Remote monitoring method of power environment in computer room based on sensor network

Abstract

The present invention relates to the technical field of abnormal monitoring of computer rooms, and specifically to a remote monitoring method for the power environment of a computer room based on a sensor network. First, by analyzing the instantaneous fluctuations and overall changes of temperature data, normal fluctuations and real abnormalities are effectively distinguished, thereby avoiding false alarms caused by temperature jitters in traditional fixed threshold methods. Then, based on the trend abnormalities of the air volume time series curve and the relative position weights of the wind source, the defects of the association between air volume and the environment are introduced, thereby enhancing the sensitivity to environmental abnormalities such as ventilation failures. Further, environmental abnormalities are comprehensively reflected in the two dimensions of temperature abnormalities and air volume abnormalities, overcoming the limitations of a single indicator. And finally, based on the characteristic that air volume and temperature will show linear changes under normal circumstances, the regional characteristic abnormality index that more accurately characterizes the abnormal conditions of each monitoring area is comprehensively determined in combination with the environmental abnormality weight, so that the regional characteristic abnormality index is more effective in remote monitoring of the power environment of the computer room.

Description

Technical Field

[0001] The present invention relates to the technical field of abnormal monitoring of computer rooms, and in particular to a remote monitoring method for a power environment of a computer room based on a sensor network. Background Art

[0002] The rapid development of hardware devices has led to the increasing prevalence of miniaturized, low-power, and highly sensitive sensors, making real-time, multi-dimensional data collection a reality. Furthermore, protocols such as LoRa and NB-IoT support long-distance, low-power transmission, and edge computing nodes enable local data processing, reducing reliance on the cloud. However, with the commercial deployment of these hardware devices, the traditional method of monitoring computer room environments, based on manual inspections, has gradually become less efficient and prone to errors, failing to meet user requirements.

[0003] Existing technologies typically use the characteristic that abnormal temperatures will rise abnormally when an abnormality occurs in the computer room environment to detect abnormalities in each monitoring area by setting a fixed temperature threshold, and then remotely monitor the computer room's power environment through temperature anomalies. However, it is necessary to consider that the sensor may experience temperature jitter when collecting temperature, causing normal temperature changes to be identified as temperature anomalies, thereby affecting the accuracy of abnormality detection in the monitoring area. In addition, existing technologies do not consider that abnormal changes in air volume can also reflect abnormalities in the environment in the monitoring area, resulting in high limitations on the detected abnormalities in the monitoring area, making the accuracy of abnormality detection in the monitoring area low. In other words, the existing technology's method of detecting abnormalities in each monitoring area by setting a fixed temperature threshold is low in accuracy, resulting in poor remote monitoring of the computer room's power environment. Summary of the Invention

[0004] In order to solve the technical problem of low accuracy of the existing method of detecting anomalies in each monitoring area by setting a fixed temperature threshold, the purpose of this application is to provide a remote monitoring method for the power environment of a computer room based on a sensor network. The technical solution adopted is as follows: In the first aspect, this application provides a remote monitoring method for the power environment of a computer room based on a sensor network, comprising:

[0005] During the monitoring period, obtain the temperature data and air volume data collected by each sensor device in each monitoring area in the computer room;

[0006] Determine the corresponding temperature normality based on the abnormal temperature data fluctuations of each sensor device in each monitoring area; determine the corresponding air volume abnormality based on the relative position of the wind source of each sensor device in each monitoring area and the abnormal sudden change of air volume data; determine the environmental abnormality weight of each monitoring area based on the temperature normality and the air volume abnormality;

[0007] According to the linear fitting between the temperature data and the air volume data in each monitoring area and the environmental anomaly weight, the corresponding regional characteristic anomaly index is determined; and the power environment of the computer room is remotely monitored according to the regional characteristic anomaly index.

[0008] Furthermore, the process of obtaining the normal temperature includes:

[0009] Determine the corresponding temperature abnormal change parameters based on the instantaneous temperature change of each sensor device in each monitoring area;

[0010] During the monitoring period, the difference between the temperature data collected by each sensor device in each monitoring area at the last sampling moment and the temperature data collected at the first sampling moment is used as the corresponding overall temperature change value; the extreme difference of the temperature data collected by each sensor device in each monitoring area is used as the maximum temperature change value; and the corresponding abnormal change degree is determined based on the ratio between the overall temperature change value and the maximum temperature change value;

[0011] The reference temperature parameter of each sensor device is determined based on the mean temperature data of each sensor device in each monitoring area during the monitoring time period, the abnormal change degree and the temperature abnormal change parameter; the corresponding temperature normality is determined based on the mean value of the reference temperature parameters of all sensor devices in each monitoring area.

