Data center operation temperature monitoring method and monitoring system

Abstract

The invention discloses a data center operation temperature monitoring method and a monitoring system, relates to the technical field of temperature monitoring, is used for solving the problem of abnormal temperature misjudgment caused by temperature adaptive change of the same data center in different positions, and is used for identifying a device combination participating in data storage in the data center and extracting device storage and temperature information. Screening core equipment, collecting the temperature of the core equipment, calculating the overall trend temperature of the equipment combination in combination with the temperature, the operation storage proportion and the calling duration of each marked equipment, extracting the operation temperature characteristic of the current period by utilizing principal component analysis, calculating the temperature time sequence deviation based on a sliding time window, and meanwhile, calculating the temperature time sequence deviation. The method comprises the following steps: acquiring ectopic data of the same equipment combination under different coordinates, constructing an ectopic temperature characteristic model, calculating a temperature bit sequence deviation between a current coordinate and an ectopic characteristic mean value, finally fusing the temperature sequence deviation and the temperature bit sequence deviation to predict the probability of temperature anomaly of a target coordinate in future time, and judging whether to trigger early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature monitoring, and more particularly to a method and system for monitoring the operating temperature of a data center. Background Art

[0002] Temperature monitoring technology is used to detect and record the temperature of the environment, equipment or materials in real time or periodically. When applied to data center operating temperature monitoring, temperature monitoring technology can speed up temperature monitoring response and improve the safety of the data center.

[0003] The existing technology has the following deficiencies:

[0004] Traditional data center temperature monitoring is performed by monitoring the temperature of the core heating device or the entire equipment. This does not take into account that the heating conditions of the data center change over time and space. When two data centers with the same equipment combination are located in two different environmental locations, the temperature requirements will change, resulting in misjudgment of abnormal temperatures and causing data corruption. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a data center operating temperature monitoring method, which determines whether to issue an early warning by analyzing the actual temperature requirements of the data center with the same setting combination at different times and coordinates to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for monitoring the operating temperature of a data center, comprising the following steps:

[0007] Step S1: Obtain a device combination involved in data storage, count the data storage items of each device in the device combination, select the device with the largest data storage item for temperature detection, and record the temperature of the core device in the device combination;

[0008] Step S2: Classify and label each device in the device combination, detect the device temperature of each labeled device, collect the running storage ratio and data call duration of each labeled device to set the label weight, and calculate the overall trend temperature of the device combination by combining the device temperature of the labeled device and the label weight;

[0009] Step S3: Analyze the operating temperature characteristics of the data center based on the core device temperature and the overall trend temperature of the device combination, call historical data, use the historical data to calculate the historical temperature characteristics of the data center, and analyze the temperature time series deviation of the data center in combination with the operating temperature characteristics;

[0010] Step S4: Obtain out-of-situ data for the same device combination, use the out-of-situ data to calculate the out-of-situ temperature characteristics of the data center, analyze the temperature sequence deviation of the data center in combination with the operating temperature characteristics, and integrate the temperature time series deviation and temperature sequence deviation to predict the operating temperature characteristics of the data center.

[0011] In a preferred embodiment, in step S1, all devices involved in data storage are identified as a device group, and data storage item information is read from each device, where the data storage item information is the used storage space of each device; the device with the largest value is selected as the core device;

[0012] Retrieve the temperature data collected by the temperature sensor inside the core device in real time and record it as the core device temperature C of the device combination. c .

[0013] In a preferred embodiment, in step S2, the running storage ratio refers to the ratio of the device running storage space to the total storage capacity of the device;

[0014] By merging the start and end timestamps of the stored data calls in each marking device, the duration of the actual data read and write operations of each marking device is accumulated as the data call duration.

[0015] In a preferred embodiment, in step S2, the data call duration is standardized to generate a data call coefficient, and the tag weight of the corresponding tag device is set according to the data call coefficient and the running storage ratio: i =α×S i +β×T i , where w i is the tag weight of each tag device, S i is the operating storage ratio of each tag device, T i is the proportion of the data call time of each tag device in the unit time, α is the importance coefficient of the running storage ratio, and β is the importance coefficient of the data call time in the unit time;

[0016] The overall trend temperature of the device combination is obtained by taking the weighted average of the real-time temperature of each marked device and the marking weight.

