Data center power supply information monitoring method and system based on UPS

Abstract

The present invention discloses a data center power supply information supervision method and system based on UPS, belonging to the technical field of power supply information supervision. The system of the present invention comprises: a data acquisition module, a data processing and analysis module, a correlation modeling module, a real-time monitoring module and an information output and feedback module; the data acquisition module acquires the historical operation data, power supply records and maintenance logs of the UPS device; the data processing and analysis module performs data analysis and processing according to the historical operation data and power supply records; the correlation modeling module establishes a correlation model; the real-time monitoring module monitors the power supply records and real-time operation data of the UPS device in real time, and analyzes the above data; the information output and feedback module sends prompt information to relevant personnel when an abnormal situation occurs.

Description

Technical Field

[0001] The present invention relates to the technical field of power supply information supervision, and in particular to a UPS-based data center power supply information supervision method and system. Background Art

[0002] In today's society, with the deepening of digital transformation, the status of data centers is becoming increasingly important. As the core of the information system of enterprises and institutions, data centers carry a large amount of data processing, storage and transmission tasks, and are key facilities to ensure business continuity and data security. UPS (uninterruptible power supply), as an important backup power supply device, is widely used in data centers. UPS can quickly switch to backup power supply when the main power supply fails, ensuring that data center equipment can still get a continuous and stable power supply when the power is interrupted, thereby avoiding data loss and business interruption.

[0003] However, the existing technology for the supervision of UPS power supply systems still has the following deficiencies: although UPS equipment can provide continuous and stable power supply when the main power fails, the maintenance of UPS equipment is often carried out according to a fixed cycle. Therefore, during the maintenance process of UPS equipment, maintenance may be carried out when the equipment is actually not needed, thereby wasting limited maintenance resources; unexpected shutdown or performance degradation may also occur due to failure to discover the fault in time, resulting in the inability to provide stable power support at critical moments. Summary of the invention

[0004] The purpose of the present invention is to provide a UPS-based data center power supply information monitoring method and system to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] A data center power supply information monitoring method based on UPS, the method comprising the following steps:

[0007] Step S100. Obtain historical operation data, power supply records and maintenance logs of UPS devices from the data center management platform, divide the historical operation data into several historical operation data segments according to the power supply records of the UPS devices, and obtain the operation data reference baseline in combination with the UPS device maintenance events recorded in the maintenance log;

[0008] Step S200. Based on the operating data reference baseline, analyze the operating data reference baseline of each historical operating data segment to obtain the historical operating data deviation index;

[0009] Step S300. Based on the UPS device usage time recorded in the power supply, the historical operation data deviation index and the UPS device usage time are analyzed to obtain the correlation between the historical operation data deviation index and the UPS device usage time;

[0010] Step S400. Monitor the power supply record of the UPS device in real time. Each time the power supply record is updated, the real-time operation data of the corresponding UPS device is obtained to obtain the real-time operation data deviation index; according to the current power supply record, the current UPS device usage time is obtained, and the correlation between the historical operation data deviation index and the UPS device usage time is combined to output the corresponding information to relevant personnel.

[0011] Furthermore, step S100 includes:

[0012] S101. The historical operation data refers to the operation status record of the UPS device in the past period of time, and the past period of time refers to the time point when the UPS device was put into use to the time point when the UPS device was eliminated and stopped using; including the changes in parameters such as voltage fluctuation, frequency stability, load size, load fluctuation, etc., which are usually recorded and stored through the data center management platform; the power supply record refers to the power supply status record of the UPS device; including the power supply source, power supply stability, power supply interruption, etc. The power supply record records and tracks the power supply received by the UPS device in order to analyze the operation of the UPS device under different power supply conditions; the maintenance log is a record of events during the maintenance and repair of the UPS device; including maintenance date, repair content, replacement parts and other information. The maintenance log records the maintenance history of the UPS device, which can be used to analyze the maintenance status of the UPS device and possible fault points, and provide a reference for subsequent operation and maintenance decisions;

[0013] S102. According to the power supply record of the UPS device, the historical operation data is divided into several historical operation data segments, and the time period of each historical operation data segment corresponds to the time period of a power supply record; according to the UPS device maintenance event recorded in the maintenance log, the time point t corresponding to the UPS device maintenance event is obtained, and the time point t corresponding to the UPS device maintenance event is matched with the historical operation data segment closest to the time point t; the historical operation data segment corresponding to the time point t that does not correspond to the UPS device maintenance event is used as the historical operation data benchmark segment, and the historical operation data segment corresponding to the time point t corresponding to the UPS device maintenance event is used as the historical operation data fluctuation segment;

