IDC equipment intelligent detection and classification management method and system

Abstract

The invention relates to the technical field of electrical equipment testing, in particular to an intelligent detection and classification management method and system for IDC equipment, and the method comprises the following steps: collecting the current, voltage, power consumption and temperature of a server in an IDC cabinet, synchronously recording the CPU occupancy rate and the GPU occupancy rate, storing the I / O load and the network throughput rate, extracting server log entries, and storing the server log entries in an equipment exception log library; and obtaining IDC equipment operation state data. According to the invention, by synchronously monitoring the current, voltage, power consumption and temperature of the IDC equipment and collecting the operation data of the server, the new scheme optimizes the comprehensiveness of the data and the real-time performance of the monitoring, and the monitoring strategy provides finer risk assessment and classification management by dynamically analyzing the state fluctuation of the equipment, so that the reliability of the IDC equipment is improved. Therefore, the accuracy of fault prediction and the efficiency of maintenance are improved, the analysis of abnormal logs and operation data is comprehensively utilized, the prediction capability of potential problems is enhanced, and the system downtime rate and the maintenance expenditure are effectively reduced.

Description

Technical Field

[0001] This invention relates to the field of electrical equipment testing technology, and in particular to an intelligent detection and classification management method and system for IDC equipment. Background Technology

[0002] The field of electrical equipment testing technology encompasses the technical means of measuring and evaluating the performance, electrical parameters, and fault conditions of various electrical devices. The core content of this technology includes the detection of parameters such as current, voltage, resistance, capacitance, inductance, and power quality, and covers signal acquisition, data analysis, and diagnostic methods. The overall technical system mainly involves the application of measuring instruments and sensors, data acquisition and transmission methods, electrical fault diagnosis methods, and related intelligent analysis tools. Electrical equipment testing technology is widely used in power systems, industrial automation, communication equipment, and computer hardware to ensure the stability, safety, and reliability of equipment.

[0003] The intelligent detection and classification management method for IDC equipment refers to a technical approach that uses pre-defined detection processes and classification rules to monitor the status and automatically classify servers, storage devices, and network equipment in IDC data centers. This method encompasses real-time monitoring of equipment operating status, identification of abnormal data, setting of equipment classification rules, and storage management of classification results. Specifically, it uses detection methods based on changes in current, voltage, and power consumption to collect equipment operating data, combines this with feature parameter matching methods to complete equipment classification, and utilizes a database system to manage the classification results.

[0004] Current monitoring and diagnostic technologies often focus on single parameters, lacking real-time analysis across multiple data dimensions. This limits the timeliness and effectiveness of fault prevention and equipment maintenance. This technological limitation results in incomplete equipment condition assessments, hindering early risk identification and classification, and increasing system instability and maintenance complexity. The lack of effective data integration and intelligent analysis leads to inefficient maintenance strategies and resource allocation, impacting the overall cost-effectiveness of equipment management. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by proposing an intelligent detection and classification management method and system for IDC equipment.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a method for intelligent detection and classification management of IDC equipment, comprising the following steps:

[0007] S1: Collect server current, voltage, power consumption, and temperature in the IDC rack, synchronously record CPU utilization, GPU utilization, storage I / O load, and network throughput, extract server log entries and store them in the device anomaly log database to obtain IDC device operating status data;

[0008] S2: Call the IDC device's operating status data, analyze the server load change rate, calculate the fluctuation of temperature, current, and voltage, count the number of abnormal log occurrences, and obtain the IDC device's status fluctuation.

[0009] S3: Calculate the operational stability score based on the state fluctuation of the IDC equipment, analyze load fluctuation, electrical parameters, and abnormal logs, compare the stability and health scores, classify risky and stable operating equipment, and generate IDC equipment operation classification labels;

[0010] S4: Based on the IDC equipment operation classification tags, analyze the trends of temperature, current, load, and abnormal logs, predict load peak changes, and establish IDC equipment abnormal trend prediction values;

[0011] S5: Calculate the maintenance priority based on the predicted abnormal trend value of the IDC equipment, adjust the equipment maintenance order, and generate an IDC equipment maintenance priority ranking.

[0012] As a further aspect of the present invention, the IDC equipment operating status data specifically includes server current, server voltage, network throughput change rate, and the contents of the equipment anomaly log database. The IDC equipment status fluctuation includes server load change rate, current difference value, voltage difference value, temperature difference value, and anomaly log weight. The IDC equipment operation classification label specifically refers to high-risk IDC equipment and stable operating IDC equipment. The IDC equipment anomaly trend prediction value specifically includes server temperature trend, current trend, load peak interval change, and anomaly log quantity trend. The IDC equipment maintenance priority ranking includes server health score, anomaly warning level, and equipment business importance score.

[0013] As a further aspect of the present invention, the step of obtaining the IDC device operating status data specifically includes:

[0014] S101: Collects current, voltage, power consumption and temperature data of servers in IDC racks, obtains CPU utilization, GPU utilization, storage I / O load and network throughput, records server log entries and stores them in the device abnormal log library, and generates device operating parameter dataset.

[0015] S102: Based on the aforementioned device operating parameter dataset, normalize the server current, voltage, and power consumption data, calculate the average power consumption and fluctuation amplitude within multiple time windows, and combine this with server temperature data to calculate the change in heat dissipation status using the following formula:

[0016]

[0017] Calculate server temperature fluctuation values ​​and generate server heat dissipation status parameters;

[0018] Among them, S temp T represents the server temperature fluctuation value. i T represents the server temperature in the i-th time window. avg Represents the average temperature, n represents the total number of time windows, and P max P represents the maximum power consumption value. min V represents the minimum power consumption value. avg Represents the average voltage;

[0019] S103: Based on the server heat dissipation status parameters, call the CPU utilization rate, GPU utilization rate, storage I / O load and network throughput data, calculate the changing trend of device power consumption and heat dissipation parameters under different load conditions, extract server abnormal state characteristics, and generate IDC device operating status data.

[0020] As a further aspect of the present invention, the step of obtaining the state fluctuation of the IDC device specifically includes:

[0021] S201: Call the IDC device operation status data, calculate the server load change rate within the differentiated time window, calculate the change rate of CPU utilization, GPU utilization and storage I / O load based on adjacent time periods, and obtain the average and fluctuation range to obtain the server load change rate.