[0017] In a preferred embodiment, in step S3, the operating temperature characteristics of the data center are analyzed based on the core device stability and overall trend temperature of the device combination using a principal component analysis method. The specific steps are as follows:

[0018] Data preparation: Set the core device temperature sequence and overall trend temperature sequence of the current device combination within the time window to form a two-dimensional matrix. Standardize the two-dimensional matrix to generate a standardized sample matrix.

[0019] Covariance matrix calculation: calculate the covariance matrix of the standardized sample matrix;

[0020] Eigenvalue decomposition: Perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues and eigenvectors, and select the eigenvector with the largest eigenvalue as the principal component direction;

[0021] Eigenvalue projection: Project the standardized temperature sample at the current time point t onto the principal component direction to obtain the operating temperature eigenvalue.

[0022] In a preferred embodiment, in step S3, a historical period is selected as the historical analysis time, and multiple time points are set within the historical analysis time to call historical data. The historical data are the core device temperature and the overall trend temperature of the device combination at each time point within the historical analysis time; multiple historical temperature features are generated based on the principal component analysis method and merged into a historical temperature feature sequence.

[0023] In a preferred embodiment, in step S3, a sliding window of length k is set, the historical temperature feature mean of each time point is calculated within the sliding window, and the absolute value of the difference between the temperature feature value at the current time point and the historical temperature feature mean is taken as the temperature time series deviation at the current time point t.

[0024] In a preferred embodiment, in step S4, the ectopic data is the operating data of the current device combination under other operating coordinates. The ectopic temperature characteristics of the data center are calculated using the ectopic data. The core device temperatures and the overall trend temperatures under different operating coordinates are formed into a matrix and normalized. The normalization results are used to generate multiple ectopic temperature characteristics using the principal component analysis method.

[0025] The sliding mean difference of the temperature characteristic value of the current running coordinate L0 relative to the mean of the ectopic temperature characteristic is calculated as the temperature sequence deviation.

[0026] In a preferred embodiment, in step S4, the temperature time series deviation and the temperature position series deviation are used as input features to construct a Bayesian binary classification inference model to perform integrated prediction of the operating temperature characteristics of the data center. The specific steps are as follows:

[0027] Define abnormal events: set the temperature abnormal value Y. When the temperature abnormal value Y=1, the temperature is judged to be abnormal; when the temperature abnormal value Y=0, the temperature is judged to be normal.

[0028] Calculate the probability: define the temperature sequence deviation and temperature sequence deviation as ΔC (tf) and ΔC (L0) , and merge them into deviation data pairs (ΔC (tf) ,ΔC (L0) ), calculate the probability value of temperature anomaly based on the deviation data;

[0029] Abnormal prediction: When the temperature abnormality probability value calculated by the deviation data is lower than the preset optimal judgment boundary, no temperature abnormality warning will be issued; when the temperature abnormality probability value calculated by the deviation data is higher than the preset optimal judgment boundary, a temperature abnormality warning will be issued.

[0030] A data center operating temperature monitoring system includes a device identification module, a tag modeling module, a temperature feature extraction module, and an anomaly prediction module;

[0031] Device identification module: used to identify all devices involved in data storage, count the used storage space of each device in the combination, filter out core devices and obtain temperature readings of their internal temperature sensors;

[0032] Tag modeling module: Classifies and tags non-core devices within the device portfolio, collects the real-time temperature, operating storage ratio, and data call duration per unit cycle for each device, and calculates the overall trend temperature of the device portfolio;

[0033] Temperature feature extraction module: This module uses core device temperature and overall trend temperature as input to generate the current operating temperature feature value. It also uses temperature data within a historical time window to calculate the sliding mean difference between the current operating temperature feature and the historical average, thereby generating a temperature time series deviation indicator for the data center.

[0034] Abnormal prediction module: retrieves monitoring records with the same equipment combination identification but different operating coordinates, extracts the temperature data in the corresponding environment, calculates the difference in temperature characteristics between the current coordinates and multiple historical operating coordinates, and comprehensively considers the temperature time series deviation and temperature position sequence deviation to determine whether to trigger a temperature abnormality warning.