[0014] S103. Extract all historical operation data benchmark segments, and analyze the data points corresponding to each historical operation data benchmark segment. The specific analysis process is as follows:

[0015] For each historical operating data benchmark segment, calculate the mean value μ and standard deviation σ to obtain the upper limit Y1 and lower limit Y2 of the operating data baseline. The specific calculation formula is: Y1=μ+a*σ, Y2=μ+a*σ, where a represents the coefficient; calculate the mean value and standard deviation of skewness S and kurtosis K to obtain the upper limit Y3 and Y5 and lower limit Y4 and Y6 of the operating data baseline. The specific calculation formula is: Y3=μ+(S_μ+f_s*S_σ), Y4=μ-(S_μ+f_s*S_σ), Y5=μ+(K_μ+f_k*K_σ), Y6=μ-(K_μ+f_k*K_σ); where S_μ and S_σ represent the mean value and standard deviation of skewness S, respectively, and K_μ and K_σ represent the mean value and standard deviation of kurtosis K, respectively. , f_s and f_k represent the correction factors of skewness S and kurtosis K respectively; for the baselines Y1 and Y2 based on the mean and standard deviation, and the baselines Y3 to Y6 based on the skewness and kurtosis, the upper limits of all baselines are taken as the maximum value Y_max, and the lower limits are taken as the minimum value Y_min, so as to obtain the baseline range of each historical operation data baseline segment; according to the baseline range, the data points of the historical operation data baseline segment that do not belong to the baseline range are screened out, so as to represent the remaining data points of the historical operation data baseline segment in a plane rectangular coordinate system, and the horizontal axis of the plane rectangular coordinate system represents the time point of the historical operation data, and the horizontal axis represents the data points corresponding to the historical operation data; the data points are connected according to the time point sequence, so as to obtain the operation data baseline;

[0016] The operating data baseline corresponding to each historical operating data baseline segment is obtained, the operating data baseline is represented in the same rectangular coordinate system, and the horizontal coordinates of the initial points of all the operating data baselines are matched, so as to fit into an operating data reference baseline.

[0017] Further, step S200 includes:

[0018] S201. Representing all data points of the historical operation data segments in the same plane rectangular coordinate system to obtain a historical operation data trend curve; and dividing the historical operation data trend curve into several historical operation data trend curve segments according to the time period of the historical operation data segments;

[0019] S202. The horizontal coordinate of the initial point of the historical operation data trend curve corresponds to the operation data reference baseline, so as to calculate the deviation of each historical operation data trend curve segment to obtain the historical operation data deviation index R. The specific calculation formula is:

[0020] ,

[0021] Where n is the number of data points in the trend curve of historical operation data. Represents the value of the i-th data point of the historical running data trend curve segment, Represents the value of the i-th data point of the corresponding running data reference baseline.

[0022] Furthermore, step S300 includes:

[0023] S301.Acquire the UPS device usage time T0 of each historical operation data segment according to the power supply record, arrange all historical operation data segments in chronological order, calculate the cumulative usage time Tc of the UPS device corresponding to each historical operation data segment, and Tc_m=Tc_m-1+T0_m, where Tc_m represents the cumulative usage time Tc of the UPS device corresponding to the m-th historical operation data segment, Tc_m-1 represents the cumulative usage time Tc of the UPS device corresponding to the m-1th historical operation data segment, and T0_m represents the usage time T0 of the UPS device of the m-th historical operation data segment;

[0024] S302. For each historical operation data segment, the corresponding UPS device cumulative usage time Tc and historical operation data deviation index R are extracted to form the coordinate point of (Tc, R); the (Tc, R) corresponding to all historical operation data segments are extracted, and all (Tc, R) coordinate points are plotted on a scatter plot, and regression analysis is performed using statistical software to fit the regression model to obtain the correlation expression: G(R)=f(Tc), where f( ) represents the correlation function. For example, the correlation expression: R=β0+β1*Tc+ε, where β0 and β1 represent regression coefficients, which are used to describe the slope and intercept of the linear relationship between R and Tc; ε represents the error term.