[0022] S202: Calculate the fluctuation values ​​of temperature, current, and voltage based on the server load change rate, monitor changes in adjacent data, and use the following formula:

[0023]

[0024] Calculate the degree of fluctuation in the operating parameters of the equipment;

[0025] Among them, Y dev T represents the degree of fluctuation in the equipment's operating parameters. j T represents the temperature data for time period j. avg I represents the average temperature. j I represents the current data for time period j. avg Represents the average current, V j V represents the voltage data for time period j. avg represents the average voltage, and m represents the number of time windows;

[0026] S203: Based on the fluctuation of the device operating parameters, count the abnormal log entries in the device abnormal log library, calculate the number of times abnormal logs occur within the differentiated time window, and combine the fluctuation of temperature, current and voltage to summarize the fluctuation trend of the differentiated time period and obtain the IDC device status fluctuation.

[0027] As a further aspect of the present invention, the step of obtaining the IDC device operation classification label specifically includes:

[0028] S301: Based on the state fluctuation of the IDC equipment, calculate the stability score of the operation of multiple devices, statistically analyze the changes in load fluctuation, electrical parameters and abnormal logs within the differentiated time window, and calculate the stability weight of multiple indicators to obtain the equipment stability score.

[0029] S302: Based on the aforementioned equipment stability score, analyze the load fluctuations, electrical parameters, and frequency of abnormal logs of multiple devices, and calculate the mean and dispersion of the stability score using the following formula:

[0030]

[0031] Calculate the equipment stability deviation value to obtain the stability and health score;

[0032] Among them, S stab W represents the equipment stability deviation value. k L represents the stability weight of the k-th device. k This represents the load fluctuation value of the k-th device. E represents the average load fluctuation. k Q represents the frequency of abnormal logs for the k-th device. k This represents the electrical parameter value of the k-th device. Represents the average electrical parameters, p represents the total number of devices, and I dev This represents the degree of current fluctuation;

[0033] S303: Based on the stability and health scores, classify the devices into high-risk devices, low-risk devices, and stable operating devices according to the score range, and mark their status categories to obtain IDC device operation classification labels.

[0034] As a further aspect of the present invention, the step of obtaining the abnormal trend prediction value of the IDC device specifically includes:

[0035] S401: Based on the IDC equipment operation classification tags, analyze the trends of temperature, current, load and abnormal logs within multiple time windows, calculate the rate of change of multiple device statuses, and obtain device status trend parameters;

[0036] S402: Based on the aforementioned device status trend parameters, analyze the load peak changes of multiple devices, calculate the load peak growth rate and fluctuation range for different time periods, using the formula:

[0037]

[0038] Calculate the load peak change parameters and integrate the load peak change trend;

[0039] Among them, P peak T represents the peak load variation parameter. s T represents the temperature data for time period s. avg I represents the average temperature. s L′ represents the current data for time period s. s Represents the load data for time period s. Represents the average load data, r represents the total number of time windows, and E α This represents the frequency of occurrence in the exception log;

[0040] S403: Based on the load peak change trend, summarize the abnormal device status change pattern, calculate the abnormal change magnitude in the future time window, and obtain the IDC device abnormal trend prediction value.

[0041] As a further aspect of the present invention, the step of obtaining the IDC equipment maintenance priority ranking is specifically as follows:

[0042] S501: Based on the predicted abnormal trend value of the IDC equipment, calculate the maintenance priority of multiple equipment, and obtain the equipment maintenance priority parameters according to the abnormal trend change rate and operation failure rate of the equipment.

[0043] S502: Based on the aforementioned equipment maintenance priority parameters, analyze the urgency of maintenance for multiple devices, calculate the maintenance demand index, and use the following formula:

[0044]

[0045] Calculate the maintenance demand index to obtain the equipment maintenance order adjustment value;

[0046] Among them, M req U represents the maintenance demand index. q R represents the rate of change of the abnormal trend of the q-th device. q W represents the mean of abnormal trends across all devices. q X represents the cumulative failure impact factor of the qth device. q Y represents the load stability index of the q-th device, p represents the total number of devices, and Y represents the load stability index of the q-th device. δ Represents parameters indicating fluctuations in equipment status;

[0047] S503: Based on the equipment maintenance order adjustment value, optimize and adjust the equipment maintenance order, and sort according to maintenance priority to obtain the IDC equipment maintenance priority ranking.

[0048] An intelligent detection and classification management system for IDC equipment, the intelligent detection and classification management system for IDC equipment is used to execute the above-mentioned intelligent detection and classification management method for IDC equipment, the system comprising:

[0049] The device operation status monitoring module collects server current, voltage, power consumption, and temperature data, obtains CPU / GPU utilization, storage I / O load, and network throughput, and stores them in the data monitoring system. It also detects logs to extract error codes and key parameters, filters characters, and stores them in the abnormal log library. The module calculates the adjacent change rate of current, voltage, and network throughput, marks abrupt change points, and stores them to obtain device operation status data.

[0050] Based on the device operating status data, the load fluctuation and anomaly analysis module calculates the server load change rate, normalizes CPU / GPU load, storage I / O load, and network throughput, calculates the first-order difference values ​​of server temperature, current, and voltage, extracts abnormal log categories, counts the number of log occurrences, calculates anomaly weights, and obtains the IDC device status fluctuation.

[0051] The server operation stability assessment module calls the IDC equipment status fluctuation degree to calculate the server operation stability score. It calculates the current status score based on load fluctuation, electrical parameter changes, and abnormal log weights. It also calculates the health status score by combining the number of power outages, current and voltage stability, and number of failures. The module then classifies or categorizes the equipment as operating stably and obtains the IDC equipment operation classification label.

[0052] The IDC equipment anomaly trend prediction module extracts temperature, current, load, and number of abnormal logs from past target periods based on the IDC equipment operation classification tags, calculates the time series trend, determines whether the trend curve is rising, calculates the change in load peak interval, and raises the warning level if the interval is shortened, thus obtaining the IDC equipment anomaly trend prediction value.