[0035] Technical effects and advantages of the present invention:

[0036] The present invention identifies the device combination involved in data storage in the data center, extracts the device storage and temperature information, screens the core devices and collects their temperatures, calculates the overall trend temperature of the device combination in combination with the temperature, operating storage ratio and call duration of each marked device, reduces the difference between the overall trend temperature and the temperature of the core devices, extracts the operating temperature characteristics of the current cycle by principal component analysis, and calculates the temperature time series deviation based on the sliding time window; at the same time, obtains the heterogeneous data of the same device combination at different coordinates, constructs an heterogeneous temperature feature model, and calculates the temperature sequence deviation between the current coordinate and the mean of the heterogeneous feature; finally, the temperature sequence deviation and the temperature sequence deviation are integrated, and the probability of temperature anomaly at the target coordinate in the future time is predicted by Bayesian inference, and it is determined whether to trigger an early warning, thereby realizing dynamic modeling and anomaly prediction of the operating temperature of the data center, improving the intelligent level of temperature control, and ensuring the safety and energy-saving operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a flow chart of a data center operating temperature monitoring method according to the present invention.

[0038] Figure 2 This is a module diagram of a data center operating temperature monitoring system according to the present invention. DETAILED DESCRIPTION

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0040] The present invention identifies the device combination involved in data storage in the data center, extracts the device storage and temperature information, screens the core devices and collects their temperatures, calculates the overall trend temperature of the device combination by combining the temperature, operating storage ratio and call duration of each marked device, extracts the operating temperature characteristics of the current cycle by principal component analysis, and calculates the temperature time series deviation based on the sliding time window. At the same time, the heterogeneous data of the same device combination at different coordinates is obtained, and an heterogeneous temperature feature model is constructed. The temperature sequence deviation between the current coordinate and the mean of the heterogeneous feature is calculated, and finally the temperature sequence deviation and the temperature sequence deviation are integrated. The probability of temperature anomaly at the target coordinate in the future time is predicted by Bayesian inference, and it is determined whether to trigger an early warning, thereby realizing dynamic modeling and anomaly prediction of the operating temperature of the data center, improving the intelligent level of temperature control, and ensuring the safety and energy-saving operation of the system.

[0041] Example 1, a data center operating temperature monitoring method, such as Figure 1 As shown, the following steps are included:

[0042] Step S1: Obtain a device combination involved in data storage, count the data storage items of each device in the device combination, select the device with the largest data storage item for temperature detection, and record the temperature of the core device in the device combination;

[0043] Step S2: Classify and label each device in the device combination, detect the device temperature of each labeled device, collect the running storage ratio and data call duration of each labeled device to set the label weight, and calculate the overall trend temperature of the device combination by combining the device temperature of the labeled device and the label weight;

[0044] Step S3: Analyze the operating temperature characteristics of the data center based on the core device temperature and the overall trend temperature of the device combination, call historical data, use the historical data to calculate the historical temperature characteristics of the data center, and analyze the temperature time series deviation of the data center in combination with the operating temperature characteristics;

[0045] Step S4: Obtain out-of-situ data for the same device combination, use the out-of-situ data to calculate the out-of-situ temperature characteristics of the data center, analyze the temperature sequence deviation of the data center in combination with the operating temperature characteristics, and integrate the temperature time series deviation and temperature sequence deviation to predict the operating temperature characteristics of the data center.

[0046] The specific implementation is as follows:

[0047] In step S1, the device management platform connected to the data center identifies all devices involved in data storage as a device group and reads data storage item information from each device. The data storage item information is the used storage space of each device.

[0048] Compare the used storage space values of each device, select the device with the largest value as the core device, retrieve the temperature data collected by the temperature sensor inside the core device in real time, and record it as the core device temperature C of the device combination. c .

[0049] It should be noted that the device management platform is a systematic software used to centrally manage and monitor various types of equipment in the data center; the temperature sensor is a physical detection element integrated inside the device, used to sense the temperature of the device and obtain the temperature value.

[0050] In step S2, each device in the device combination is marked as d i (i=1,2,...,n), retrieve the temperature data collected by the temperature sensor inside each device in real time and record it as C i , and at the same time read the running storage space from each tagged device and calculate the running storage ratio. The running storage ratio refers to the ratio of the device's running storage space to the device's total storage capacity, and the calculation formula is: Where S i R is the operating storage ratio, i Run storage space for the device, D i The total storage capacity of the device.

[0051] By merging the start and end timestamps of each data call, the actual duration of the data read and write operations of each tag device is accumulated as the data call duration. The data call duration is standardized based on the proportion of data retrieval time within a fixed monitoring period T. The specific calculation formula is: Among them, T i is the normalized value of the data call duration, is the starting timestamp, is the end timestamp, i represents the device number, j represents the number of times the device calls the event in the period, m is the number of data calls that occur in the device in the current monitoring period, and T is the fixed monitoring period.

