioned contents, as well as other objects, features, and advantages of this application, will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0019] Figure 1 The illustrations depict application scenarios of data center monitoring systems, devices, media, and program products according to embodiments of this application.

[0020] Figure 2 The schematic diagram illustrates the structure of a data center monitoring system according to an embodiment of this application;

[0021] Figure 3 A flowchart illustrating the process of determining a new monitored device according to an embodiment of this application is shown schematically;

[0022] Figure 4 A flowchart illustrating the device identification process according to an embodiment of this application is shown schematically.

[0023] Figure 5 A flowchart illustrating the setting of a security setting range according to an embodiment of this application is shown schematically;

[0024] Figure 6 A flowchart illustrating a device warning according to an embodiment of this application is shown schematically;

[0025] Figure 7 This illustration schematically shows another structural diagram of a data center monitoring system according to an embodiment of the present application; and

[0026] Figure 8 A block diagram of an electronic device suitable for implementing a data center monitoring system according to an embodiment of this application is illustrated schematically. Detailed Implementation

[0027] The embodiments of this application will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of this application. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of this application for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concepts of this application.

[0028] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0029] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0030] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0031] This application provides a data center monitoring system, comprising: a custom monitoring item module for providing a graphical configuration interface, allowing users to add, edit, or delete monitoring items in response to user operations, wherein the monitoring item includes at least the device category, device number, monitoring item name, data source, data acquisition frequency, data processing algorithm, and data alarm threshold of the monitored device; an automatic sensing module for scanning the target network via address resolution protocol to determine whether a new monitored device exists, and automatically triggering a new monitored device identification process in response to the detection of a new monitored device; a data acquisition module for generating and executing acquisition tasks based on the monitoring items, wherein the acquisition tasks are used to acquire monitoring data from a specified data source; an intelligent operation and maintenance module for providing early warnings using a pre-trained monitoring item prediction model and a pre-trained device prediction model, and generating a security setting range for configuration items associated with the monitoring item in response to a monitoring item early warning, wherein the monitoring item prediction model and the device prediction model are constructed based on a long short-term memory network model; and a three-dimensional data center display module for generating a three-dimensional model based on the distribution of the monitored devices, wherein the three-dimensional model displays at least the basic information and status information of the monitored devices. In this way, users can expand the monitoring items they need with simple configuration. This solves the problem that existing data center monitoring systems have fixed monitoring items and cannot meet personalized monitoring needs. It achieves comprehensiveness and flexibility in data center monitoring and can save on the cost of custom development of data center monitoring systems by customizing monitoring items.

[0032] Figure 1 The illustration shows an application scenario diagram of a data center monitoring system, device, media, and program product according to an embodiment of this application.

[0033] like Figure 1 As shown, application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0034] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0035] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0036] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0037] It should be noted that the data center monitoring system provided in the embodiments of this application can generally be configured in server 105. The data center monitoring system provided in the embodiments of this application can also be configured in a server or server cluster that is different from server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or server 105.

[0038] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0039] The following will be based on Figure 1 The described scene, through Figures 2-7 A data center monitoring system according to embodiments of this application will be described in detail.

[0040] Figure 2 The schematic diagram illustrates the structure of a data center monitoring system according to an embodiment of this application.

[0041] like Figure 2 As shown, the data center monitoring system 200 of this embodiment includes a custom monitoring item module 210, an automatic sensing module 220, a data acquisition module 230, an intelligent operation and maintenance module 240, and a three-dimensional computer room display module 250.

[0042] The custom monitoring item module 210 provides a graphical configuration interface to allow users to add, edit, or delete monitoring items in response to their operations. The monitoring items include at least the equipment category, equipment number, monitoring item name, data source, data acquisition frequency, data processing algorithm, and data alarm threshold of the monitored equipment.

[0043] In the embodiments of this application, users can manually add, edit, or delete monitoring items of the monitored device through the graphical configuration interface of the custom monitoring item module. The graphical configuration interface can support interactive operation. For example, users can quickly add items by dragging and dropping, and can instantly view the configuration effect through the real-time preview window, which greatly improves configuration efficiency and operation experience.

[0044] In the embodiments of this application, the input information for the added monitoring items may include the following: Equipment classification indicates the category to which the equipment belongs, such as environmental monitoring (e.g., temperature and humidity sensors), production auxiliary (e.g., ventilation equipment, lighting systems), etc. Equipment number serves as a unique identifier for the equipment, used for accurate identification and tracking. Monitoring item name refers to the specific indicators that are monitored and measured during the equipment monitoring process, such as CPU utilization, available memory, temperature, humidity, etc. Data source indicates the data acquisition method for the monitoring item data, such as a specific sensor or interface of the monitored equipment. Data acquisition frequency refers to the data acquisition cycle for the monitoring item data, such as 1 time / minute, 5 times / minute, 1 time / day, etc. Data processing algorithm refers to the targeted processing method of the collected raw monitoring item data through a specific mathematical model or calculation rule. Its core objective is to transform the raw monitoring item data (which usually has characteristics such as noise, strong dispersion, or ambiguous business orientation) into high-quality data with clear business semantics that can directly support analysis and decision-making, thereby providing a reliable data foundation for application scenarios such as trend prediction and anomaly early warning. Data processing algorithms that can be used include moving average algorithm, Kalman filter algorithm, etc. The data alarm threshold is designed to define the safe operating boundary of the monitored items. Users can customize the alarm threshold. When the data of the monitored items exceeds or falls below the preset data alarm threshold, the system will automatically trigger the early warning mechanism, thereby helping operation and maintenance personnel or managers to discover potential risks, abnormal fluctuations or fault signs in a timely manner.

[0045] For example, a list of algorithms can be preset for data processing, and users can intuitively and flexibly select the appropriate data processing algorithm according to the specific application scenario requirements through the drop-down list.

[0046] The automatic sensing module 220 is used to scan the target network through the address resolution protocol to determine whether there is a new monitored device, and in response to the detection of a new monitored device, automatically trigger the new monitored device identification process.