[0012] Furthermore, the process of obtaining the abnormal temperature change parameter includes:

[0013] During the monitoring period, the difference between the temperature data of each sensor device at each sampling moment and the temperature data at the previous sampling moment in each monitoring area is used as the instantaneous temperature change value at each sampling moment; when the maximum value of the instantaneous temperature change values ​​of all sampling moments is greater than or equal to the preset temperature fluctuation threshold, the temperature abnormal change parameter of the corresponding sensor device is set to the preset first threshold;

[0014] When the maximum value of the instantaneous temperature change value at all sampling moments is less than the preset temperature fluctuation threshold, the temperature abnormal change parameter of the corresponding sensor device is set to the preset second threshold; wherein the preset first threshold is greater than the preset second threshold.

[0015] Furthermore, the process of obtaining the reference temperature parameter includes:

[0016] A negative correlation mapping is performed on the product of the temperature data mean value of each sensor device in each monitoring area in the monitoring time period, the abnormal change degree and the temperature abnormal change parameter to determine the reference temperature parameter of each sensor device.

[0017] Furthermore, the process of obtaining the abnormal degree of air volume includes:

[0018] Arrange all the air volume data collected by each sensor device in each monitoring area in chronological order and perform curve fitting to determine the corresponding air volume data time series curve; determine the degree of fluctuation abnormality based on the abnormal change trend of the air volume data time series curve;

[0019] The difference between the air volume data at the first sampling moment and the air volume data at the last sampling moment on the air volume data time series curve is used as the corresponding overall air volume change value;

[0020] Determine the corresponding distance weight according to the negative correlation mapping value of the minimum distance between each sensor device and all wind source outlets;

[0021] Normalizing the product of the wind volume data range at all sampling moments on the wind volume data time series curve, the distance weight, the overall wind volume change value, and the fluctuation abnormality degree to determine the wind volume abnormality parameter of each sensor device;

[0022] The corresponding degree of air volume abnormality is determined based on the mean value of the air volume abnormality parameters of all sensor devices in each monitoring area.

[0023] Furthermore, the process of obtaining the degree of fluctuation anomaly includes:

[0024] On the wind volume data time series curve, the average of the absolute values ​​of the slopes at all sampling moments is used as the degree of fluctuation abnormality.

[0025] Furthermore, the process of obtaining the environmental anomaly weight includes:

[0026] The environmental abnormality weight of each monitoring area is determined according to the product of the negative correlation mapping value of the temperature normality and the wind volume abnormality.

[0027] Furthermore, the process of obtaining the regional characteristic anomaly index includes:

[0028] Determine the corresponding temperature and air volume linear parameters based on the correlation between the temperature data and air volume data of each sensor device in each monitoring area during the monitoring period;

[0029] The product of the negative correlation mapping value of the mean value of the temperature and air volume linear parameters of all sensor devices in each monitoring area and the environmental anomaly weight is normalized to determine the regional characteristic anomaly index of each monitoring area.

[0030] Furthermore, the process of obtaining the temperature and air volume linear parameters includes:

[0031] Arrange all temperature data of each sensor device in each monitoring area during the monitoring time period in chronological order to obtain a temperature data time series sequence; arrange all air volume data of each sensor device in each monitoring area during the monitoring time period in chronological order to obtain an air volume data time series sequence; determine the temperature and air volume linear parameters based on the normalized value of the Pearson correlation coefficient between the temperature data time series sequence and the air volume data time series sequence.

[0032] Furthermore, the process of remotely monitoring the power environment of the computer room according to the regional characteristic anomaly index includes:

[0033] The monitoring area with a regional characteristic abnormality index greater than a preset abnormality threshold is regarded as a high-risk area; remote monitoring of the power environment of the computer room is carried out based on the high-risk area.