[0053] The equipment maintenance priority ranking module calls the abnormal trend prediction value of the IDC equipment, calculates the maintenance priority, and generates a maintenance score by combining the health score, abnormal warning level, and equipment business criticality score. The maintenance plan is arranged according to the score ranking to establish the IDC equipment maintenance priority ranking.

[0054] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0055] This invention optimizes data comprehensiveness and real-time monitoring by synchronously monitoring the current, voltage, power consumption, and temperature of IDC equipment and collecting server operation data. This monitoring strategy provides more refined risk assessment and classification management through dynamic analysis of equipment status fluctuations, thereby improving the accuracy of fault prediction and maintenance efficiency. Comprehensive utilization of anomaly logs and operational data analysis enhances the ability to predict potential problems, effectively reducing system downtime and maintenance costs. Attached Figure Description

[0056] Figure 1 This is a schematic diagram of the workflow of the present invention;

[0057] Figure 2 This is a flowchart illustrating the steps for acquiring IDC device operating status data according to the present invention.

[0058] Figure 3 This is a flowchart illustrating the steps for obtaining the state fluctuation of IDC equipment according to the present invention.

[0059] Figure 4 This is a flowchart illustrating the steps for obtaining the IDC equipment operation classification tags according to the present invention.

[0060] Figure 5 This is a flowchart illustrating the steps for obtaining the predicted abnormal trend value of IDC equipment according to the present invention.

[0061] Figure 6 This is a flowchart illustrating the steps for obtaining the IDC equipment maintenance priority ranking in this invention. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0063] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0064] Example 1

[0065] Please see Figure 1This invention provides a technical solution: a method for intelligent detection and classification management of IDC equipment, comprising the following steps:

[0066] S1: Collect electrical parameters such as server current, voltage, power consumption, and temperature in the IDC rack, record the collected values ​​at the set sampling interval, collect equipment operating status parameters such as CPU utilization, GPU utilization, storage I / O load, and network throughput, and store them in the IDC data monitoring system; detect server logs, extract the number of log entries, error codes, and key parameters, perform character filtering, and store them in the equipment abnormal log database; calculate the rate of change of adjacent sampling points of server current, voltage, and network throughput, mark abrupt change points, and store them; thus obtaining IDC equipment operating status data.

[0067] S2: Based on IDC equipment operating status data, calculate the server load change rate, normalize CPU / GPU load, storage I / O load, and network throughput, determine whether the rate exceeds the set threshold, calculate the first-order difference values ​​of server temperature, current, and voltage in the IDC rack, analyze the change trend at adjacent time points, calculate the mean, determine the degree of fluctuation, extract abnormal log categories, count the number of times the logs of this category have appeared in the past N periods, calculate the abnormal weight, and obtain the IDC equipment status fluctuation degree.

[0068] S3: Call the IDC device status fluctuation rate to calculate the server operation stability score. Use the load fluctuation degree, electrical parameter change rate, and abnormal log weight to calculate the current status score and calculate the server health status score. Calculate the score based on the number of server power outages, current and voltage stability, and historical failure count, and normalize it. Compare the current period operation stability score with the health status score. If the operation stability score is lower than the set threshold and the health status score is low, it is classified as a high-risk IDC device. If the load change rate is normal, electrical parameters are not exceeded, and the health status score is high, it is classified as a stable operating IDC device. Generate IDC device operation classification labels.

[0069] S4: Based on the IDC equipment operation classification tags, extract server temperature, current, load, and number of abnormal logs over the past N collection periods, calculate the time series trend, determine whether the trend curve is rising, calculate the change in server load peak interval, and if the peak interval gradually shortens, increase the abnormal warning level; obtain the IDC equipment abnormal trend prediction value.

[0070] S5: Call the abnormal trend prediction value of IDC equipment, calculate the server maintenance priority, generate a comprehensive maintenance score using server health score, abnormal warning level, and equipment business importance score, and arrange maintenance plans according to the score ranking; establish IDC equipment maintenance priority ranking.

[0071] IDC equipment operating status data specifically includes server current, server voltage, network throughput change rate, and equipment anomaly log storage content. IDC equipment status fluctuation includes server load change rate, current difference value, voltage difference value, temperature difference value, and anomaly log weight. IDC equipment operation classification tags specifically refer to high-risk IDC equipment and stable operating IDC equipment. IDC equipment anomaly trend prediction values ​​specifically include server temperature trend, current trend, load peak interval change, and anomaly log quantity trend. IDC equipment maintenance priority ranking includes server health score, anomaly warning level, and equipment business importance score.

[0072] Please see Figure 2 The specific steps for obtaining IDC device operating status data are as follows:

[0073] S101: Collects current, voltage, power consumption and temperature data of servers in IDC racks, obtains CPU utilization, GPU utilization, storage I / O load and network throughput, records server log entries and stores them in the device abnormal log library, and generates device operating parameter dataset.

[0074] The acquisition of current, voltage, power consumption, and temperature data for servers in the IDC rack is achieved through high-precision current and voltage sensors installed on the server power supply lines, as well as temperature sensors within the rack. The current sensors utilize Hall effect sensors with a sampling frequency set to 100Hz to ensure the capture of high-frequency current fluctuations. The voltage sensors employ a voltage divider measurement circuit and are equipped with an A / D conversion module to convert analog voltage signals into digital signals for storage. Power consumption data is obtained by real-time multiplication of current and voltage signals and stored in a database. Temperature data is acquired from multiple temperature probes within the rack, and a moving average filtering algorithm is used to eliminate instantaneous fluctuations. Furthermore, the acquisition of CPU utilization, GPU utilization, storage I / O load, and network throughput data relies on the server operating system's monitoring module. CPU utilization is obtained by calling the Task Manager interface, recorded once per second, and calculated... Average utilization over the minutes, GPU utilization is collected periodically using NVIDIASMI or AMD RadeonMetrics tools and stored in JSON format, storage I / O load is obtained using Iostat or the system's built-in monitoring, recorded every 10 seconds and stored in the database, network throughput is obtained through the network card traffic statistics module, including uplink and downlink traffic, recorded in Mbps, server log entries are obtained from system logs (Syslog) or Windows event logs (EventViewer), log content includes error codes, alarm information and operation records, exception logs are stored in the device exception log database according to timestamps and indexed to accelerate retrieval for subsequent calls, finally, after data cleaning, these data form a complete device operating parameter dataset, which contains server status information at various times, as shown in Table 1.