[0025] Furthermore, step S400 includes:

[0026] S401 real-time monitoring of UPS equipment power supply records, power supply records are updated every time, the corresponding UPS equipment real-time operation data as real-time operation data fragment; with reference to the historical operation data fragment calculation process of the historical operation data deviation index, calculate the real-time operation data deviation index R1;

[0027] S402. According to the current power supply record, the current UPS device usage time is obtained, so as to obtain the UPS device cumulative usage time Tc1 corresponding to the current real-time operation data segment; according to the correlation expression between the historical operation data deviation index and the UPS device usage time, the UPS device cumulative usage time Tc1 is input to obtain the predicted operation data deviation index R2;

[0028] S403. If the relationship between the real-time operation data deviation index R1 and the predicted operation data deviation index R2 is: |R1-R2|≤e*(R0_max-R0_min), where e represents the deviation factor, output prompt information of normal use of UPS equipment to relevant personnel; if the relationship between the real-time operation data deviation index R1 and the predicted operation data deviation index R2 is: |R1-R2|>e*(R0_max-R0_min), output prompt information of UPS equipment abnormality to relevant personnel, and have the relevant personnel repair the UPS equipment.

[0029] The data center power supply information supervision system based on UPS includes: data acquisition module, data processing and analysis module, correlation relationship modeling module, real-time monitoring module and information output and feedback module;

[0030] The data acquisition module obtains the historical operation data, power supply records and maintenance logs of the UPS equipment from the data center management platform and integrates them into a usable data format;

[0031] The data processing and analysis module divides the historical operation data into several historical operation data segments according to the power supply records of the UPS equipment, and combines the UPS equipment maintenance events recorded in the maintenance log to obtain the operation data reference baseline and calculate the historical operation data deviation index;

[0032] The correlation modeling module establishes a correlation model based on the correlation between the historical operation data deviation index and the UPS equipment usage time;

[0033] The real-time monitoring module monitors the power supply record of the UPS device in real time, obtains the real-time operation data of the corresponding UPS device, thereby obtaining the real-time operation data deviation index, and predicts the real-time operation data deviation index according to the correlation model;

[0034] The information output and feedback module determines whether the operating status of the UPS device is normal based on the real-time operating data deviation index and the predicted real-time operating data deviation index. When an abnormal situation occurs, a prompt message is sent to relevant personnel.

[0035] Further, the data acquisition module includes a data acquisition unit and a data transmission unit;

[0036] The data acquisition unit obtains historical operation data, power supply records and maintenance logs from the UPS equipment and the data center management platform; the data transmission unit transmits the collected data to the data processing and analysis module.

[0037] The data processing and analysis module includes a data segmentation unit, a reference baseline generation unit, and a deviation index calculation unit;

[0038] The data segmentation unit divides the historical operation data into a plurality of historical operation data segments; the reference baseline generation unit combines the maintenance log and the historical operation data segments to generate a reference baseline for the historical operation data; and the deviation index calculation unit calculates the deviation index of the historical operation data.

[0039] Furthermore, the real-time monitoring module includes a real-time data acquisition unit, a real-time deviation index prediction unit, and an operation status judgment unit;

[0040] The real-time data acquisition unit acquires the real-time operation data and power supply records of the UPS device and calculates the deviation index of the real-time operation data; the real-time deviation index prediction unit predicts the deviation index of the real-time operation data according to the historical correlation model; the operation status judgment unit judges whether the operation status of the UPS device is normal according to the real-time deviation index and the reference baseline.

[0041] Furthermore, the information output and feedback module includes a normal use prompt unit and an abnormal use prompt unit;

[0042] The normal use prompt unit outputs corresponding prompt information when the UPS device is operating normally; the abnormal prompt unit outputs corresponding warning information when the UPS device is abnormal and notifies relevant personnel to handle it.

[0043] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0044] By combining the historical operation data of the UPS device with the power supply records and maintenance logs, the present invention can determine the reference baseline of the operation data and formulate an accurate maintenance strategy based on it; compared with fixed-cycle maintenance, this method can more accurately determine the maintenance timing, avoid unnecessary maintenance and waste of resources, and ensure timely maintenance when needed, reducing the risk of unexpected downtime;

[0045] The present invention can obtain the status information of the equipment at any time by real-time monitoring of the power supply record and real-time operation data of the UPS equipment, and provide real-time operation and maintenance guidance by combining the correlation between the deviation index of the historical operation data and the usage time; this real-time monitoring and feedback mechanism helps to timely discover equipment abnormalities and take corresponding measures, thereby improving the reliability and stability of the UPS equipment;