[0034] In a second aspect, the present application provides a remote monitoring system for a computer room power environment based on a sensor network, the system comprising:

[0035] The data acquisition module is used to obtain the temperature data and air volume data collected by each sensor device in each monitoring area in the computer room during the monitoring period;

[0036] An environmental anomaly weight determination module is used to determine the corresponding temperature normality based on the abnormal temperature data fluctuation of each sensor device in each monitoring area; determine the corresponding air volume abnormality based on the relative position of the wind source of each sensor device in each monitoring area and the abnormal sudden change of air volume data; and determine the environmental anomaly weight of each monitoring area based on the temperature normality and the air volume abnormality;

[0037] The computer room power environment remote monitoring module is used to determine the corresponding regional characteristic anomaly index based on the linear fitting between the temperature data and air volume data in each monitoring area and the environmental anomaly weight; and remotely monitor the computer room power environment based on the regional characteristic anomaly index.

[0038] In a third aspect, the present application provides a computer device comprising a memory and a processor. The memory is configured to store computer program code, and the processor is configured to call and execute the computer program code from the memory to perform the method of the first aspect or any embodiment of the first aspect of the present application.

[0039] In a fourth aspect, the present application provides a computer program product, comprising a computer program code. When the computer program code is executed, the method of the first aspect or any embodiment of the first aspect of the present application is performed.

[0040] In a fifth aspect, the present application provides a computer-readable storage medium, which stores computer program code. When the computer program code is executed, it performs the method of the first aspect of the present application or any embodiment of the first aspect.

[0041] This application has the following beneficial effects:

[0042] This application first effectively distinguishes normal fluctuations from real anomalies by analyzing the instantaneous fluctuations and overall changes of temperature data, avoiding false alarms caused by temperature jitter in the traditional fixed threshold method. Then, based on the trend anomaly of the air volume time series curve and the relative position weight of the wind source, the degree of air volume anomaly is quantified, thereby introducing the defect of the air volume and environment correlation, and enhancing the sensitivity to environmental anomalies such as ventilation failure. Further, the environmental anomaly is comprehensively reflected in the two dimensions of temperature anomaly and air volume anomaly to overcome the limitations of a single indicator. And finally, based on the characteristic that air volume and temperature will show linear changes under normal circumstances, combined with the environmental anomaly weight, a more accurate regional characteristic anomaly index that characterizes the abnormal situation of each monitoring area is comprehensively determined, so that the regional characteristic anomaly index is more effective in remote monitoring of the power environment of the computer room. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 A flow chart of a method for remotely monitoring a power environment in a computer room based on a sensor network according to an embodiment of the present invention;

[0045] Figure 2 A structural diagram of a remote monitoring system for a computer room power environment based on a sensor network provided by one embodiment of the present invention;

[0046] Figure 3 The present invention provides a schematic diagram of a computer device structure according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the following, in combination with the accompanying drawings and preferred embodiments, a method for remote monitoring of the power environment of a computer room based on a sensor network proposed in accordance with the present invention, its specific implementation method, structure, characteristics and effects are described in detail as follows. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment, and the specific features, structures or characteristics in one or more embodiments may be combined in any suitable form. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0048] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0049] The following describes in detail a specific solution of a remote monitoring method for a computer room power environment based on a sensor network provided by the present invention with reference to the accompanying drawings.

[0050] This application embodiment provides a remote monitoring method for the power environment of a computer room based on a sensor network. Figure 1 , which shows a flow chart of a method for remote monitoring of a computer room power environment based on a sensor network according to an embodiment of the present invention. The method includes:

[0051] Step S101: During a monitoring period, temperature data and air volume data collected by each sensor device in each monitoring area in the computer room are obtained.

[0052] In a specific implementation of an embodiment of the present invention, a square area in the computer room centered around each computer room device (such as a server, switch, hardware gateway, etc.) is used as a monitoring area; the side length of the square corresponding to the monitoring area is set to 2 meters; a sensor device is installed at the center point of each triangular area divided by the two diagonal lines of the square area of ​​the monitoring area, and the sensor device includes a temperature sensor and an air volume sensor. The temperature data collected by the temperature sensor and the air volume data collected by the air volume sensor are transmitted to the edge gateway in the computer room via a low-power wide area network for data processing. It should be noted that the division of the monitoring area and the location setting of the sensor device can be adjusted according to the specific implementation environment and will not be further elaborated here.