[0075] Table 1 Example of Equipment Operating Parameter Dataset

[0076]

[0077] As shown in Table 1, this dataset contains several key parameters such as timestamps, current, voltage, power consumption, and temperature, which can be used to further analyze the server status.

[0078] S102: Based on the device operating parameter dataset, the server current, voltage, and power consumption data are normalized, the average power consumption and fluctuation amplitude within multiple time windows are calculated, and the change in heat dissipation status is calculated by combining server temperature data, using the formula:

[0079]

[0080] Calculate server temperature fluctuation values ​​and generate server heat dissipation status parameters;

[0081] Among them, Stemp T represents the server temperature fluctuation value. i T represents the server temperature in the i-th time window. avg Represents the average temperature, n represents the total number of time windows, and P max P represents the maximum power consumption value. min V represents the minimum power consumption value. avg Represents the average voltage;

[0082] Based on the device operating parameter dataset, the server's current, voltage, and power consumption data are first normalized using minimum-maximum normalization, calculated as follows:

[0083]

[0084] Where X is the original data, X min and X max These represent the minimum and maximum values ​​of the parameter in the dataset, respectively. For example, assuming the power consumption data ranges from 2000W to 3000W, and the power consumption value at a certain moment is 2415W, its normalized value is:

[0085]

[0086] Next, the average power consumption and fluctuation range are calculated over multiple time windows, which are set to 1 minute, 5 minutes, and 10 minutes, and the average power consumption is calculated for each window. and standard deviation σ P Assuming the power consumption data within a 1-minute window is {2400, 2450, 2500, 2420, 2415}W, then:

[0087]

[0088] Then, the change in heat dissipation state S is calculated by combining the server temperature data. temp :

[0089]

[0090] Assuming the temperature data over 5 minutes is {35, 36, 37, 36, 35}℃, the maximum power consumption P max =2500W, minimum power consumption P min =2400W, average voltage V avg =230V, then:

[0091]

[0092] This value represents the server's temperature fluctuation value (S). temp The temperature is low, and under these circumstances, the server's thermal status parameters are within the normal range.

[0093] S103: Based on server heat dissipation status parameters, it calls CPU utilization, GPU utilization, storage I / O load and network throughput data to calculate the changing trends of device power consumption and heat dissipation parameters under different load conditions, extracts abnormal server status characteristics, and generates IDC device operating status data.

[0094] Based on the calculated server heat dissipation state parameter S temp Further analysis was conducted on the trends of power consumption and heat dissipation parameters under different load conditions. Specifically, CPU utilization, GPU utilization, storage I / O load, and network throughput data for different time periods were first selected, and their correlation with power consumption and heat dissipation status was calculated. For example, within a 5-minute time window, the correlation coefficient between each load parameter and power consumption was calculated.

[0095]

[0096] Assuming the calculated value of r is... P,CPU =0.85 indicates a strong positive correlation between CPU load and power consumption. By analyzing data under different load conditions, abnormal server status characteristics can be extracted. For example, if the power consumption is still higher than 2500W under low load (CPU utilization <20%), it indicates that the server may have hardware failure or resource leakage problems. Finally, all data is aggregated to generate IDC equipment operating status data for anomaly detection and intelligent control.

[0097] Please see Figure 3 The specific steps for obtaining the status fluctuation of IDC equipment are as follows:

[0098] S201: Call the IDC device operating status data, calculate the server load change rate within the differentiated time window, calculate the change rate based on the CPU utilization, GPU utilization and storage I / O load of adjacent time periods, and obtain the average and fluctuation range to obtain the server load change rate.

[0099] To retrieve IDC device operational status data, firstly, CPU utilization, GPU utilization, and storage I / O load data at different times are extracted from the database. This data is then divided into time windows (1 minute, 5 minutes, and 10 minutes) to analyze load changes at different time granularities. The rate of load change within adjacent time windows is calculated; specifically, the CPU load change rate R is calculated between time t and t+1. CPU and GPU load change rate R GPU The calculation method is as follows:

[0100]

[0101] Assuming that within a 5-minute time window, CPU utilization is {30, 35, 40, 38, 42}% and GPU utilization is {20, 22, 25, 23, 26}%, then:

[0102]

[0103] After calculating the complete dataset using the method described above, obtain the rate of change within all time windows and calculate the average value. and standard deviation σ R Calculate the load fluctuation amplitude, if the standard deviation σ R If the load exceeds the set threshold (e.g., 10%), it indicates that the server load change rate is large. Through the above process, server load change rate data can be obtained, as shown in Table 1.

[0104] Table 1 Server Load Change Rate Data

[0105]

[0106] As shown in Table 1, this data is used for subsequent calculations of equipment status fluctuations.

[0107] S202: Calculates temperature, current, and voltage fluctuations based on the server load change rate, monitors changes in adjacent data, and uses the following formula:

[0108]

[0109] Calculate the degree of fluctuation in the operating parameters of the equipment;

[0110] Among them, Y dev T represents the degree of fluctuation in the equipment's operating parameters. j T represents the temperature data for time period j. avg I represents the average temperature. j I represents the current data for time period j. avg Represents the average current, V j V represents the voltage data for time period j. avg represents the average voltage, and m represents the number of time windows;

[0111] Based on server load change rate data, temperature, current, and voltage data are extracted within the same time window. The fluctuation values ​​of each parameter in adjacent time windows are calculated. First, the mean value within each time window is calculated:

[0112]

[0113] Then calculate the fluctuation degree Y of the equipment operating parameters. dev :

[0114]

[0115] Assuming the temperature data over 5 minutes is {35, 36, 37, 36, 35}℃, and the current data is...

[0116] Given a voltage of {10.5, 10.8, 10.2, 10.6, 10.4}A and a voltage of {229, 230, 231, 229, 230}V, then:

[0117]

[0118] Calculate fluctuations in temperature, current, and voltage:

[0119]

[0120] This value indicates the degree of fluctuation in the equipment's operating parameters.