[0047] Address Resolution Protocol (ARP) scanning is a network probing technique. Its core principle is based on the working mechanism of the ARP protocol in a local area network (LAN). In a LAN environment, communication between devices ultimately requires knowing each other's Media Access Control (MAC) address. To achieve this, ARP scanning broadcasts ARP request packets throughout the LAN, querying for the MAC address corresponding to a specific Internet Protocol (IP) address. Since ARP is the fundamental protocol for communication between devices within a LAN, all online devices receiving a request matching their own IP address must respond with an ARP reply packet containing their MAC address. When a new device connects to the network and obtains an IP address, if an ARP scan is performed at this time, the broadcast ARP request packet will trigger a response from the new device. Therefore, during subsequent ARP scans, if a previously unrecorded IP address returns a valid ARP response (i.e., a device responds and provides its MAC address), it can be determined that this is a newly connected device.

[0048] In the embodiments of this application, the automatic sensing module can scan the monitored network via ARP at the initial startup of the system to obtain the mapping relationship between the IP addresses and MAC addresses of each device in the network, thereby identifying and listing the existing monitored devices in the current network, forming a "snapshot" of the network devices. Subsequently, using this snapshot as a benchmark, by scanning again and comparing it with the snapshot, newly added monitored devices in the network can be detected in a timely manner, thereby realizing continuous monitoring of the dynamic changes of monitored devices. At the same time, when a new monitored device is detected, the new monitored device identification process is automatically triggered.

[0049] The following will be combined with the appendix Figure 3 Appendix Figure 4 The automatic sensing module 220 is described in detail.

[0050] The data acquisition module 230 is used to generate and execute acquisition tasks based on the monitoring items, wherein the acquisition tasks are used to obtain monitoring data from a specified data source.

[0051] In the embodiments of this application, the data acquisition module is used to automatically generate and schedule corresponding periodic acquisition tasks based on the different data acquisition frequencies (such as 1 time / minute, 5 times / minute, 1 time / day, etc.) set for different monitoring items by the custom monitoring item module and the automatic sensing module. After the acquisition task is started and executed, it can actively send structured data request messages to various data sources based on the communication protocol and data interaction specifications of the data sources set for the monitoring items, thereby accurately acquiring the target monitoring item data.

[0052] In the embodiments of this application, in response to obtaining a data packet from a specified data source, a pre-built protocol parsing database is used to perform protocol matching on the data packet. The protocol parsing database contains multiple protocol parsing plugins for parsing different protocols, and each protocol parsing plugin corresponds to a communication protocol. In response to a successful protocol match, the successfully matched protocol parsing plugin is used to parse the data packet to obtain monitoring data.

[0053] In the embodiments of this application, in order to parse heterogeneous data packets from different data sources, a protocol parsing database is first pre-built. This database has various pre-installed protocol parsing plugins, such as Simple Network Management Protocol (SMMP) and Secure Shell Protocol (SMP). When a data packet to be parsed is received, the system extracts key feature information from the packet (such as fixed header identifiers, specific field values, transmission ports, or protocol signatures) and compares it with the protocol parsing plugins in the protocol parsing database. When a feature match with a plugin is detected, the successfully matched plugin is dynamically loaded to parse the packet, ultimately outputting structured data. When no plugin is found to match the current packet features after traversing the protocol parsing database, the system will trigger an alarm mechanism, which can push real-time alarm prompts through pop-ups, in-system messages, emails, etc.

[0054] Optionally, upon successful protocol parsing plugin matching, a "protocol compatibility verification" step can be performed. The verification logic is as follows: After loading the protocol parsing plugin, the system sends a "protocol handshake command" to check if a valid response is received from the monitored device. Upon receiving the response message, the system verifies whether the response data format matches the parsing module's expectations. If the format verification fails, the system sends a "protocol compatibility failure" alarm to the monitoring and display module, prompting the user to check the parsing module or device parameters. If no response message is received, it indicates a protocol mismatch between the parsing module and the device, and an early warning can also be issued.

[0055] Optionally, when users add monitoring items, an input field for the protocol parsing plugin can be added, allowing users to upload protocol parsing plugins that do not exist in the current protocol parsing database.

[0056] In the embodiments of this application, by pre-building a protocol parsing database, the system can adapt to multiple communication protocols and stably acquire data from various devices without having to write parsing code for each protocol from scratch, thus enabling the reuse of protocol parsing plugins.

[0057] The intelligent operation and maintenance module 240 is used to provide early warnings using a pre-trained monitoring item prediction model and a pre-trained device prediction model, and in response to the occurrence of a monitoring item early warning, to generate a security setting range for the configuration item associated with the monitoring item. The monitoring item prediction model and the device prediction model are constructed and generated based on a long short-term memory network model.

[0058] In the embodiments of this application, using a pre-trained monitoring item prediction model for early warning includes: inputting historical time series monitoring data of the monitoring item into the pre-trained monitoring item prediction model to obtain a prediction result, wherein the monitoring item prediction model is generated based on a long short-term memory network model; and issuing an early warning in response to the prediction result being greater than a data alarm threshold.

[0059] The monitoring item prediction model is built using an LSTM (Long Short-Term Memory) network, which is suitable for processing and predicting time series data and natural language processing tasks. When training the monitoring item prediction model, historical monitoring item data is first sampled and organized according to fixed time steps (e.g., every minute, hour, or day), forming a series of continuous time steps, each representing a monitoring value at a specific moment. Based on these chronologically arranged multi-time-step input data, the model performs internal calculations through its internal loop structure and gating mechanism to capture the dependencies of data in the time dimension and predict the monitoring results for one or more future time steps. Next, the model's predictions are compared with the actual monitoring results step-by-step, the corresponding loss function is calculated, and the gradient is calculated using the backpropagation algorithm. Then, the model parameters are updated using optimization algorithms, continuously iterating the training process to minimize the difference between the predicted and actual values, thereby improving the model's prediction accuracy and generalization ability. Once the Long Short-Term Memory (LSTM) network model is trained, during actual monitoring, the monitoring data collected in real time and organized according to the same time step is input into the trained monitoring prediction model. The model analyzes and infers the data trend of the current and subsequent time steps based on the time series patterns and inherent laws learned during the training phase, thereby predicting the value of the monitoring item at a specific time step in the future (such as the next moment or several future time points). If the predicted data exceeds the pre-set data alarm threshold range of the monitoring item (such as exceeding the upper limit or falling below the lower limit), it will automatically trigger and output the corresponding early warning signal, realizing anomaly monitoring and timely response based on time series prediction.