[0053] In a specific implementation of an embodiment of the present invention, a monitoring time period is set every 10 seconds. After all temperature data and air volume data in a monitoring time period are collected, an analysis and calculation of the regional characteristic anomaly index is performed, and remote monitoring of the computer room power environment is performed based on the regional characteristic anomaly index. In addition, the sampling frequency is set to once per second, and the length of the monitoring time period and the sampling frequency can be adjusted according to the specific implementation environment.

[0054] Step S102: Determine the corresponding temperature normality based on the abnormal temperature data fluctuations of each sensor device in each monitoring area; determine the corresponding air volume abnormality based on the relative position of the wind source of each sensor device in each monitoring area and the abnormal sudden change of air volume data; determine the environmental abnormality weight of each monitoring area based on the temperature normality and the air volume abnormality.

[0055] For the computer room environment, the slow growth of the ambient temperature in the computer room is normal linear, but the instantaneous higher temperature growth may correspond to abnormal temperature changes, or it may be temperature jitter belonging to normal temperature changes. Therefore, this application analyzes the abnormal fluctuations of the temperature data of each sensor in the monitoring area, and determines the temperature performance in the monitoring area according to the normal degree of temperature.

[0056] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the normality of temperature includes:

[0057] Determine the corresponding abnormal temperature change parameter based on the instantaneous temperature change of each sensor device in each monitoring area. The abnormal temperature change parameter acquisition process includes:

[0058] During the monitoring time period, the difference between the temperature data of each sensor device in each monitoring area at each sampling moment and the temperature data at the previous sampling moment is used as the instantaneous temperature change value at each sampling moment; when the maximum value of the instantaneous temperature change values ​​of all sampling moments is greater than or equal to the preset temperature fluctuation threshold, the temperature abnormal change parameter of the corresponding sensor device is set to the preset first threshold; when the maximum value of the instantaneous temperature change values ​​of all sampling moments is less than the preset temperature fluctuation threshold, the temperature abnormal change parameter of the corresponding sensor device is set to the preset second threshold; wherein the preset first threshold is greater than the preset second threshold.

[0059] In a specific implementation of an embodiment of the present invention, the preset temperature fluctuation threshold is set to 1 degree Celsius, the preset first threshold is set to 1, and the preset second threshold is set to 0, which can be adjusted according to the specific implementation environment. When the instantaneous temperature change value is greater than the preset temperature fluctuation threshold, it means that a large temperature change has occurred in a short period of time, and the possibility of corresponding temperature anomaly is high. Therefore, the role of the temperature anomaly change parameter here is to determine whether there is an instantaneous temperature anomaly. When the maximum value of the instantaneous temperature change value is greater than or equal to the preset temperature fluctuation threshold, it means that there is an instantaneous temperature change anomaly in the monitoring time period. Therefore, the amplitude is 1 to further analyze whether there is a real temperature anomaly. When the maximum value of the instantaneous temperature change value is less than the preset temperature fluctuation threshold, it means that the overall temperature change is relatively stable, there is no significant temperature change anomaly, and no further analysis is required. Therefore, it is assigned a value of 0 to ignore the situation of subsequent analysis.

[0060] During the monitoring period, the difference between the temperature data collected by each sensor device in each monitoring area at the last sampling moment and the temperature data collected at the first sampling moment is used as the corresponding overall temperature change value; the extreme difference in temperature data collected by each sensor device in each monitoring area is used as the maximum temperature change value; and the corresponding degree of abnormal change is determined based on the ratio between the overall temperature change value and the maximum temperature change value. In the case of temperature jitter, temperature jitter is usually instantaneous, so after an abnormal temperature change, it usually returns to normal within a short period of time. Therefore, if the overall temperature change value is significantly less than the maximum temperature change value, it means that the temperature has returned to normal after a short period of abnormal change, and the overall temperature still shows a normal change trend, so the corresponding degree of abnormal change should be small. If the overall temperature change value is close to the maximum temperature change value, it means that the temperature may have risen abnormally and did not return to normal temperature, so the corresponding degree of abnormal change should be large.