[0121] S203: Based on the fluctuation of equipment operating parameters, count the abnormal log entries in the equipment abnormal log library, calculate the number of times abnormal logs occur within the differentiated time window, and combine the fluctuation of temperature, current and voltage to summarize the fluctuation trend of differentiated time periods and obtain the status fluctuation of IDC equipment.

[0122] Based on the calculated Y dev The abnormal log entries in the abnormal log database within the corresponding time window are counted, and the number of occurrences is calculated. The number of logs within the same time window is then filtered out, as shown in Table 2.

[0123] Table 2. Statistics of Abnormal Logs

[0124]

[0125] Based on the degree of equipment status fluctuation, determine whether the number of abnormal log occurrences exceeds a set threshold (e.g., if the number of abnormal log occurrences exceeds 5 within a 5-minute window, it is considered an abnormal state). If it exceeds the set threshold, it indicates that the IDC equipment status fluctuates significantly. Further summarize the fluctuation trend over differentiated time periods. Assume that the statistical results show a high-temperature state (T... avg If the fluctuation level increases significantly at temperatures above 40℃, it can be determined that the high-temperature environment affects the stability of the equipment, and the fluctuation data of the IDC equipment status can be obtained.

[0126] Please see Figure 4 The specific steps for obtaining the category tags for IDC equipment are as follows:

[0127] S301: Based on the state fluctuation of IDC equipment, calculate the stability score of multiple devices, statistically analyze the changes in load fluctuation, electrical parameters and abnormal logs within the differentiated time window, and calculate the stability weight of multiple indicators to obtain the equipment stability score.

[0128] Based on the status fluctuation of IDC devices, the operating status data of multiple devices in different time windows are first extracted, including load fluctuations, electrical parameters (current, voltage, power consumption), and the occurrence of anomaly logs. For each device, the load fluctuation amplitude σ is calculated in each time window. L Electrical parameter variation σ Q and the number of times the exception log appeared (E) k Then, determine the distribution of each parameter across all devices and calculate the stability weight W. k The stability weight is determined based on the equipment's historical operating performance. A higher weight value indicates that the equipment's historical operating fluctuations are smaller. The weight is calculated as follows:

[0129]

[0130] Assume a certain device experiences load fluctuations σ L =5%, electrical parameter fluctuation σ Q =3V, number of exception log entries E k =2, then:

[0131]

[0132] Then, based on the stability weight W of each device k Calculate its stability score S score The scoring method is as follows:

[0133] S score =W k ×(1-σ L )×(1-σ Q )×(1-E k );

[0134] Assuming the equipment load fluctuation σ L =5%, electrical parameter fluctuation σ Q =3V, number of exception log entries E k =2, calculate its stability score:

[0135] S score =0.16×(1-0.05)×(1-0.03)×(1-0.02)=0.16×0.95×0.97×0.98=0.142;

[0136] Finally, the stability scores of all devices are summarized to obtain the overall equipment operational stability score, as shown in Table 3.

[0137] Table 3 Equipment Stability Rating

[0138]

[0139] As shown in Table 3, this score can be used to further calculate the stability deviation value.

[0140] S302: Based on equipment stability scores, analyze the load fluctuations, electrical parameters, and frequency of abnormal logs of multiple devices to calculate the mean and dispersion of the stability scores using the following formula:

[0141]

[0142] Calculate the equipment stability deviation value to obtain the stability and health score;

[0143] Among them, S stab W represents the equipment stability deviation value. k L represents the stability weight of the k-th device. k This represents the load fluctuation value of the k-th device. E represents the average load fluctuation. k Q represents the frequency of abnormal logs for the k-th device. k This represents the electrical parameter value of the k-th device. Represents the average electrical parameters, p represents the total number of devices, and I dev This represents the degree of current fluctuation;

[0144] Based on the equipment stability rating, the rating data for all devices were extracted, and the average rating was calculated. And the degree of dispersion, the mean score is calculated as follows:

[0145]

[0146] Assuming the stability scores of devices A1, A2, and A3 are 0.142, 0.228, and 0.072 respectively, then:

[0147]

[0148] Next, the equipment stability deviation value S is calculated. stab :

[0149]

[0150] Assuming the average load fluctuation Average electrical parameters Current fluctuation level I dev =1.5, then calculate:

[0151]

[0152] Calculate Part Two:

[0153]

[0154] Finally, the equipment stability deviation value S is obtained. stab =1.61.

[0155] S303: Based on stability and health scores, the devices are classified into high-risk devices, low-risk devices, and stable operating devices according to the score range, and their status categories are marked to obtain IDC device operation classification labels.

[0156] Based on stability and health scores, we first define classification labels for the devices, and set the classification criteria as follows:

[0157] High-risk equipment: S stab >2.0;

[0158] Low-risk equipment: 1.0≤S stab ≤2.0;

[0159] Stable operating equipment: S stab <1.0;

[0160] Based on the calculation results of S302, the equipment stability deviation value S stab =1.61, falling into the low-risk range, therefore the equipment is classified as low-risk equipment. For all equipment, calculate its stability deviation value and mark the equipment operation classification label according to the classification criteria, as shown in Table 4.

[0161] Table 4 Equipment Operation Classification Labels

[0162]

[0163] As shown in Table 4, this classification is used to identify the operating status of different devices, and finally obtain the IDC device operating classification label.

[0164] Please see Figure 5 The specific steps for obtaining the predicted abnormal trends of IDC equipment are as follows:

[0165] S401: Based on the IDC equipment operation classification tags, analyze the trends of temperature, current, load and abnormal logs within multiple time windows, calculate the rate of change of multiple device statuses, and obtain device status trend parameters.