[0060] In the embodiments of this application, the intelligent operation and maintenance module can also be used to automatically generate reports for different statistical periods of the same monitored device or all monitored devices in the system, such as weekly reports, monthly reports, quarterly reports, annual reports, etc.

[0061] In the embodiments of this application, the intelligent operation and maintenance module can also be used to generate structured archive records and archive key information such as historical monitoring item warnings, triggering reasons for historical equipment warnings, and maintenance handling methods into a knowledge base. Simultaneously, based on the content of this knowledge base, a large language model can be combined to achieve human-computer interaction, engage in dialogue with the user, and complete question-and-answer sessions. For example, the large language model uses semantic parsing and vectorized retrieval technology to transform user questions into query vectors, performs similarity matching in the knowledge base, accurately locates relevant historical data, and interacts with the user in the form of natural language dialogue, dynamically generating clear and accurate answers.

[0062] In the embodiments of this application, by using a monitoring item prediction model to provide early warning for individual monitoring items of the monitored equipment, potential risks, anomalies or malfunctions of the monitoring items can be detected in advance, thereby gaining valuable time to take timely countermeasures, effectively avoiding or mitigating losses, and ensuring the safe and stable operation of the monitored equipment.

[0063] In the embodiments of this application, when a warning is detected for a monitored item, a security setting range (such as a normal value range) for the configuration item associated with that monitored item can be automatically generated. This is used to clarify the deviation between the current value of the configuration item and the security setting range, providing a clear basis for subsequent countermeasures. The following will refer to the appendix... Figure 5 It will be explained in detail.

[0064] In the embodiments of this application, a pre-trained device prediction model can be used for early warning. When a potential risk is predicted for the monitored device, the intelligent operation and maintenance module will automatically trigger the device early warning mechanism and generate corresponding early warning information. This helps operation and maintenance personnel identify potential problems with the monitored device in advance and take timely intervention measures. The following will be combined with the appendix... Figure 6 It will be explained in detail.

[0065] The 3D equipment room display module 250 is used to generate a 3D model based on the distribution of the monitored equipment. The 3D model displays at least the basic information and status information of the monitored equipment.

[0066] In the embodiments of this application, the 3D equipment room display module can display the monitored equipment in three dimensions based on the actual spatial location of the monitored equipment. For example, when the mouse hovers over the device, basic information about these devices, including static attributes such as equipment category, equipment name, equipment number, and installation time, can be displayed. The status information of the monitored equipment can be provided in real time through a combination of colors, icons, and text. For instance, solid green indicates normal operation, flashing yellow indicates a warning based on a monitoring item prediction model or equipment prediction model, and flashing red indicates that the actual monitored item data exceeds the preset alarm threshold range for that monitoring item.

[0067] In the embodiments of this application, on the one hand, users can freely create, modify, and delete monitoring items according to the unique needs of the data center through the custom monitoring item module. The system, through dynamic loading technology, can make newly added monitoring items effective without restarting the system, completely breaking free from the constraints of fixed monitoring items in traditional monitoring systems. Whether it's the introduction of new equipment or changes in business needs, users can quickly adjust the monitoring content, making the monitoring system adapt to the personalized scenarios of the data center. Simultaneously, through the automatic sensing module, the system can proactively identify and connect new monitored equipment, improving system flexibility and convenience. On the other hand, the data center monitoring system provides an intelligent operation and maintenance module, capable of providing early warnings for both individual monitoring items and monitored equipment, thereby identifying potential faults in advance and helping operation and maintenance personnel intervene accurately before problems occur. Furthermore, the three-dimensional data center display module can intuitively display the location and status of equipment, significantly improving equipment troubleshooting efficiency.

[0068] Figure 3 A flowchart illustrating the process of determining a new monitored device according to an embodiment of this application is shown schematically;

[0069] like Figure 3 As shown, the process 300 for determining a new monitored device in this embodiment includes operations S310 to S350.

[0070] When operating S310, maintain a list of known devices in the target network.

[0071] In the embodiments of this application, the known device list includes the network protocol addresses and corresponding media access control addresses of the known monitored devices. At the initial system startup, an ARP scan of the monitored network (i.e., the target network) can be performed to obtain the mapping relationship between the IP addresses and MAC addresses of each monitored device within that network, thus forming the known device list.

[0072] When operating the S320, an Address Resolution Protocol (ARP) request is sent to the target network according to a preset broadcast triggering policy.

[0073] In embodiments of this application, sending an address resolution protocol request to a target network according to a preset broadcast triggering strategy includes: detecting changes in the power parameters of at least one target socket in real time through an intelligent power distribution unit; and sending an address resolution protocol request to the target network in response to detecting changes in the power parameters of the target socket.

[0074] Intelligent Power Distribution Units (PDUs) can monitor changes in the power parameters of each socket in real time, such as voltage, current, power, and energy. When a socket that originally had no power parameters (i.e., no load device was connected) suddenly detects a change in power parameters (such as an increase in voltage, current, or power), it indicates that a new device has been connected to the socket and started to operate. This situation may be due to the addition of a new monitored device. Therefore, an ARP request message can be broadcast to the target network at this time.

[0075] In the embodiments of this application, broadcasting an ARP request message after detecting a change in the power parameters of the target socket through the smart PDU can reduce invalid transmissions and save resources and costs.