[0061] The reference temperature parameter of each sensor device is determined based on the mean temperature data, degree of abnormal change, and temperature abnormal change parameter of each sensor device in each monitoring area during the monitoring period. The reference temperature parameter acquisition process includes: performing negative correlation mapping on the product of the mean temperature data, degree of abnormal change, and temperature abnormal change parameter of each sensor device in each monitoring area during the monitoring period to determine the reference temperature parameter of each sensor device. For each monitoring period, the larger the mean temperature data value, the higher the overall temperature level, and therefore the higher the possibility of temperature abnormality. Therefore, based on the mean temperature data value, combined with the degree of abnormal change that characterizes temperature abnormality and the temperature abnormal change parameter, a comprehensive analysis is conducted. Through the negative correlation mapping method, the smaller the reference temperature parameter obtained, the more likely it corresponds to a temperature abnormality. Finally, based on the mean reference temperature parameter of all sensor devices in each monitoring area, the corresponding temperature normality is determined.

[0062] In a specific implementation of the embodiment of the present invention, the process of obtaining the reference temperature parameter is expressed as follows: ;in, For the In the monitoring area Reference temperature parameters of each sensor device; For the In the monitoring area The average temperature data of each sensor device during the monitoring period; For the In the monitoring area Abnormal temperature change parameters corresponding to each sensor device; For the In the monitoring area The temperature data of each sensor device at the last sampling moment in the monitoring period; For the In the monitoring area The temperature data of each sensor device at the first sampling moment in the monitoring period; is the absolute value symbol; For the In the monitoring area The overall temperature change value corresponding to each sensor device; For the In the monitoring area The maximum value of the temperature data of each sensor device during the monitoring period; For the In the monitoring area The minimum temperature data value of each sensor device during the monitoring period; For the In the monitoring area The temperature data of each sensor device is extremely poor, that is, the maximum temperature change; For the In the monitoring area The degree of abnormal changes in each sensor device; is a linear normalization function. It should be noted that, in order to ensure that the calculation results are meaningful, when performing fractional operations in the embodiment of the present invention, when encountering a situation where the denominator is 0, it is necessary to add a parameter adjustment factor greater than 0 to the denominator to prevent the denominator from being 0. In a specific implementation of the embodiment of the present invention, the parameter adjustment factor is set to 0.1; the value of the parameter adjustment factor can be set by the implementer according to the actual situation, and this application does not impose any special restrictions.

[0063] In a specific implementation of the embodiment of the present invention, the process of obtaining the normal temperature is expressed by the formula: ;in, For the Normal temperature of each monitoring area; For the The number of sensor devices in each monitoring area; For the In the monitoring area The reference temperature parameter of each sensor device.

[0064] For wind volume data, when the wind volume collected by the sensor changes greatly, it means that the equipment corresponding to the wind source in the environment may have a fault, such as a fault in the air conditioner used for refrigeration; the closer the sensor is to the wind source, the more credible the abnormal wind volume change it reflects, and therefore the corresponding weight for analyzing wind volume data anomalies is higher. Therefore, the abnormal situation of the wind volume data is comprehensively characterized based on the degree of wind volume anomaly determined by the relative position of the wind source and the abnormal mutation of the wind volume data.

[0065] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the degree of abnormal air volume includes:

[0066] All air volume data collected by each sensor device in each monitoring area is arranged in chronological order and then curve-fitted to determine the corresponding air volume data time series curve. The degree of fluctuation anomaly is determined based on the abnormal trend of the air volume data time series curve. The degree of fluctuation anomaly is obtained by taking the average of the absolute values ​​of the slope of the tangent at all sampling moments on the air volume data time series curve as the degree of fluctuation anomaly.

[0067] For wind volume data, under normal circumstances, the wind volume data is usually relatively stable, and when it changes, it also shows a relatively slow change; according to the definition of slope, the larger the absolute value of the tangent slope at each sampling moment on the wind volume data time series curve is, the more prominent the change in the overall wind volume data is. Therefore, the greater the degree of abnormal fluctuation, the more inconsistent the wind volume data change is with normal conditions, and the more abnormal the environment is in terms of the wind volume data dimension.

[0068] The difference between the wind volume data at the first sampling moment and the wind volume data at the last sampling moment on the wind volume data time series curve is used as the corresponding overall wind volume change value; the corresponding distance weight is determined based on the negative correlation mapping value of the minimum distance between each sensor device and all wind source outlets; wherein, the larger the overall wind volume change value, the greater the overall change in the wind volume data after the monitoring period, and the more likely it is that the corresponding wind source device cannot ensure that the wind volume data returns to normal data after a failure, so the degree of environmental abnormality in the wind volume data is higher. Since the smaller the distance between the sensor and the wind source, the higher the weight used to analyze wind volume data anomalies, the minimum distance between the sensor device and all wind source outlets is negatively correlated, so that the larger the determined distance weight, the higher the weight of the corresponding sensor in analyzing wind volume data anomalies.