[0052] After completing the standardized calculation of the data call time of each marking device, it is input together with the synchronously collected running storage ratio into the marking weight calculation process of each marking device. The specific marking weight calculation formula is: w i =α×S i +β×T i , in this formula, w i is the tag weight of each tag device, S i is the operating storage ratio of each tag device, T i is the proportion of data call time of each tag device in unit time, α is the importance coefficient of running storage ratio, β is the importance coefficient of data call time in unit time, α and β can be adjusted according to actual situation.

[0053] Based on the temperature data and tag weight of each tagged device, a weighted average model is used to calculate the overall trend temperature of the device combination. The specific calculation formula is as follows: Among them, C g is the overall trend temperature of the device combination, n is the number of marked devices participating in the calculation in the current device combination, C gi is the temperature data of the marked device, and w is the marking weight of the marked device.

[0054] It should be noted that the timestamp refers to the absolute time identifier that records the moment a specified event occurs, which is used to accurately identify the time point when a specific event occurs; the parameters of the device combination are continuously collected during operation (including device identification, core equipment, temperature of each device, used storage space, call duration, and device operation coordinates) and uniformly connected to the historical data storage platform of the data center. When performing historical retrospective analysis of temperature characteristics, the unique identification of the device combination and the specified time window are used.

[0055] Through the above weighted calculation, the operating thermal load characteristics of each marked device are aggregated into a unified overall trend temperature indicator, providing a quantifiable data basis for subsequent data center operating temperature characteristic modeling, historical characteristic comparative analysis, and temperature anomaly warning.

[0056] In step S3, the principal component analysis (PCA) method is used to comprehensively analyze the operating temperature characteristics of the equipment combination based on the core equipment temperature and the overall trend temperature of the equipment combination to obtain a quantifiable operating temperature characteristic index. The specific calculation process is as follows:

[0057] First, suppose is the core device temperature sequence collected within the time window of the current device combination, To represent the overall trend temperature sequence within the corresponding time window, the two types of sequence data are constructed into a two-dimensional matrix, which is recorded as: in, is the nth time point data of the core device temperature, is the nth time point data of the overall trend temperature, and n is the number of samples.

[0058] Normalize the input matrix to obtain the standardized sample matrix. The calculation formula is: Among them, X ij is the j-th type of temperature data at the i-th time point (j=1 represents the core device temperature of the device combination, j=2 represents the overall trend temperature of the device combination), μ j is the mean of the j-th class sample, and the calculation formula is σ j is the sample standard deviation of the jth column, and the calculation formula is

[0059] Then the covariance matrix of the standardized sample matrix Z is calculated to obtain the joint variation relationship between the temperature dimensions. The calculation formula is: Among them, Σ is the standardized covariance matrix, Z T is the transpose of the normalized matrix.

[0060] Perform eigenvalue decomposition on the covariance matrix Σ, according to the relationship formula Σ×V k =λ k ×V k (k=1,2), get the corresponding eigenvalue λ k and the eigenvector V k , V1 is the eigenvector with the largest eigenvalue, indicating the direction of maximum variation (i.e., the direction of the principal component), and the first principal component vector V1 is selected as the main direction of the operating temperature feature.

[0061] For the normalized temperature sample at the current time point t Projecting it to the principal component direction, we can obtain the operating temperature eigenvalue: Among them, C (t) is the characteristic value of the operating temperature at the current time point t, is the normalized core temperature at time t, is the standardized overall trend temperature at time point t, V 1ct and V 1gt The weight coefficients corresponding to the core temperature and the overall trend temperature in the principal component vector respectively.

[0062] Select a historical period as the historical analysis time, set multiple time points within the historical analysis time to call historical data. The historical data includes the core device temperature and overall trend temperature of the device combination at each time point within the historical analysis time; generate multiple historical temperature features based on the principal component analysis method and merge them into a historical temperature feature sequence.

[0063] Based on the historical temperature characteristic value sequence generated by principal component analysis, a sliding time window model is constructed to evaluate the dynamic deviation of temperature at different time points. (t-k) ,C (t-k+1) ,...,C (t-1)} is the temperature characteristic value of the first k time points with a sliding window length of k. The mean of the historical temperature characteristic values in the sliding window is calculated. The specific formula is: Where a represents the ath time point going back from the current time point t.