[0076] In another embodiment of this application, ARP request messages can be automatically broadcast to the local area network at preset time intervals (such as every hour, a specific time period each day, or every week) to dynamically detect the IP and MAC address mapping relationship of the existing monitored devices, and quickly identify newly added monitored devices by combining the known device list.

[0077] When operating S330, in response to a response message that requests the existence of an Address Resolution Protocol (ARP) request, the network protocol address and the corresponding media access control address of the response message are parsed and obtained.

[0078] The ARP response message contains mapping information between the target IP address and its corresponding MAC address. In the embodiments of this application, when the response message of the ARP request is received, the sender's IP address and its corresponding physical MAC address can be accurately obtained by parsing the message.

[0079] In operation S340, the current device identified by the target network protocol address and the corresponding media access control address is compared with the list of known devices.

[0080] In operation S350, in response to the existence of a device not recorded in the known device list, the device is identified as a new device and the known device list is updated.

[0081] In the embodiments of this application, all monitored devices in the currently identified target network are compared with monitored devices in the known device list. If a monitored device is not recorded in the known device list, that device is identified as a new monitored device. Simultaneously, the new monitored device needs to be added to the known device list to form a "snapshot" of the network devices at the current moment.

[0082] In the embodiments of this application, by detecting new monitored devices through ARP scanning, newly connected monitored devices can be discovered in the first instance. The system can quickly include these new devices in the monitoring scope, quickly complete the initialization settings, and perform monitoring, thereby reducing the workload of operation and maintenance personnel and improving management efficiency.

[0083] Figure 4 A flowchart illustrating the device identification process according to an embodiment of this application is shown.

[0084] like Figure 4 As shown, the monitored device identification process 400 in this embodiment includes operations S410 to S450.

[0085] When operating the S410, multiple device categories are pre-configured.

[0086] In the embodiments of this application, each equipment category corresponds to a type of equipment. For example, equipment categories can be set as environmental monitoring category, production auxiliary category, computing equipment category, energy storage equipment category, etc.

[0087] In operation S420, at least one initial monitoring item is pre-set under each device category.

[0088] In the embodiments of this application, the data center monitoring system can pre-configure at least one initial monitoring item for each device category. For example, for devices in the environmental monitoring category, monitoring items such as consumable lifespan and internal temperature can be pre-configured; for devices in the computing device category, monitoring items such as memory utilization and disk utilization can be pre-configured. Simultaneously, the input information for each monitoring item is pre-configured, including at least the device category, monitoring item name, data source, data acquisition frequency, data processing algorithm, and data alarm threshold. The device number can be automatically assigned a unique identifier to a new device after it is identified.

[0089] When operating S430, in response to the detection of a new monitored device connecting, the device category of the new monitored device is automatically matched.

[0090] In the embodiments of this application, after a new device is detected, it is necessary to identify the device category of the new monitored device.

[0091] For example, upon detecting a new monitored device, its IP address and MAC address are already obtained. Based on these two types of addresses, the device type can be effectively identified and classified. Specifically, the IP address reflects the subnet range and possible network role of the device; for example, 192.111.1.xxx could be a printer subnet, and 192.222.2.xxx could be a camera subnet. The MAC address is a 48-bit hardware identifier, where the first 24 bits are the Organizationally Unique Identifier (OUI), which can be used to determine the device manufacturer and common device categories; for example, 0:AA:11 could be an X-camera, and 0:BB:22 could be a virtual machine. Furthermore, the subnet and OUI can be used together for identification. For example, if a device's OUI belongs to an air conditioner manufacturer, and its IP address is consistently located within the 192.33.3.xxx / 24 subnet specifically allocated for IoT devices, then the device is likely a smart home appliance, and the device can be classified accordingly.

[0092] In another embodiment of this application, after detecting a new monitored device and obtaining its IP and MAC addresses, a corresponding service or agent program, such as a Simple Network Management Protocol agent program or a Web (World Wide Web) service, can be installed on the new monitored device. The device can then be sent a corresponding request to actively obtain basic information such as its device name, device type, and manufacturer identification. Based on this basic information, the device can be further classified.

[0093] In the embodiments of this application, when adding a new monitoring item through the custom monitoring item module, the system can automatically list the initial monitoring items that have not yet been added in the equipment category to which the monitored device belongs.

[0094] When operating S440, in response to successful device category matching, the initial monitoring items under the device category are obtained.

[0095] In the embodiments of this application, the obtained device classification is matched with multiple pre-set device classifications in the system. After a successful match, all initial monitoring items set under that device classification can be obtained. If no corresponding device classification exists in the system's preset device classifications, the system can issue an alert. After the administrator or maintenance personnel add the corresponding device classification, the identification will be performed again.

[0096] When operating the S450, monitor the new monitored device according to the initial monitoring items.

[0097] In the embodiments of this application, after the device category is successfully matched, the new monitoring device is automatically added a monitoring item based on all the initial monitoring items set under the device category, and then enters the monitoring state.

[0098] It should be noted that users can customize, modify, or delete the initial monitoring items added to a new monitored device, and can also add other monitoring items to the new monitored device.

[0099] Optionally, inclusion status identifiers can be set for monitored devices, including: pending inclusion, included, and rejected inclusion. Pending inclusion refers to an intermediate state where the device cannot be included in the monitoring scope due to a mismatch in device classification. Included indicates that the new monitored device has been included in the monitoring scope and monitoring has commenced. Rejected inclusion signifies that the new monitored device does not meet the system's preset inclusion conditions, resulting in the inclusion request being rejected; for example, the inclusion of the new monitored device was not approved by relevant personnel or the approval was rejected.

[0100] In the embodiments of this application, by automatically identifying new monitored devices, the monitoring environment network can be scanned in real time or periodically without the need for manual addition of each new monitored device, significantly reducing manpower and workload. Furthermore, once a new monitored device is automatically identified, the system can quickly add initial monitoring items under the device category, eliminating the need for manual configuration of each input item.