[0069] A larger range in air volume data indicates a larger numerical span within the monitoring period. Therefore, the range of air volume data represents a sudden change in air volume data. The larger the range, the more severe the anomaly. Similar to the overall air volume change and the degree of fluctuation anomaly, the range of air volume data is positively correlated with air volume data anomaly. Furthermore, the product of the range of air volume data at all sampling moments on the air volume data time series curve, the distance weight, the overall air volume change, and the degree of fluctuation anomaly is normalized to determine the air volume anomaly parameter for each sensor device. This results in a larger air volume anomaly parameter indicating a more severe environmental anomaly reflected by the corresponding sensor device in the air volume data dimension. Finally, the degree of air volume anomaly in each monitoring area is comprehensively determined based on the mean value of the air volume anomaly parameter for all sensor devices within the monitoring area.

[0070] In a specific implementation of the embodiment of the present invention, the process of obtaining the abnormal air volume parameter is expressed by the formula: ;in, For the In the monitoring area Abnormal air volume parameters of each sensor device; For the In the monitoring area The air volume data at all sampling moments on the air volume data time series curve of each sensor device is extremely poor; For the In the monitoring area The average of the absolute values ​​of the tangent slopes at all sampling moments on the air volume data time series curve of each sensor device, that is, the corresponding degree of fluctuation anomaly; For the In the monitoring area The wind volume data at the last sampling moment on the wind volume data time series curve of each sensor device; For the In the monitoring area The wind volume data at the first sampling moment on the wind volume data time series curve of each sensor device; For the In the monitoring area The overall air volume change value of each sensor device; For the In the monitoring area The minimum distance between each sensor device and all air source outlets; is an exponential function with a natural constant as its base; For the In the monitoring area The distance weight corresponding to each sensor device.

[0071] In a specific implementation of the embodiment of the present invention, the process of obtaining the degree of abnormal air volume is expressed by the formula: ;in, For the The abnormal degree of air volume in each monitoring area; For the The number of sensor devices in each monitoring area; For the In the monitoring area Abnormal air volume parameters of each sensor device.

[0072] The smaller the temperature normality, the more abnormal the temperature performance of the corresponding monitoring area; and the greater the air volume abnormality, the more abnormal the air volume performance of the corresponding monitoring area. Therefore, when comprehensively characterizing the environmental abnormality from the two aspects of temperature and air volume, the smaller the corresponding temperature normality and the greater the air volume abnormality, the greater the environmental abnormality weight representing the environmental abnormality should be. Specifically, the process of obtaining the environmental abnormality weight includes:

[0073] The environmental anomaly weight of each monitoring area is determined based on the product of the negative correlation mapping value of the temperature normality and the air volume abnormality. In a specific implementation of the embodiment of the present invention, the process of obtaining the environmental anomaly weight is expressed by the formula: ;in, For the Environmental anomaly weight of each monitoring area; For the The abnormal degree of air volume in each monitoring area; For the Normal temperature of each monitoring area; is an exponential function with a natural constant as its base.

[0074] Step S103: Determine the corresponding regional characteristic anomaly index based on the linear fitting between the temperature data and the air volume data in each monitoring area and the environmental anomaly weight; and perform remote monitoring of the power environment of the computer room based on the regional characteristic anomaly index.

[0075] In addition to characterizing abnormal conditions in the computer room environment based on abnormal air volume data and abnormal temperature data, it is also necessary to consider that under normal circumstances, the air volume of the air source in the computer room corresponds to the temperature in the environment. When the temperature is high, the air volume is large, and when the temperature is low, the air volume is small. That is, the corresponding air volume data and temperature data should maintain a certain positive linear correlation in time series. Therefore, based on the environmental anomaly weight, further analysis is conducted in combination with the linear fitting situation between the air volume data and the temperature data, that is, the correlation situation.