[0064] Then calculate the sliding mean difference of the temperature characteristic value at the current time point relative to the window mean to represent the temperature time series deviation. The calculation formula is: Where, ΔC (t) is the temperature timing deviation at the current time point t.

[0065] After completing the operating temperature feature extraction and temperature time series deviation calculation, a temperature comparison mechanism in the spatial dimension is further introduced to achieve a global steady-state analysis of the data center operating temperature.

[0066] In step S4, the unique identifier of the device combination currently being analyzed is G id , whose running coordinate is L0, and the historical data storage platform is used to retrieve the equipment with the same combination identifier but different running coordinates (such as L1, L2, ..., L m ) monitoring data records, and obtain the operating data of the current equipment combination under other operating coordinates, that is, "extraneous data". Based on the principal component analysis (PCA) method, the core equipment temperature and overall trend temperature of the equipment combination under different operating coordinates are constructed into a matrix in, For equipment combination in position L m The core device temperature under For equipment combination in position L m The overall trend temperature under , m is the number of running coordinates used for analysis.

[0067] Standardize the matrix Y' to obtain the standardized sample matrix. The calculation formula is: Among them, Z ij * is the standardized sample matrix, Y ij′ is the temperature data of the jth type at the ith operating coordinate (j=1 represents the core equipment temperature of the equipment combination, j=2 represents the overall trend temperature of the equipment combination), μ j * is the mean of the j-th class sample, and the calculation formula is σ j * is the sample standard deviation of the jth column, and the calculation formula is

[0068] Standardize the sample matrix Z * Calculate the covariance matrix to obtain the joint variation relationship between temperature dimensions. The calculation formula is: Among them, Σ is the standardized covariance matrix, Z *Τ is the transpose of the normalized matrix.

[0069] Perform eigenvalue decomposition on the covariance matrix Σ, and according to the relationship formula Σ×V=×V, take the eigenvector V corresponding to the maximum eigenvalue as the main direction of the ectopic temperature change.

[0070] For the standardized temperature sample of the current running coordinate projected onto the principal component direction, the ectopic running temperature characteristic value of the current running coordinate L0 is obtained. The specific calculation formula is: in is the characteristic value of the ectopic operation temperature, is the normalized core temperature of the operating coordinate L0, is the normalized overall trend temperature of the running coordinate L0, V cp and V gp The weight coefficients corresponding to the core temperature and the overall trend temperature in the principal component vector respectively.

[0071] Based on the ectopic temperature characteristic value sequence generated by principal component analysis, let It is the average value of the temperature characteristic value of the equipment combination under all the operating coordinates participating in PCA modeling, that is, the mean of the ectopic temperature characteristic value. The specific calculation formula is: in is the mean value of the ectopic temperature characteristic, and b represents the bth running coordinate from the current running coordinate L0.

[0072] Calculate the sliding mean difference of the temperature characteristic value of the current running coordinate L0 relative to the mean of the ectopic temperature characteristic to represent the temperature sequence deviation. The calculation formula is: in, It is the temperature sequence deviation of the current running coordinate L0.

[0073] Timing deviation based on temperature ΔC (t) Temperature sequence deviation The calculation results of the two types of deviation data are used as input features to build a Bayesian two-class inference model to estimate the future time t f The probability of temperature anomalies.

[0074] Assume that the temperature anomaly event is recorded as a binary random variable Y∈{0,1}, where Y=1 means that at time t f If temperature anomaly occurs, Y=0 means no anomaly. The corresponding probability value of temperature anomaly is: in, For deviation data The probability value corresponding to temperature anomaly, P(Y=1) is the prior probability of abnormal events in the training sample, When an abnormality occurs, The conditional probability of the combination occurring, is the marginal probability of the deviated combination in the population sample.

[0075] Using the feature conditional independence assumption, the joint conditional probability is decomposed into: Further, fitting models based on Gaussian distribution are established for temperature timing deviation and position sequence deviation, which are expressed as follows: where y∈{0,1} represents non-abnormal and abnormal situations respectively, Indicates that in the sample with label y The mean and standard deviation of for The mean and standard deviation of the current monitoring point The calculation formula for the predicted probability of temperature anomaly is as follows:

[0076] Set a series of candidate threshold sets {θ j}, j = 1, 2, ..., M, for each threshold, calculate the performance index under the model prediction, and calculate the harmonic mean F1 score of precision and recall. Precision refers to the proportion of actual anomalies among samples predicted to be anomalies, which is marked as S; recall refers to the proportion of successfully predicted anomalies among actual anomalies, which is marked as R; the calculation formula of F1 is Finally, we take the value that makes F1(θ j )The largest threshold is taken as the optimal decision boundary of the system, denoted as θ.