[0166] Based on the IDC equipment operation classification labels, historical operation data for each category of equipment is first filtered, including time-series data of temperature, current, load, and anomaly logs. The dataset is then divided according to a set time window (1 minute, 5 minutes, 10 minutes). For each time window, the temperature data T of the equipment is extracted. s Current data I s Load data L s and the number of times the exception log appears (E) α Calculate the rate of change of state for each device, where the load change rate ΔLs The calculation method is as follows:

[0167]

[0168] Assuming the load data for a device within a 5-minute time window is {55, 60, 58, 62, 65}%, calculate the rate of change:

[0169]

[0170] Calculate the status trend parameters of the device:

[0171]

[0172] For the rate of change of current ΔI s and the rate of temperature change ΔT s The calculation method is the same. For example, if the current data is {12.5, 12.8, 12.7, 13.0, 13.2} A and the temperature data is {32, 33, 34, 34, 35} °C, then:

[0173]

[0174] Finally, the rate of change of state for all devices was calculated, and the device state trend parameters were obtained, as shown in Table 5.

[0175] Table 5 Equipment Status Trend Parameters

[0176]

[0177] As shown in Table 5, this data is used to further calculate the load peak variation parameters.

[0178] S402: Based on equipment status trend parameters, analyze the load peak changes of multiple devices, calculate the load peak growth rate and fluctuation range for different time periods, using the formula:

[0179]

[0180] Calculate the load peak change parameters and integrate the load peak change trend;

[0181] Among them, P peak T represents the peak load variation parameter. s T represents the temperature data for time period s. avg I represents the average temperature. s L′ represents the current data for time period s. s Represents the load data for time period s. Represents the average load data, r represents the total number of time windows, and E α This represents the frequency of occurrence in the exception log;

[0182] Based on equipment status trend parameters, temperature, current, and load data for different time windows are extracted, and the load peak change parameter P is calculated. peak The calculation method is as follows:

[0183]

[0184] In this context, we assume that the 5-minute window temperature data for a certain device is {32,33,34,34,35}℃, the current data is {12.5,12.8,12.7,13.0,13.2}A, the load data is {55,60,58,62,65}%, and the number of exception log entries is E. α =3, calculate:

[0185]

[0186] Calculate load fluctuations:

[0187]

[0188] Finally, the peak load variation parameters of all devices are summarized as shown in Table 6.

[0189] Table 6 Load Peak Variation Parameters

[0190]

[0191]

[0192] As shown in Table 6, this data is used to predict future abnormal trends.

[0193] S403: Based on the load peak change trend, summarize the abnormal device status change pattern, calculate the abnormal change magnitude in the future time window, and obtain the IDC device abnormal trend prediction value.

[0194] Based on the load peak change trend, the abnormal equipment status change pattern is summarized, and the abnormal change amplitude in the future time window is calculated. First, historical load fluctuation data of high-risk and low-risk equipment are extracted, and their growth trend is calculated. The load growth rate between time windows t and t+1 is set:

[0195]

[0196] Assuming the load data of a certain device is {55, 60, 65, 68, 72}%, then:

[0197]

[0198] Calculate future load growth trends:

[0199]

[0200] Extrapolate this trend to the next time window:

[0201]

[0202] Finally, the predicted values ​​of abnormal trends of IDC equipment were obtained, as shown in Table 7.

[0203] Table 7 Forecasted Load for Future Time Window

[0204]

[0205] As shown in Table 7, this data is used to identify abnormal trends in advance and ultimately obtain the predicted value of abnormal trends of IDC equipment.

[0206] Please see Figure 6 The specific steps for obtaining the maintenance priority ranking of IDC equipment are as follows:

[0207] S501: Based on the predicted abnormal trends of IDC equipment, calculate the maintenance priority of multiple devices, and obtain the equipment maintenance priority parameters according to the rate of change of abnormal trends and the failure rate of operation.

[0208] Based on the predicted abnormal trends of IDC devices, the abnormal trend change rate U of all devices is first extracted. q And historical operational failure rates, and calculate maintenance priority parameters for each device, and for each device, the abnormal trend change rate U q The load growth rate ΔL and the abnormal log growth rate ΔE of adjacent time windows are determined as follows:

[0209]

[0210] Assuming the load data for device A1 within its time window is {65,70,75,80,85%}% and the number of exception logs is {3,4,5,6,7}, calculate the rate of change:

[0211] ΔL1=70-65=5, ΔL2=75-70=5;

[0212] ΔE1=4-3=1, ΔE2=5-4=1;

[0213]

[0214] Calculate the abnormal trend change rate of all equipment and combine it with the historical operating failure rate to obtain equipment maintenance priority parameters, as shown in Table 8.

[0215] Table 8 Equipment Maintenance Priority Parameters

[0216]

[0217] As shown in Table 8, this data is used to further calculate the maintenance demand index.

[0218] S502: Based on equipment maintenance priority parameters, analyze the urgency of maintenance for multiple devices, calculate the maintenance demand index, and use the following formula:

[0219]

[0220] Calculate the maintenance demand index to obtain the equipment maintenance order adjustment value;

[0221] Among them, M req U represents the maintenance demand index. q R represents the rate of change of the abnormal trend of the q-th device. q W represents the mean of abnormal trends across all devices. q X represents the cumulative failure impact factor of the qth device. q Y represents the load stability index of the q-th device, p represents the total number of devices, and Y represents the load stability index of the q-th device. δ Represents parameters related to equipment status fluctuations;

[0222] Based on the equipment maintenance priority parameter, the abnormal trend change rate U of all equipment is extracted. q And operational failure rate, and calculate the maintenance demand index M. req The calculation method is as follows:

[0223]

[0224] Among them, R q The average of abnormal trends across all devices:

[0225]

[0226] Assume the abnormal trend change rates of devices A1, A2, and A3 are {6.0, 7.2, 5.8}:

[0227]

[0228] Calculate the error term:

[0229]

[0230] Cumulative Failure Impact Factor W of Computing Equipment q and load stability index X q :

[0231]

[0232] Set the device status fluctuation parameter Y δ =0.8, calculate the maintenance demand index:

[0233]

[0234] Finally, the maintenance requirement index of all equipment is summarized as shown in Table 9.

[0235] Table 9 Equipment Maintenance Demand Index

[0236]

[0237]

[0238] As shown in Table 9, this data is used to optimize the equipment maintenance sequence.

[0239] S503: Based on the equipment maintenance order adjustment value, optimize and adjust the equipment maintenance order, and sort according to maintenance priority to obtain the IDC equipment maintenance priority ranking.