[0101] Figure 5 A flowchart illustrating the setting of a security setting range according to an embodiment of this application is shown schematically;

[0102] like Figure 5 As shown, the setting of the security setting range 500 in this embodiment includes operations S510 to S560.

[0103] When operating the S510, all configuration items of the monitored device are obtained, and the first configuration item set is generated.

[0104] In the embodiments of this application, a monitored device often monitors multiple monitoring items, and each monitoring item may be related to multiple configuration items. All configuration items of the same monitored device and their historical time point settings can be uploaded to the data center monitoring system as the data basis for subsequent analysis. At the same time, all configuration items of the same monitored device can be integrated together to form a first configuration item set.

[0105] In operation S520, in response to the occurrence of a monitoring item warning, a mutual information algorithm is used to calculate the mutual information value between the monitoring item and each configuration item in the first configuration item set.

[0106] When operating S530, a second set of configuration items related to the monitoring items is selected based on mutual information values.

[0107] In the embodiments of this application, after a warning is issued for a certain monitoring item of a monitored device, a mutual information algorithm can be used to calculate the mutual information value between the monitoring item and each configuration item in the first configuration item set of the monitored device. Then, based on the mutual information value, a second configuration item set related to the monitoring item is selected.

[0108] For example, historical observations of monitoring items at multiple consecutive time points can be obtained, along with the values ​​of each configuration item in the first configuration item set at the corresponding time points. This ensures strict alignment between the monitoring item data and the configuration data in the time dimension, thereby constructing a series of synchronized monitoring and configuration data samples. Then, based on these samples, the marginal probability distributions of the monitoring items and configuration items, as well as their joint probability distribution, are estimated. Next, the ratio of the joint probability to the product of the corresponding marginal probabilities is calculated, the logarithm is taken, and then a weighted sum is obtained to obtain the mutual information value between the monitoring items and the configuration items. According to a preset mutual information threshold, configuration items whose mutual information values ​​reach or exceed the threshold are selected as key configuration items that have a significant impact on or are associated with the monitoring items, forming a second configuration item set.

[0109] In operation S540, retrieve the historical normal setting values ​​of each configuration item in the second configuration item set.

[0110] In the embodiments of this application, after filtering out the second set of configuration items related to the monitoring items, the setting values ​​used by each configuration item in the second set of configuration items under the historical normal operation state of the monitored device at multiple consecutive time points can be obtained respectively.

[0111] When operating the S550, the mean and standard deviation are calculated based on the historical normal settings for each configuration item.

[0112] In the embodiments of this application, based on the historical normal setting values ​​of each configuration item at multiple consecutive time points, the arithmetic mean of its values ​​is calculated as the mean, and the average of the squares of the differences between each setting value and the mean is calculated as the variance. The standard deviation is obtained by taking the square root of the variance.

[0113] When operating the S560, the security setting range of each configuration item is generated according to the mean and standard deviation of each configuration item and a preset rule.

[0114] In the embodiments of this application, the security setting range for each configuration item is calculated and generated according to a preset rule based on the mean and standard deviation of each configuration item. For example, the mean can be the center, and a range of several times the standard deviation can be set, such as the mean plus or minus 1, 2, or 3 times the standard deviation, thereby constructing a security setting range with the mean as the core that covers most normal values.

[0115] For example, the data center monitoring system can send instructions to control the monitored devices with early warning monitoring items, and adjust the values ​​of each configuration item in the second configuration item set. For example, it can directly set them to the average value obtained in operation S550.

[0116] In the embodiments of this application, firstly, the security setting range can provide a reference standard for operation and maintenance personnel, improving the operation and maintenance response speed and processing efficiency; secondly, it can accurately locate configuration items that may cause problems, eliminating the need to check one by one among many configurations, saving a lot of time.

[0117] Figure 6 A flowchart illustrating a device warning according to an embodiment of this application is shown.

[0118] like Figure 6 As shown, the device warning 600 in this embodiment includes operations S610 to S670.

[0119] When operating S610, all monitoring items of the monitored device are obtained, and the first monitoring item set is generated.

[0120] In operation S620, based on the mutual information algorithm, the mutual information value between each monitoring item in the first monitoring item set and the equipment anomaly is calculated.

[0121] In the embodiments of this application, the mutual information value represents the degree of correlation between the monitored item and the equipment anomaly; the higher the mutual information value, the greater the degree of correlation.

[0122] In operation S630, based on mutual information values, monitoring items related to equipment anomalies are filtered from the first set of monitoring items to generate a second set of monitoring items.

[0123] In the embodiments of this application, all monitoring items of the same monitored device can be integrated to generate a first monitoring item set. Then, by acquiring historical data of the monitoring items, the mutual information value between each monitoring item in the first monitoring item set and the device anomaly is calculated based on the mutual information algorithm. Next, according to a preset mutual information threshold, monitoring items whose mutual information values ​​reach or exceed the threshold are selected as key monitoring items that have a significant impact on or are associated with the device anomaly, and a second monitoring item set is generated.

[0124] Optionally, a threshold for the number of monitoring items for the monitored device can be set (e.g., 5 monitoring items). When the number of monitoring items monitored in real time exceeds this threshold, the device anomaly prediction process will be started to avoid affecting the reliability and accuracy of the model prediction results due to insufficient monitoring items.

[0125] In operation S640, the correlation between monitoring items in the second monitoring item set is calculated based on the Spearman rank correlation coefficient.

[0126] Spearman's rank correlation coefficient is a nonparametric statistical method that can effectively measure the monotonic relationship between two variables. It can determine the strength and direction of the relationship and assess the correlation between variables.

[0127] In the embodiments of this application, the correlation between each monitoring item in the second monitoring item set is calculated based on the Spearman rank correlation coefficient.

[0128] In operation S650, in response to identifying a group of monitoring items with a correlation greater than a preset threshold, the monitoring item with the highest mutual information value with the device anomaly is selected from the monitoring item group, and a third monitoring item set is generated.