[0046] By avoiding unnecessary maintenance and timely discovering UPS equipment problems, the present invention can optimize the use of maintenance resources and reduce maintenance costs; at the same time, by reducing the risk of unexpected downtime, it can save production losses and business interruption costs caused by downtime, thereby achieving comprehensive cost-saving benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0048] Figure 1 It is a schematic diagram of the module of the data center power supply information monitoring system based on UPS of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0050] See also Figure 1 , the present invention provides a technical solution:

[0051] The data center power supply information supervision system based on UPS includes: data acquisition module, data processing and analysis module, correlation relationship modeling module, real-time monitoring module and information output and feedback module;

[0052] The data acquisition module obtains the historical operation data, power supply records and maintenance logs of the UPS equipment from the data center management platform and integrates them into a usable data format;

[0053] The data processing and analysis module divides the historical operation data into several historical operation data segments according to the power supply records of the UPS equipment, and combines the UPS equipment maintenance events recorded in the maintenance log to obtain the operation data reference baseline and calculate the historical operation data deviation index;

[0054] The correlation modeling module establishes a correlation model based on the correlation between the historical operation data deviation index and the UPS equipment usage time;

[0055] The real-time monitoring module monitors the power supply record of the UPS device in real time, obtains the real-time operation data of the corresponding UPS device, thereby obtaining the real-time operation data deviation index, and predicts the real-time operation data deviation index according to the correlation model;

[0056] The information output and feedback module determines whether the operating status of the UPS device is normal based on the real-time operating data deviation index and the predicted real-time operating data deviation index. When an abnormal situation occurs, a prompt message is sent to relevant personnel.

[0057] The data acquisition module includes a data acquisition unit and a data transmission unit;

[0058] The data acquisition unit obtains historical operation data, power supply records and maintenance logs from the UPS equipment and the data center management platform; the data transmission unit transmits the collected data to the data processing and analysis module.

[0059] The data processing and analysis module includes a data segmentation unit, a reference baseline generation unit, and a deviation index calculation unit;

[0060] The data segmentation unit divides the historical operation data into a plurality of historical operation data segments; the reference baseline generation unit combines the maintenance log and the historical operation data segments to generate a reference baseline for the historical operation data; and the deviation index calculation unit calculates the deviation index of the historical operation data.

[0061] The real-time monitoring module includes a real-time data acquisition unit, a real-time deviation index prediction unit, and an operation status judgment unit;

[0062] The real-time data acquisition unit acquires the real-time operation data and power supply records of the UPS device and calculates the deviation index of the real-time operation data; the real-time deviation index prediction unit predicts the deviation index of the real-time operation data according to the historical correlation model; the operation status judgment unit judges whether the operation status of the UPS device is normal according to the real-time deviation index and the reference baseline.

[0063] The information output and feedback module includes a normal use prompt unit and an abnormal use prompt unit;

[0064] The normal use prompt unit outputs corresponding prompt information when the UPS device is operating normally; the abnormal prompt unit outputs corresponding warning information when the UPS device is abnormal and notifies relevant personnel to handle it.

[0065] A data center power supply information monitoring method based on UPS, the method comprising the following steps:

[0066] Step S100. Obtain historical operation data, power supply records and maintenance logs of UPS devices from the data center management platform, divide the historical operation data into several historical operation data segments according to the power supply records of the UPS devices, and obtain the operation data reference baseline in combination with the UPS device maintenance events recorded in the maintenance log;

[0067] Step S200. Based on the operating data reference baseline, each historical operating data segment is analyzed in combination with the operating data reference baseline to obtain a historical operating data deviation index;

[0068] Step S300. Based on the UPS device usage time recorded in the power supply, the historical operation data deviation index and the UPS device usage time are analyzed to obtain the correlation between the historical operation data deviation index and the UPS device usage time;

[0069] Step S400. Monitor the power supply record of the UPS device in real time. Each time the power supply record is updated, the real-time operation data of the corresponding UPS device is obtained to obtain the real-time operation data deviation index; according to the current power supply record, the current UPS device usage time is obtained, and the correlation between the historical operation data deviation index and the UPS device usage time is combined to output the corresponding information to relevant personnel.