[0077] According to the probability threshold θ, if No temperature abnormality warning is issued, indicating that at the operating coordinate L0 and time t f The risk of temperature anomalies is low; if Then a temperature abnormality warning is issued, indicating that at the operating coordinate L0 and time t fThe risk of temperature anomalies is low.

[0078] Example 2, a data center operating temperature monitoring system, such as Figure 2 As shown, a method for monitoring the operating temperature of a data center is implemented, which includes the following modules: a device identification module, a tag modeling module, a temperature feature extraction module, and an anomaly prediction module. The functions of each module are as follows:

[0079] Device identification module: used to identify all devices involved in data storage, count the used storage space of each device in the combination, filter out core devices and obtain temperature readings of their internal temperature sensors;

[0080] Tag modeling module: Classifies and tags non-core devices within the device portfolio, collects the real-time temperature, operating storage ratio, and data call duration per unit cycle for each device, and calculates the overall trend temperature of the device portfolio;

[0081] Temperature feature extraction module: This module uses core device temperature and overall trend temperature as input to generate the current operating temperature feature value. It also uses temperature data within a historical time window to calculate the sliding mean difference between the current operating temperature feature and the historical average, thereby generating a temperature time series deviation indicator for the data center.

[0082] Abnormal prediction module: retrieves monitoring records with the same equipment combination identification but different operating coordinates, extracts the temperature data in the corresponding environment, calculates the difference in temperature characteristics between the current coordinates and multiple historical operating coordinates, and comprehensively considers the temperature time series deviation and temperature position sequence deviation to determine whether to trigger a temperature abnormality warning.

[0083] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0084] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0085] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0086] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0087] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0088] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0089] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0090] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0091] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0092] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for monitoring operating temperature of a data center, characterized by: The following steps are involved: Step S1: Obtain a device combination involved in data storage, count the data storage items of each device in the device combination, select the device with the largest data storage item for temperature detection, and record the temperature of the core device in the device combination; Step S2: Classify and label each device in the device combination, detect the device temperature of each labeled device, collect the running storage ratio and data call duration of each labeled device to set the label weight, and calculate the overall trend temperature of the device combination by combining the device temperature of the labeled device and the label weight; Step S3: Analyze the operating temperature characteristics of the data center based on the core device temperature and the overall trend temperature of the device combination, call historical data, use the historical data to calculate the historical temperature characteristics of the data center, and analyze the temperature time series deviation of the data center in combination with the operating temperature characteristics; Step S4: Obtain out-of-situ data for the same device combination, use the out-of-situ data to calculate the out-of-situ temperature characteristics of the data center, analyze the temperature sequence deviation of the data center in combination with the operating temperature characteristics, and integrate the temperature time series deviation and temperature sequence deviation to predict the operating temperature characteristics of the data center.

2. A data center operating temperature monitoring method according to claim 1, characterized in that: In step S1, all devices involved in data storage are identified as a device group, and data storage item information is read from each device. The data storage item information is the used storage space of each device; the device with the largest value is selected as the core device; Retrieve the temperature data collected by the temperature sensor inside the core device in real time and record it as the core device temperature C of the device combination. c .

3. The data center operating temperature monitoring method according to claim 1, characterized in that: In step S2, the running storage ratio refers to the ratio of the device running storage space to the total storage capacity of the device; By merging the start and end timestamps of the stored data calls in each marking device, the duration of the actual data read and write operations of each marking device is accumulated as the data call duration.

4. A data center operating temperature monitoring method according to claim 3, characterized in that: In step S2, the data call duration is standardized to generate a data call coefficient, and the tag weight of the corresponding tag device is set according to the data call coefficient and the running storage ratio: w i =α×S i +β×T i , where w i is the tag weight of each tag device, S i is the operating storage ratio of each tag device, T i is the proportion of the data call time of each tag device in the unit time, α is the importance coefficient of the running storage ratio, and β is the importance coefficient of the data call time in the unit time; The overall trend temperature of the device combination is obtained by taking the weighted average of the real-time temperature of each marked device and the marking weight.