[0129] In the embodiments of this application, a correlation threshold can be preset, and monitoring item pairs with an absolute correlation value greater than the preset threshold can be selected. These highly correlated monitoring items are then grouped together. Since the monitoring items within a group have significant correlations with each other, information redundancy may occur, which could affect the predictive performance and stability of the subsequent model. Therefore, the monitoring items with the highest mutual information value with equipment anomalies can be selected from the group to generate a third set of monitoring items. This retains the monitoring items that have the most significant impact on equipment anomalies while effectively reducing the risk of multicollinearity and improving the accuracy and generalization ability of the model prediction.

[0130] When operating S660, the historical time series monitoring data of the third monitoring item set is input into the pre-trained equipment prediction model to obtain the equipment anomaly prediction probability value.

[0131] In the embodiments of this application, the device prediction model is built based on an LSTM model. The LSTM model can be trained using historical time-series monitoring data collected at the time points corresponding to the occurrence of anomalies in historical monitored devices, from a third set of monitoring items. This data contains temporal changes in device parameters before the anomaly occurred (e.g., monitoring values ​​per minute or hour within a 24-hour or longer window before the anomaly). By inputting this pre-anomaly time-series data into the LSTM model for training, the LSTM model can effectively capture the dynamic characteristics of the monitoring item data evolving over time and its correlation with the occurrence of device anomalies. After training, the model can be used to predict real-time or time-series monitoring data for a specified period, outputting the predicted probability value of device anomalies occurring at a specific future time.

[0132] When operating S670, an early warning is issued in response to the device anomaly prediction probability value exceeding the preset alarm threshold.

[0133] In the embodiments of this application, an alarm threshold for the device can be preset, and an early warning will be issued if the predicted probability value meets the threshold.

[0134] In the embodiments of this application, a monitored device often monitors multiple monitoring items. Some of these monitoring items may be related to equipment anomalies. By using a mutual information value algorithm, these monitoring items related to equipment anomalies can be effectively screened out. By jointly analyzing these monitoring items, potential anomalies of the monitored device can be predicted in advance, thereby enabling the development of preventive maintenance plans before equipment failures actually occur and improving equipment reliability.

[0135] Figure 7 This illustration shows another structural diagram of a data center monitoring system according to an embodiment of the present application.

[0136] like Figure 7 As shown, the data center monitoring system 700 may also include: a data processing module, a process approval module, a data storage module, and a monitoring and display module.

[0137] For example, the data processing module is used to process data based on the data processing algorithm in the monitoring item to obtain processed monitoring data.

[0138] In the embodiments of this application, the data processing module can first perform a data preprocessing process on the collected monitoring data, which may include data cleaning (e.g., deduplication, missing value imputation, outlier filtering), data transformation (e.g., unit standardization, encoding mapping), etc. After ensuring the accuracy, consistency and usability of the original data, the data processing algorithm in the monitoring item is used to process the data to obtain the processed monitoring data.

[0139] For example, the process approval module is used for the application review process for the inclusion of new monitored equipment and the application review process for pre-embedded monitored equipment, wherein the application for pre-embedded monitored equipment is an application for the early inclusion of monitored equipment.

[0140] In the embodiments of this application, a multi-level permission hierarchical management system is established according to the different responsibilities of users in the data center monitoring system. For example, it may include senior administrators, system administrators, other administrators and users, and set progressively decreasing operation permissions, in accordance with the control rules of the superior approving the subordinate application process.

[0141] In the embodiments of this application, a new monitored device needs to be approved before being included in the monitoring system. This includes two approval processes: First, if a new monitored device already exists and needs to be included in the system, a "New Monitored Device Inclusion Application Review Process" is required. After this application is approved, the new monitored device's status changes from "Pending Inclusion" to "Included." If the application is rejected, the monitored device's status changes from "Pending Inclusion" to "Rejected Inclusion." For rejected monitored devices, maintenance personnel can power them down on-site based on their location information. Second, if no new monitored device actually exists but an inclusion approval process has been initiated in advance, i.e., a "Pre-embedded Monitored Device Application Review Process," pre-embedded devices can be directly identified and included in the system monitoring sequence by the automatic sensing module after the device is actually powered on. When adding a new monitored device through the automatic sensing module, the system can first check if the device is a pre-embedded device. If it is, the subsequent device identification process proceeds directly; if it is not, the "New Monitored Device Inclusion Application Review Process" is automatically triggered. After the process is approved, the device is identified and added.

[0142] For example, the data storage module is used to store the data generated by each module. The monitoring and display module is used to display the monitoring data of the monitored items, and to generate and display alarm information in response to the data alarm threshold triggered by the monitoring data of the monitored items.

[0143] In the embodiments of this application, the monitoring and display module can analyze and display the processed monitoring data to the user in an intuitive way, such as bar charts, line charts, etc. The monitoring and display module can also generate and display alarm information, such as abnormal time and excessive value, when the monitoring data of the monitored item triggers the data alarm threshold.

[0144] In the embodiments of this application, the custom monitoring item module and the automatic sensing module require authorization to add new monitored devices through the process approval module. Monitoring of the devices can only begin after the process approval module approves the authorization. The data acquisition module generates corresponding acquisition tasks based on the monitoring items added by the custom monitoring item module and the automatic sensing module, and obtains monitoring data from the data source. The data processing module processes the monitoring data obtained by the data acquisition module based on the data processing algorithm in the monitoring item to obtain processed monitoring data. The intelligent operation and maintenance module makes predictions based on the monitoring data processed by the data processing module. The monitoring and display module analyzes and displays the monitoring data processed by the data processing module. The three-dimensional data center display module displays the early warning information from the intelligent operation and maintenance module and the monitoring and display module in three dimensions. The data storage module is used to store the data generated by each module, providing the underlying data foundation for the system's data query, data analysis, historical tracing, and functional support.