[0240] Based on the equipment maintenance order adjustment value, the equipment is sorted according to the maintenance demand index, and the maintenance priority sorting rules are as follows:

[0241] High priority (requires immediate maintenance): M req >0.25;

[0242] Medium priority (short-term maintenance): 0.20≤M req ≤0.25;

[0243] Low priority (routine inspection): M req <0.20;

[0244] According to the calculation results of S502, the maintenance demand index of device A2 is 0.26, which is high priority; the maintenance demand index of device A1 is 0.21, which is medium priority; and the maintenance demand index of device A3 is 0.18, which is low priority. The final IDC device maintenance priority ranking is shown in Table 10.

[0245] Table 10 Equipment Maintenance Priority Ranking

[0246]

[0247] As shown in Table 10, this sorting result is used to determine the maintenance plan for IDC equipment and ultimately obtain the maintenance priority ranking of IDC equipment.

[0248] An intelligent detection and classification management system for IDC equipment, used to execute the aforementioned intelligent detection and classification management method for IDC equipment, the system comprising:

[0249] The device operation status monitoring module collects server current, voltage, power consumption, and temperature data, obtains CPU / GPU utilization, storage I / O load, and network throughput, and stores them in the data monitoring system. It also detects logs to extract error codes and key parameters, filters characters, and stores them in the abnormal log library. The module calculates the adjacent change rate of current, voltage, and network throughput, marks abrupt change points, and stores them to obtain device operation status data.

[0250] The load fluctuation and anomaly analysis module calculates the server load change rate based on the device operating status data, normalizes the CPU / GPU load, storage I / O load, and network throughput, calculates the first-order difference values ​​of server temperature, current, and voltage, extracts the abnormal log categories, counts the number of log occurrences, calculates the anomaly weight, and obtains the IDC device status fluctuation.

[0251] The server operation stability assessment module calls the IDC equipment status fluctuation degree to calculate the server operation stability score. It calculates the current status score based on load fluctuation, electrical parameter changes, and abnormal log weights. It also calculates the health status score by combining the number of power outages, current and voltage stability, and number of failures. The module then classifies or categorizes the equipment as operating stably and obtains the IDC equipment operation classification label.

[0252] The IDC equipment anomaly trend prediction module extracts temperature, current, load, and number of abnormal logs from past target periods based on the IDC equipment operation classification tags, calculates the time series trend, determines whether the trend curve is rising, calculates the change in load peak interval, and raises the warning level if the interval shortens, thus obtaining the IDC equipment anomaly trend prediction value.

[0253] The equipment maintenance priority ranking module calls the IDC equipment anomaly trend prediction value to calculate the maintenance priority. It combines the health score, anomaly warning level, and equipment business criticality score to generate a maintenance score. The module then arranges maintenance plans according to the score ranking and establishes the IDC equipment maintenance priority ranking.

[0254] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A method for intelligent detection and classification management of IDC equipment, characterized in that, Includes the following steps: S1: Collect server current, voltage, power consumption, and temperature in the IDC rack, synchronously record CPU utilization, GPU utilization, storage I / O load, and network throughput, extract server log entries and store them in the device anomaly log database to obtain IDC device operating status data; S2: Call the IDC device's operating status data, analyze the server load change rate, calculate the fluctuation of temperature, current, and voltage, count the number of abnormal log occurrences, and obtain the IDC device's status fluctuation. S3: Calculate the operational stability score based on the state fluctuation of the IDC equipment, analyze load fluctuation, electrical parameters, and abnormal logs, compare the stability and health scores, classify risky and stable operating equipment, and generate IDC equipment operation classification labels; S4: Based on the IDC equipment operation classification tags, analyze the trends of temperature, current, load, and abnormal logs, predict load peak changes, and establish IDC equipment abnormal trend prediction values; S5: Calculate the maintenance priority based on the predicted abnormal trend value of the IDC equipment, adjust the equipment maintenance order, and generate an IDC equipment maintenance priority ranking.

2. The intelligent detection and classification management method for IDC equipment according to claim 1, characterized in that, The IDC equipment operating status data specifically includes server current, server voltage, network throughput change rate, and the contents of the equipment anomaly log database. The IDC equipment status fluctuation includes server load change rate, current difference value, voltage difference value, temperature difference value, and anomaly log weight. The IDC equipment operation classification label specifically refers to high-risk IDC equipment and stable operating IDC equipment. The IDC equipment anomaly trend prediction value specifically includes server temperature trend, current trend, load peak interval change, and anomaly log quantity trend. The IDC equipment maintenance priority ranking includes server health score, anomaly warning level, and equipment business importance score.

3. The intelligent detection and classification management method for IDC equipment according to claim 2, characterized in that, The specific steps for obtaining the IDC device operating status data are as follows: S101: Collects current, voltage, power consumption and temperature data of servers in IDC racks, obtains CPU utilization, GPU utilization, storage I / O load and network throughput, records server log entries and stores them in the device abnormal log library, and generates device operating parameter dataset. S102: Based on the aforementioned device operating parameter dataset, normalize the server current, voltage, and power consumption data, calculate the average power consumption and fluctuation amplitude within multiple time windows, and combine this with server temperature data to calculate the change in heat dissipation status using the following formula: Calculate server temperature fluctuation values ​​and generate server heat dissipation status parameters; Among them, S temp T represents the server temperature fluctuation value. i T represents the server temperature in the i-th time window. avg Represents the average temperature, n represents the total number of time windows, and P max P represents the maximum power consumption value. min V represents the minimum power consumption value. avg Represents the average voltage; S103: Based on the server heat dissipation status parameters, call the CPU utilization rate, GPU utilization rate, storage I / O load and network throughput data, calculate the changing trend of device power consumption and heat dissipation parameters under different load conditions, extract server abnormal state characteristics, and generate IDC device operating status data.