[0070] Step S100 includes:

[0071] S101. The historical operation data refers to the operation status record of the UPS device in the past period of time, and the past period of time refers to the time point when the UPS device was put into use to the time point when the UPS device was eliminated and stopped using; including the changes in parameters such as voltage fluctuation, frequency stability, load size, load fluctuation, etc., which are usually recorded and stored through the data center management platform; the power supply record refers to the power supply status record of the UPS device; including the power supply source, power supply stability, power supply interruption, etc. The power supply record records and tracks the power supply received by the UPS device in order to analyze the operation of the UPS device under different power supply conditions; the maintenance log is a record of events during the maintenance and repair of the UPS device; including maintenance date, repair content, replacement parts and other information. The maintenance log records the maintenance history of the UPS device, which can be used to analyze the maintenance status of the UPS device and possible fault points, and provide a reference for subsequent operation and maintenance decisions;

[0072] S102. According to the power supply record of the UPS device, the historical operation data is divided into several historical operation data segments, and the time period of each historical operation data segment corresponds to the time period of a power supply record; according to the UPS device maintenance event recorded in the maintenance log, the time point t corresponding to the UPS device maintenance event is obtained, and the time point t corresponding to the UPS device maintenance event is matched with the historical operation data segment closest to the time point t; the historical operation data segment corresponding to the time point t that does not correspond to the UPS device maintenance event is used as the historical operation data benchmark segment, and the historical operation data segment corresponding to the time point t corresponding to the UPS device maintenance event is used as the historical operation data fluctuation segment;

[0073] S103. Extract all historical operation data benchmark segments, and analyze the data points corresponding to each historical operation data benchmark segment. The specific analysis process is as follows:

[0074] For each historical operating data benchmark segment, calculate the mean value μ and standard deviation σ to obtain the upper limit Y1 and lower limit Y2 of the operating data baseline. The specific calculation formula is: Y1=μ+a*σ, Y2=μ+a*σ, where a represents the coefficient; calculate the mean value and standard deviation of skewness S and kurtosis K to obtain the upper limit Y3 and Y5 and lower limit Y4 and Y6 of the operating data baseline. The specific calculation formula is: Y3=μ+(S_μ+f_s*S_σ), Y4=μ-(S_μ+f_s*S_σ), Y5=μ+(K_μ+f_k*K_σ), Y6=μ-(K_μ+f_k*K_σ); where S_μ and S_σ represent the mean value and standard deviation of skewness S, respectively, and K_μ and K_σ represent the mean value and standard deviation of kurtosis K, respectively. , f_s and f_k represent the correction factors of skewness S and kurtosis K respectively; for the baselines Y1 and Y2 based on the mean and standard deviation, and the baselines Y3 to Y6 based on the skewness and kurtosis, the upper limits of all baselines are taken as the maximum value Y_max, and the lower limits are taken as the minimum value Y_min, so as to obtain the baseline range of each historical operation data baseline segment; according to the baseline range, the data points of the historical operation data baseline segment that do not belong to the baseline range are screened out, so as to represent the remaining data points of the historical operation data baseline segment in a plane rectangular coordinate system, and the horizontal axis of the plane rectangular coordinate system represents the time point of the historical operation data, and the horizontal axis represents the data points corresponding to the historical operation data; the data points are connected according to the time point sequence, so as to obtain the operation data baseline;

[0075] The operating data baseline corresponding to each historical operating data baseline segment is obtained, the operating data baseline is represented in the same rectangular coordinate system, and the horizontal coordinates of the initial points of all the operating data baselines are matched, so as to fit into an operating data reference baseline.

[0076] In this embodiment, it is assumed that there is a historical running data benchmark segment, which contains the following data points: [10, 12, 14, 16, 18, 20, 22, 24, 26, 28];

[0077] Calculate the mean μ and standard deviation σ:

[0078] ;

[0079] ;

[0080] Determine the baseline range:

[0081] Assuming coefficient a=1.5, the upper limit Y1=19+1.5*6=28, the lower limit Y2 =19-1.5*6=28= 10;

[0082] Calculate the skewness S and kurtosis K, and calculate the mean and standard deviation of the skewness and kurtosis;

[0083] Determine the baseline range:

[0084] Assuming the correction factors f_S=0.5 and f_K=0.25, the upper limit Y3=μ+(S_μ+f_s*S_σ), the lower limit Y4=μ-(S_μ+f_s*S_σ), the upper limit Y5=μ+(K_μ+f_k*K_σ), the lower limit Y6=μ-(K_μ+f_k*K_σ);

[0085] Comprehensive baseline range:

[0086] By comprehensively considering the baselines Y1 and Y2 based on the mean and standard deviation, and the baselines Y3 to Y6 based on the skewness and kurtosis, the upper limit Y_max and lower limit Y_min of the final operating data baseline can be obtained.