5. A data center operating temperature monitoring method according to claim 4, characterized in that: In step S3, the principal component analysis method is used to analyze the operating temperature characteristics of the data center based on the core equipment stability and overall trend temperature of the equipment combination. The specific steps are as follows: Data preparation: Set the core device temperature sequence and overall trend temperature sequence of the current device combination within the time window to form a two-dimensional matrix. Standardize the two-dimensional matrix to generate a standardized sample matrix. Covariance matrix calculation: calculate the covariance matrix of the standardized sample matrix; Eigenvalue decomposition: Perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues and eigenvectors, and select the eigenvector with the largest eigenvalue as the principal component direction; Eigenvalue projection: Project the standardized temperature sample at the current time point t onto the principal component direction to obtain the operating temperature eigenvalue.

6. A data center operating temperature monitoring method according to claim 5, characterized in that: In step S3, a historical period is selected as the historical analysis time, and multiple time points are set within the historical analysis time to call historical data. The historical data are the core device temperature and the overall trend temperature of the device combination at each time point within the historical analysis time; multiple historical temperature features are generated based on the principal component analysis method and merged into a historical temperature feature sequence.

7. A data center operating temperature monitoring method according to claim 6, characterized in that: In step S3, a sliding window of length k is set, and the historical temperature feature mean of each time point is calculated within the sliding window. The absolute value of the difference between the temperature feature value at the current time point and the historical temperature feature mean is taken as the temperature time series deviation at the current time point t.

8. A data center operating temperature monitoring method according to claim 7, characterized in that: In step S4, the ectopic data is the operating data of the current equipment combination under other operating coordinates. The ectopic temperature characteristics of the data center are calculated using the ectopic data. The core equipment temperature and the overall trend temperature under different operating coordinates are constructed into a matrix and normalized. The normalization result is used to generate multiple ectopic temperature characteristics using the principal component analysis method; The sliding mean difference of the temperature characteristic value of the current running coordinate L0 relative to the mean of the ectopic temperature characteristic is calculated as the temperature sequence deviation.

9. A data center operating temperature monitoring method according to claim 8, characterized in that: In step S4, the temperature time series deviation and temperature position series deviation are used as input features to build a Bayesian binary classification inference model to perform integrated prediction of the operating temperature characteristics of the data center. The specific steps are as follows: Define abnormal events: set the temperature abnormal value Y. When the temperature abnormal value Y=1, the temperature is judged to be abnormal; when the temperature abnormal value Y=0, the temperature is judged to be normal. Calculate the probability: define the temperature sequence deviation and temperature sequence deviation as ΔC (tf) and ΔC (L0) , and merge them into deviation data pairs (ΔC (tf) ,ΔC (L0) ), calculate the probability value of temperature anomaly based on the deviation data; Abnormal prediction: When the temperature abnormality probability value calculated by the deviation data is lower than the preset optimal judgment boundary, no temperature abnormality warning will be issued; When the temperature anomaly probability value calculated by the deviation data is higher than the preset optimal judgment boundary, a temperature anomaly warning is issued.

10. A data center operating temperature monitoring system, based on a data center operating temperature monitoring method according to any one of claims 1 to 9, characterized in that: It includes device identification module, tag modeling module, temperature feature extraction module and anomaly prediction module; Device identification module: used to identify all devices involved in data storage, count the used storage space of each device in the combination, filter out core devices and obtain temperature readings of their internal temperature sensors; Tag modeling module: Classifies and tags non-core devices within the device portfolio, collects the real-time temperature, operating storage ratio, and data call duration per unit cycle for each device, and calculates the overall trend temperature of the device portfolio; Temperature feature extraction module: This module uses core device temperature and overall trend temperature as input to generate the current operating temperature feature value. It also uses temperature data within a historical time window to calculate the sliding mean difference between the current operating temperature feature and the historical average, thereby generating a temperature time series deviation indicator for the data center. Abnormal prediction module: retrieves monitoring records with the same equipment combination identification but different operating coordinates, extracts the temperature data in the corresponding environment, calculates the difference in temperature characteristics between the current coordinates and multiple historical operating coordinates, and comprehensively considers the temperature time series deviation and temperature position sequence deviation to determine whether to trigger a temperature abnormality warning.

Images