4. The intelligent detection and classification management method for IDC equipment according to claim 3, characterized in that, The specific steps for obtaining the status fluctuation of the IDC equipment are as follows: S201: Call the IDC device operation status data, calculate the server load change rate within the differentiated time window, calculate the change rate of CPU utilization, GPU utilization and storage I / O load based on adjacent time periods, and obtain the average and fluctuation range to obtain the server load change rate. S202: Calculate the fluctuation values ​​of temperature, current, and voltage based on the server load change rate, monitor changes in adjacent data, and use the following formula: Calculate the degree of fluctuation in the operating parameters of the equipment; Among them, Y dev T represents the degree of fluctuation in the equipment's operating parameters. j T represents the temperature data for time period j. avg I represents the average temperature. j I represents the current data for time period j. avg Represents the average current, V j V represents the voltage data for time period j. avg represents the average voltage, and m represents the number of time windows; S203: Based on the fluctuation of the device operating parameters, count the abnormal log entries in the device abnormal log library, calculate the number of times abnormal logs occur within the differentiated time window, and combine the fluctuation of temperature, current and voltage to summarize the fluctuation trend of the differentiated time period and obtain the IDC device status fluctuation.

5. The intelligent detection and classification management method for IDC equipment according to claim 4, characterized in that, The specific steps for obtaining the IDC device operation classification label are as follows: S301: Based on the state fluctuation of the IDC equipment, calculate the stability score of the operation of multiple devices, statistically analyze the changes in load fluctuation, electrical parameters and abnormal logs within the differentiated time window, and calculate the stability weight of multiple indicators to obtain the equipment stability score. S302: Based on the aforementioned equipment stability score, analyze the load fluctuations, electrical parameters, and frequency of abnormal logs of multiple devices, and calculate the mean and dispersion of the stability score using the following formula: Calculate the equipment stability deviation value to obtain the stability and health score; Among them, S stab W represents the equipment stability deviation value. k L represents the stability weight of the k-th device. k This represents the load fluctuation value of the k-th device. E represents the average load fluctuation. k Q represents the frequency of abnormal logs for the k-th device. k This represents the electrical parameter value of the k-th device. Represents the average electrical parameters, p represents the total number of devices, and I dev This represents the degree of current fluctuation; S303: Based on the stability and health scores, classify the devices into high-risk devices, low-risk devices, and stable operating devices according to the score range, and mark their status categories to obtain IDC device operation classification labels.

6. The intelligent detection and classification management method for IDC equipment according to claim 5, characterized in that, The specific steps for obtaining the abnormal trend prediction value of the IDC equipment are as follows: S401: Based on the IDC equipment operation classification tags, analyze the trends of temperature, current, load and abnormal logs within multiple time windows, calculate the rate of change of multiple device statuses, and obtain device status trend parameters; S402: Based on the aforementioned device status trend parameters, analyze the load peak changes of multiple devices, calculate the load peak growth rate and fluctuation range for different time periods, using the formula: Calculate the load peak change parameters and integrate the load peak change trend; Among them, P peak T represents the peak load variation parameter. s T represents the temperature data for time period s. avg I represents the average temperature. s L′ represents the current data for time period s. s Represents the load data for time period s. Represents the average load data, r represents the total number of time windows, and E α This represents the frequency of occurrence in the exception log; S403: Based on the load peak change trend, summarize the abnormal device status change pattern, calculate the abnormal change magnitude in the future time window, and obtain the IDC device abnormal trend prediction value.

7. The intelligent detection and classification management method for IDC equipment according to claim 6, characterized in that, The specific steps for obtaining the maintenance priority ranking of the IDC equipment are as follows: S501: Based on the predicted abnormal trend value of the IDC equipment, calculate the maintenance priority of multiple equipment, and obtain the equipment maintenance priority parameters according to the abnormal trend change rate and operation failure rate of the equipment. S502: Based on the aforementioned equipment maintenance priority parameters, analyze the urgency of maintenance for multiple devices, calculate the maintenance demand index, and use the following formula: Calculate the maintenance demand index to obtain the equipment maintenance order adjustment value; Among them, M req U represents the maintenance demand index. q R represents the rate of change of the abnormal trend of the q-th device. q W represents the mean of abnormal trends across all devices. q X represents the cumulative failure impact factor of the qth device. q Y represents the load stability index of the q-th device, p represents the total number of devices, and Y represents the load stability index of the q-th device. δ Represents parameters related to equipment status fluctuations; S503: Based on the equipment maintenance order adjustment value, optimize and adjust the equipment maintenance order, and sort according to maintenance priority to obtain the IDC equipment maintenance priority ranking.

8. An intelligent detection and classification management system for IDC equipment, characterized in that, The intelligent detection and classification management method for IDC equipment according to any one of claims 1-7, wherein the system comprises: The device operation status monitoring module collects server current, voltage, power consumption, and temperature data, obtains CPU / GPU utilization, storage I / O load, and network throughput, and stores them in the data monitoring system. It also detects logs to extract error codes and key parameters, filters characters, and stores them in the abnormal log library. The module calculates the adjacent change rate of current, voltage, and network throughput, marks abrupt change points, and stores them to obtain device operation status data. Based on the device operating status data, the load fluctuation and anomaly analysis module calculates the server load change rate, normalizes CPU / GPU load, storage I / O load, and network throughput, calculates the first-order difference values ​​of server temperature, current, and voltage, extracts abnormal log categories, counts the number of log occurrences, calculates anomaly weights, and obtains the IDC device status fluctuation. The server operation stability assessment module calls the IDC equipment status fluctuation degree to calculate the server operation stability score. It calculates the current status score based on load fluctuation, electrical parameter changes, and abnormal log weights. It also calculates the health status score by combining the number of power outages, current and voltage stability, and number of failures. The module then classifies or categorizes the equipment as operating stably and obtains the IDC equipment operation classification label. The IDC equipment anomaly trend prediction module extracts temperature, current, load, and number of abnormal logs from past target periods based on the IDC equipment operation classification tags, calculates the time series trend, determines whether the trend curve is rising, calculates the change in load peak interval, and raises the warning level if the interval is shortened, thus obtaining the IDC equipment anomaly trend prediction value. The equipment maintenance priority ranking module calls the abnormal trend prediction value of the IDC equipment, calculates the maintenance priority, and generates a maintenance score by combining the health score, abnormal warning level, and equipment business criticality score. The maintenance plan is arranged according to the score ranking to establish the IDC equipment maintenance priority ranking.

Images