[0087] Step S200 includes:

[0088] S201. Representing all data points of the historical operation data segments in the same plane rectangular coordinate system to obtain a historical operation data trend curve; and dividing the historical operation data trend curve into several historical operation data trend curve segments according to the time period of the historical operation data segments;

[0089] S202. The horizontal coordinate of the initial point of the historical operation data trend curve corresponds to the operation data reference baseline, so as to calculate the deviation of each historical operation data trend curve segment to obtain the historical operation data deviation index R. The specific calculation formula is:

[0090] ,

[0091] Where n is the number of data points in the trend curve of historical operation data. Represents the value of the i-th data point of the historical running data trend curve segment, Represents the value of the i-th data point of the corresponding running data reference baseline.

[0092] Step S300 includes:

[0093] S301.Acquire the UPS device usage time T0 of each historical operation data segment according to the power supply record, arrange all historical operation data segments in chronological order, calculate the cumulative usage time Tc of the UPS device corresponding to each historical operation data segment, and Tc_m=Tc_m-1+T0_m, where Tc_m represents the cumulative usage time Tc of the UPS device corresponding to the m-th historical operation data segment, Tc_m-1 represents the cumulative usage time Tc of the UPS device corresponding to the m-1th historical operation data segment, and T0_m represents the usage time T0 of the UPS device of the m-th historical operation data segment;

[0094] S302. For each historical operation data segment, the corresponding UPS device cumulative usage time Tc and historical operation data deviation index R are extracted to form the coordinate point of (Tc, R); the (Tc, R) corresponding to all historical operation data segments are extracted, and all (Tc, R) coordinate points are plotted on a scatter plot, and regression analysis is performed using statistical software to fit the regression model to obtain the correlation expression: G(R)=f(Tc), where f( ) represents the correlation function. For example, the correlation expression: R=β0+β1*Tc+ε, where β0 and β1 represent regression coefficients, which are used to describe the slope and intercept of the linear relationship between R and Tc; ε represents the error term.

[0095] Step S400 includes:

[0096] S401 real-time monitoring of UPS equipment power supply records, power supply records are updated every time, the corresponding UPS equipment real-time operation data as real-time operation data fragment; with reference to the historical operation data fragment calculation process of the historical operation data deviation index, calculate the real-time operation data deviation index R1;

[0097] S402. According to the current power supply record, the current UPS device usage time is obtained, so as to obtain the UPS device cumulative usage time Tc1 corresponding to the current real-time operation data segment; according to the correlation expression between the historical operation data deviation index and the UPS device usage time, the UPS device cumulative usage time Tc1 is input to obtain the predicted operation data deviation index R2;

[0098] S403. If the relationship between the real-time operation data deviation index R1 and the predicted operation data deviation index R2 is: |R1-R2|≤e*(R0_max-R0_min), where e represents the deviation factor, output prompt information of normal use of UPS equipment to relevant personnel; if the relationship between the real-time operation data deviation index R1 and the predicted operation data deviation index R2 is: |R1-R2|>e*(R0_max-R0_min), output prompt information of UPS equipment abnormality to relevant personnel, and have the relevant personnel repair the UPS equipment.