[0145] For example, the monitored device is a server using immersion liquid cooling technology, requiring monitoring of specific indicators such as coolant temperature, flow rate, and pump operating status. Traditional monitoring systems lack corresponding monitoring items. In the data center monitoring system of this application's embodiment, the user can set the following monitoring items sequentially through the graphical interface of the custom monitoring item module: device category is computing device; device number is A001; monitoring item name is "liquid-cooled server coolant temperature"; data source is specified as the liquid cooling equipment management interface; data acquisition frequency is set to 1 time / minute; data processing algorithm is selected as "moving average (window size 5)"; alarm threshold is set to an upper limit of 35℃ and a lower limit of 18℃. The data acquisition module obtains temperature data in real time from the liquid-cooled server sensor through the Simple Network Management Protocol (SMLP). The data processing module filters fluctuation noise according to the set algorithm. The user can monitor the coolant temperature change trend in real time through the monitoring display module. When the temperature exceeds 35℃, the monitoring display module highlights it in red and triggers an audible and visual alarm, while simultaneously sending an SMS notification to the maintenance personnel. The location of the alarming device is displayed on the 3D computer room display module, and its status is highlighted in red.

[0146] For example, to achieve green energy saving, data centers deploy lithium battery energy storage systems, requiring monitoring of indicators such as battery pack state of charge, charging and discharging power, and individual cell voltage balance. In the data center monitoring system of the embodiments of this application, users can set the following monitoring items sequentially through the graphical interface of the custom monitoring item module: device classification as energy storage device; device number as C001; monitoring item name as "battery pack state of charge"; data source as the energy storage system's Modibos protocol interface; data acquisition frequency set to 5 times / minute; data processing algorithm selected as "Kalman filter"; alarm threshold set to a state of charge below 20% or above 95% (wherein, 0% state of charge indicates a depleted battery, and 100% state of charge indicates a fully charged battery). Then, monitoring of the "battery pack state of charge" is achieved based on this monitoring item.

[0147] In an embodiment of this application, a data center monitoring method is also disclosed, comprising: a user adding monitoring items to the monitored device through a custom monitoring item module; generating and executing a data collection task based on the monitoring items, wherein the data collection task is used to obtain monitoring data from a specified data source; issuing an early warning based on the monitoring data using a pre-trained monitoring item prediction model and a pre-trained device prediction model; and generating a security setting range for a configuration item associated with the monitoring item in response to a monitoring item early warning.

[0148] In embodiments of this application, the data center monitoring method further includes: generating a three-dimensional model based on the distribution of the monitored devices, wherein the three-dimensional model displays at least basic information and status information of the monitored devices; and updating the status displayed in the three-dimensional model in response to a change in the status of the monitored devices.

[0149] In embodiments of this application, the data center monitoring method further includes: scanning the target network via Address Resolution Protocol to determine whether a new monitored device exists; and automatically triggering a new monitored device identification process in response to the detection of a new monitored device.

[0150] In the embodiments of this application, the data center monitoring system, through a custom monitoring item module and an automatic sensing module, can solve the problem that existing data center monitoring systems have fixed monitoring items and cannot meet personalized monitoring needs. This allows users to flexibly add, modify, and delete monitoring items according to actual conditions, improving the targeting and effectiveness of data center monitoring. The intelligent operation and maintenance module can provide early warnings for monitoring items and monitored equipment, thereby identifying potential faults in advance and improving system reliability. The three-dimensional computer room display module can intuitively display the location and status of equipment, significantly improving equipment troubleshooting efficiency.

[0151] Figure 8 A block diagram of an electronic device suitable for implementing a data center monitoring system according to an embodiment of this application is illustrated schematically.

[0152] like Figure 8 As shown, an electronic device 800 according to an embodiment of this application includes a processor 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage portion 808 into a random access memory (RAM) 803. The processor 801 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 801 may also include onboard memory for caching purposes. The processor 801 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this application.

[0153] RAM 803 stores various programs and data required for the operation of electronic device 800. Processor 801, ROM 802, and RAM 803 are interconnected via bus 804. Processor 801 executes various operations of the method flow according to embodiments of this application by executing programs in ROM 802 and / or RAM 803. It should be noted that the programs may also be stored in one or more memories other than ROM 802 and RAM 803. Processor 801 may also execute various operations of the method flow according to embodiments of this application by executing programs stored in said one or more memories.

[0154] According to embodiments of this application, the electronic device 800 may further include an input / output (I / O) interface 805, which is also connected to a bus 804. The electronic device 800 may also include one or more of the following components connected to the input / output (I / O) interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN card, modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the input / output (I / O) interface 805 as needed. A removable medium 811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 810 as needed so that computer programs read from it can be installed into the storage section 808 as needed.

[0155] This application also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of this application.

[0156] According to embodiments of this application, the computer-readable storage medium can be a non-volatile computer-readable storage medium, such as including but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this application, the computer-readable storage medium may include ROM 802 and / or RAM 803 and / or one or more memories other than ROM 802 and RAM 803 described above.

[0157] Embodiments of this application also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code enables the computer system to implement the data center monitoring system provided by embodiments of this application.

[0158] When the computer program is executed by the processor 801, it performs the functions defined in the system / apparatus of the embodiments of this application. According to the embodiments of this application, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0159] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 809, and / or installed from a removable medium 811. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0160] In such an embodiment, the computer program can be downloaded and installed from a network via communication section 809, and / or installed from removable medium 811. When the computer program is executed by processor 801, it performs the functions defined in the system of the embodiments of this application. According to embodiments of this application, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0161] According to embodiments of this application, program code for executing the computer programs provided in embodiments of this application can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0162] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0163] Those skilled in the art will understand that the features described in the various embodiments of this application can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this application. In particular, the features described in the various embodiments of this application can be combined and / or combined in various ways without departing from the spirit and teachings of this application. All such combinations and / or combinations fall within the scope of this application.