[0099] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0100] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A data center power supply information monitoring method based on UPS, characterized in that: The method comprises the following steps: Step S100. Obtain historical operation data, power supply records and maintenance logs of UPS devices from the data center management platform, divide the historical operation data into several historical operation data segments according to the power supply records of the UPS devices, and obtain the operation data reference baseline in combination with the UPS device maintenance events recorded in the maintenance log; Step S200. Based on the operating data reference baseline, each historical operating data segment is analyzed in combination with the operating data reference baseline to obtain a historical operating data deviation index; Step S300. Based on the UPS device usage time recorded in the power supply, the historical operation data deviation index and the UPS device usage time are analyzed to obtain the correlation between the historical operation data deviation index and the UPS device usage time; Step S400. Real-time monitoring of the power supply record of the UPS device. Each time the power supply record is updated, the real-time operation data of the corresponding UPS device is obtained, thereby obtaining the real-time operation data deviation index; according to the current power supply record, the current UPS device usage time is obtained, and the correlation between the historical operation data deviation index and the UPS device usage time is combined to output the corresponding information to the relevant personnel; The step S100 includes: S101. The historical operation data refers to the operation status record of the UPS device in the past period of time, and the past period of time refers to the time when the UPS device starts to be used to the time when the UPS device is eliminated and stopped using; the power supply record refers to the power supply status record of the UPS device; the maintenance log is the event record during the maintenance and repair of the UPS device; S102. According to the power supply record of the UPS device, the historical operation data is divided into several historical operation data segments, and the time period of each historical operation data segment corresponds to the time period of a power supply record; according to the UPS device maintenance event recorded in the maintenance log, the time point t corresponding to the UPS device maintenance event is obtained, and the time point t corresponding to the UPS device maintenance event is matched with the historical operation data segment closest to the time point t; the historical operation data segment corresponding to the time point t that does not correspond to the UPS device maintenance event is used as the historical operation data benchmark segment, and the historical operation data segment corresponding to the time point t corresponding to the UPS device maintenance event is used as the historical operation data fluctuation segment; S103. Extract all historical operation data benchmark segments, and analyze the data points corresponding to each historical operation data benchmark segment. The specific analysis process is as follows: For each historical operating data benchmark segment, calculate the mean value μ and standard deviation σ to obtain the upper limit Y1 and lower limit Y2 of the operating data baseline. The specific calculation formula is: Y1=μ+a*σ, Y2=μ+a*σ, where a represents the coefficient; calculate the mean value and standard deviation of skewness S and kurtosis K to obtain the upper limit Y3 and Y5 and lower limit Y4 and Y6 of the operating data baseline. The specific calculation formula is: Y3=μ+(S_μ+f_s*S_σ), Y4=μ-(S_μ+f_s*S_σ), Y5=μ+(K_μ+f_k*K_σ), Y6=μ-(K_μ+f_k*K_σ); where S_μ and S_σ represent the mean value and standard deviation of skewness S, respectively, and K_μ and K_σ represent the mean value and standard deviation of kurtosis K, respectively. , f_s and f_k represent the correction factors of skewness S and kurtosis K respectively; for the baselines Y1 and Y2 based on the mean and standard deviation, and the baselines Y3 to Y6 based on the skewness and kurtosis, the upper limits of all baselines are taken as the maximum value Y_max, and the lower limits are taken as the minimum value Y_min, so as to obtain the baseline range of each historical operation data baseline segment; according to the baseline range, the data points of the historical operation data baseline segment that do not belong to the baseline range are screened out, so as to represent the remaining data points of the historical operation data baseline segment in a plane rectangular coordinate system, and the horizontal axis of the plane rectangular coordinate system represents the time point of the historical operation data, and the horizontal axis represents the data points corresponding to the historical operation data; the data points are connected according to the time point sequence, so as to obtain the operation data baseline; Obtaining an operating data baseline corresponding to each historical operating data baseline segment, representing the operating data baseline in the same rectangular coordinate system, and matching the horizontal coordinates of the initial points of all operating data baselines, thereby fitting an operating data reference baseline; The step S200 includes: S201. Representing all data points of the historical operation data segments in the same plane rectangular coordinate system to obtain a historical operation data trend curve; and dividing the historical operation data trend curve into several historical operation data trend curve segments according to the time period of the historical operation data segments; S202. The horizontal coordinate of the initial point of the historical operation data trend curve corresponds to the operation data reference baseline, so as to calculate the deviation of each historical operation data trend curve segment to obtain the historical operation data deviation index R. The specific calculation formula is: ， Where n is the number of data points in the trend curve of historical operation data. Represents the value of the i-th data point of the historical running data trend curve segment, represents the value of the i-th data point of the corresponding operating data reference baseline; The step S300 includes: S301.Acquire the UPS device usage time T0 of each historical operation data segment according to the power supply record, arrange all historical operation data segments in chronological order, calculate the cumulative usage time Tc of the UPS device corresponding to each historical operation data segment, and Tc_m=Tc_m-1+T0_m, where Tc_m represents the cumulative usage time Tc of the UPS device corresponding to the m-th historical operation data segment, Tc_m-1 represents the cumulative usage time Tc of the UPS device corresponding to the m-1th historical operation data segment, and T0_m represents the usage time T0 of the UPS device of the m-th historical operation data segment; S302. For each historical operation data segment, the corresponding UPS device cumulative usage time Tc and historical operation data deviation index R are extracted to form the coordinate point (Tc, R); the (Tc, R) corresponding to all historical operation data segments are extracted, and all (Tc, R) coordinate points are plotted on a scatter plot. The statistical software is used to perform regression analysis, and the regression model is fitted to obtain the correlation expression: G(R)=f(Tc), where f( ) represents the correlation function; The step S400 includes: S401 real-time monitoring of UPS equipment power supply records, power supply records are updated every time, the corresponding UPS equipment real-time operation data as real-time operation data fragment; with reference to the historical operation data fragment calculation process of the historical operation data deviation index, calculate the real-time operation data deviation index R1; S402. According to the current power supply record, the current UPS device usage time is obtained, so as to obtain the UPS device cumulative usage time Tc1 corresponding to the current real-time operation data segment; according to the correlation expression between the historical operation data deviation index and the UPS device usage time, the UPS device cumulative usage time Tc1 is input to obtain the predicted operation data deviation index R2; S403. If the relationship between the real-time operation data deviation index R1 and the predicted operation data deviation index R2 is: |R1-R2|≤e*(R0_max-R0_min), where e represents the deviation factor, output prompt information of normal use of UPS equipment to relevant personnel; if the relationship between the real-time operation data deviation index R1 and the predicted operation data deviation index R2 is: |R1-R2|>e*(R0_max-R0_min), output prompt information of UPS equipment abnormality to relevant personnel, and have the relevant personnel repair the UPS equipment.