Claims

1. A data center monitoring system, characterized in that, The system includes: The custom monitoring item module provides a graphical configuration interface, allowing users to add, edit, or delete monitoring items in response to their actions. The monitoring items include at least the device category, device number, monitoring item name, data source, data acquisition frequency, data processing algorithm, and data alarm threshold of the monitored device. The automatic sensing module is used to scan the target network through the address resolution protocol to determine whether there are new monitored devices, and to automatically trigger the new monitored device identification process in response to the detection of new monitored devices; A data acquisition module is used to generate and execute acquisition tasks based on the monitoring items, wherein the acquisition tasks are used to obtain monitoring data from a specified data source; The intelligent operation and maintenance module is used to provide early warnings using a pre-trained monitoring item prediction model and a pre-trained device prediction model, and to generate a security setting range for configuration items associated with the monitoring item in response to the occurrence of a monitoring item early warning. The monitoring item prediction model and the device prediction model are constructed and generated based on a long short-term memory network model. The 3D equipment room display module is used to generate a three-dimensional model based on the distribution of the monitored equipment. The three-dimensional model displays at least the basic information and status information of the monitored equipment.

2. The system according to claim 1, characterized in that, The use of a pre-trained device prediction model for early warning includes: Obtain all monitoring items of the monitored device and generate a first monitoring item set; Based on the mutual information algorithm, the mutual information value between each monitoring item in the first monitoring item set and the device anomaly is calculated, wherein the mutual information value represents the degree of correlation between the monitoring item and the device anomaly, and the higher the mutual information value, the greater the degree of correlation; Based on the mutual information value, monitoring items related to equipment anomalies are selected from the first monitoring item set to generate a second monitoring item set; Based on the Spearman rank correlation coefficient, the correlation degree between monitoring items in the second monitoring item set is calculated, wherein the correlation degree is used to represent the strength of the relationship between the monitoring items; In response to identifying a group of monitoring items with a correlation greater than a preset threshold, the monitoring item with the highest abnormal mutual information value with the device is selected from the monitoring item group to generate a third set of monitoring items; The historical time series monitoring data of the third monitoring item set is input into the pre-trained device prediction model to obtain the device anomaly prediction probability value, wherein the device prediction model is generated based on the long short-term memory network model; An early warning is issued in response to the device's abnormality prediction probability value exceeding a preset alarm threshold.

3. The system according to claim 1, characterized in that, The method of using a pre-trained monitoring item prediction model for early warning includes: The historical time series monitoring data of the monitoring item is input into the pre-trained monitoring item prediction model to obtain the prediction result, wherein the monitoring item prediction model is generated based on the long short-term memory network model; An early warning is issued in response to the prediction result being greater than the data alarm threshold.

4. The system according to claim 1, characterized in that, The step of generating a security setting range for a configuration item associated with a monitoring item in response to a monitoring item alert includes: Obtain all configuration items of the monitored device and generate a first configuration item set; In response to the occurrence of a monitoring item warning, a mutual information algorithm is used to calculate the mutual information value between the monitoring item and each configuration item in the first configuration item set; Based on the mutual information value, a second set of configuration items related to the monitoring item is selected; Retrieve the historical normal setting values ​​of each configuration item in the second configuration item set; Calculate the mean and standard deviation based on the historical normal settings for each configuration item; Based on the mean and variance of each configuration item, a security setting range for the configuration item is generated according to a preset rule.

5. The system according to claim 1, characterized in that, The data acquisition task is used to obtain monitoring data from a specified data source, including: In response to receiving a data packet from a specified data source, the protocol of the data packet is matched using a pre-built protocol parsing database, wherein the protocol parsing database contains multiple protocol parsing plugins for parsing different protocols, and each protocol parsing plugin corresponds to a communication protocol. In response to a successful protocol match, the data packet is parsed using the protocol parsing plugin that matched the protocol to obtain monitoring data.

6. The system according to claim 1, characterized in that, The automatic triggering of the new monitored device identification process in response to the detection of a new monitored device includes: Multiple equipment categories are pre-defined, with each category corresponding to a specific equipment type. At least one initial monitoring item is pre-set under each of the aforementioned equipment categories; In response to the detection of a new monitored device connecting to the system, the system automatically matches the device category of the new monitored device. In response to a successful device category matching, the initial monitoring items under the device category are obtained; The new monitored device is monitored based on the initial monitoring items.

7. The system according to claim 1, characterized in that, The step of scanning the target network using the Address Resolution Protocol (ARP) to determine whether new monitored devices exist includes: Maintain a list of known devices in the target network, wherein the list of known devices includes the network protocol addresses and corresponding media access control addresses of the known devices; According to the preset broadcast triggering strategy, an Address Resolution Protocol (ARP) request is sent to the target network; In response to a response message that requests the Address Resolution Protocol (ARP) to exist, the network protocol address and the corresponding media access control address of the response message are parsed and obtained. The current device identified by the target network protocol address and the corresponding media access control address is compared with the list of known devices; In response to the existence of a device not recorded in the known device list, the device is identified as a new device and the known device list is updated.

8. The system according to claim 7, characterized in that, Sending an Address Resolution Protocol (ARP) request to the target network according to a preset broadcast triggering strategy includes: The power parameter changes of at least one target socket are detected in real time by the intelligent power distribution unit. In response to detecting a change in the power parameters of the target socket, an Address Resolution Protocol (ARP) request is sent to the target network.

9. The system according to claim 1, characterized in that, The system also includes: The data processing module is used to process data based on the data processing algorithm in the monitoring item to obtain the processed monitoring data; The process approval module is used for the application review process for the inclusion of new monitored equipment and the application review process for pre-embedded monitored equipment, wherein the application for pre-embedded monitored equipment is an application for the early inclusion of monitored equipment; The data storage module is used to store the data generated by each module; The monitoring and display module is used to display the monitoring data of the monitored items, and to generate and display alarm information in response to the data alarm threshold triggered by the monitoring data of the monitored items.

10. An electronic device, comprising: One or more processors; Memory, used to store one or more computer programs. The feature is that the one or more processors execute the one or more computer programs to implement the system according to any one of claims 1 to 9.

11. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed by a processor, they implement the system according to any one of claims 1 to 9.

12. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by a processor, they implement the system according to any one of claims 1 to 9.

Images