2. A UPS-based data center power supply information monitoring system, applied to the UPS-based data center power supply information monitoring method according to claim 1, characterized in that: The system includes: a data acquisition module, a data processing and analysis module, a correlation relationship modeling module, a real-time monitoring module, and an information output and feedback module; The data acquisition module acquires historical operation data, power supply records and maintenance logs of UPS devices from the data center management platform and integrates them into a usable data format; The data processing and analysis module divides the historical operation data into several historical operation data segments according to the power supply record of the UPS device, and obtains the operation data reference baseline in combination with the UPS device maintenance events recorded in the maintenance log, and calculates the historical operation data deviation index; The association relationship modeling module establishes an association relationship model according to the association relationship between the historical operation data deviation index and the UPS device usage time; The real-time monitoring module monitors the power supply record of the UPS device in real time, obtains the real-time operation data of the corresponding UPS device, thereby obtaining the real-time operation data deviation index, and predicts the real-time operation data deviation index according to the association relationship model; The information output and feedback module determines whether the operating status of the UPS device is normal according to the real-time operating data deviation index and the predicted real-time operating data deviation index, and sends a prompt message to relevant personnel when an abnormal situation occurs.

3. The UPS-based data center power supply information monitoring system according to claim 2, characterized in that: The data acquisition module includes a data acquisition unit and a data transmission unit; The data acquisition unit acquires historical operation data, power supply records and maintenance logs from the UPS device and the data center management platform; the data transmission unit transmits the collected data to the data processing and analysis module.

4. The UPS-based data center power supply information monitoring system according to claim 2, characterized in that: The data processing and analysis module includes a data segmentation unit, a reference baseline generation unit and a deviation index calculation unit; The data segmentation unit divides the historical operation data into a plurality of historical operation data segments; the reference baseline generation unit combines the maintenance log and the historical operation data segments to generate a reference baseline for the historical operation data; The deviation index calculation unit calculates the deviation index of the historical operation data.

5. The UPS-based data center power supply information monitoring system according to claim 2 is characterized in that: the real-time monitoring module includes a real-time data acquisition unit, a real-time deviation index prediction unit and an operation status judgment unit; The real-time data acquisition unit acquires the real-time operation data and power supply records of the UPS device and calculates the real-time operation data deviation index; the real-time deviation index prediction unit predicts the deviation index of the real-time operation data according to the historical correlation model; the operation status judgment unit judges whether the operation status of the UPS device is normal according to the real-time deviation index and the reference baseline.

6. The UPS-based data center power supply information monitoring system according to claim 2, characterized in that: The information output and feedback module includes a normal use prompt unit and an abnormal use prompt unit; The normal use prompt unit outputs corresponding prompt information when the UPS device is in normal operation; the abnormal prompt unit outputs corresponding warning information and notifies relevant personnel to handle when an abnormality occurs in the UPS device.

Images