[0076] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the regional characteristic anomaly index includes:

[0077] According to the correlation between the temperature data and the air volume data of each sensor device in each monitoring area during the monitoring period, the corresponding temperature and air volume linear parameters are determined. The corresponding temperature and air volume linear parameters are obtained by:

[0078] Arrange all temperature data from each sensor device in each monitoring area during the monitoring period in chronological order to obtain a temperature data time series sequence. Arrange all air volume data from each sensor device in each monitoring area during the monitoring period in chronological order to obtain an air volume data time series sequence. Determine the temperature-air volume linear parameter based on the normalized Pearson correlation coefficient between the temperature data time series sequence and the air volume data time series sequence. According to the properties of the Pearson correlation coefficient, the larger the corresponding temperature-air volume linear parameter, the more positively correlated the temperature data time series sequence with the air volume data time series sequence, and the more consistent the corresponding temperature and air volume changes are with normal conditions. Therefore, the smaller the temperature-air volume linear parameter, the more abnormal the environment reflected by the data collected by the corresponding sensor device.

[0079] Furthermore, combined with the temperature and air volume linear parameters of all sensor devices, the product of the negative correlation mapping value of the mean value of the temperature and air volume linear parameters of all sensor devices in each monitoring area and the environmental anomaly weight is normalized to determine the regional characteristic anomaly index of each monitoring area; the larger the regional characteristic anomaly index, the more prominent the environmental anomaly performance of the corresponding monitoring area.

[0080] In a specific implementation of the embodiment of the present invention, the process of obtaining the regional characteristic anomaly index is expressed by the formula: ;in, For the Regional characteristic anomaly index of each monitoring area; For the Environmental anomaly weight of each monitoring area; For the The number of sensor devices in each monitoring area; For the In the monitoring area The Pearson correlation coefficient between the temperature data time series and the wind volume data time series of each sensor device; For the In the monitoring area Temperature and air volume linear parameters of each sensor device; is an exponential function with a natural constant as its base. Normalization limits the value range of the regional characteristic anomaly index to between 0 and 1, making the characterization of environmental anomalies in the monitored area more intuitive and facilitating subsequent screening of high-risk areas.

[0081] Preferably, in a specific implementation of an embodiment of the present invention, the process of remotely monitoring the power environment of a computer room according to a regional characteristic anomaly index includes: treating a monitoring area with a regional characteristic anomaly index greater than a preset anomaly threshold as a high-risk area; and remotely monitoring the power environment of a computer room according to the high-risk area. In a specific implementation of an embodiment of the present invention, the preset anomaly threshold is set to 0.7, which can be adjusted according to the specific implementation environment and will not be further elaborated here. Since the larger the regional characteristic anomaly index, the more abnormal the environment of the corresponding monitoring area, the monitoring area with a larger regional characteristic anomaly index is screened out as a high-risk area for remote monitoring of the power environment of the computer room.

[0082] In a specific implementation of the embodiment of the present invention, when a high-risk area is monitored, the server information corresponding to the high-risk area is sent to the administrator terminal, and a risk alarm is issued to promptly handle the abnormal environment situation.

[0083] In summary, the sensor network-based remote monitoring method for the computer room power environment first effectively distinguishes normal fluctuations from real anomalies by analyzing the instantaneous fluctuations and overall changes of temperature data, avoiding false alarms caused by temperature jitter in the traditional fixed threshold method. Then, based on the trend anomaly of the air volume time series curve and the relative position weight of the air source, the degree of air volume anomaly is quantified, thereby introducing the defect of the association between air volume and the environment, and enhancing the sensitivity to environmental anomalies such as ventilation failures. Furthermore, environmental anomalies are comprehensively reflected in the two dimensions of temperature anomaly and air volume anomaly, overcoming the limitations of a single indicator. Finally, based on the characteristic that air volume and temperature will show linear changes under normal circumstances, combined with the environmental anomaly weight, a more accurate regional characteristic anomaly index is determined to characterize the abnormal situation of each monitoring area, making the regional characteristic anomaly index more effective in remote monitoring of the computer room power environment.

[0084] This application also provides a remote monitoring system for the power environment of the computer room based on a sensor network. Figure 2 , which shows a structural diagram of a computer room power environment remote monitoring system based on a sensor network provided by an embodiment of the present invention. The system includes: a data acquisition module 201, an environmental anomaly weight determination module 202 and a computer room power environment remote monitoring module 203.

[0085] The data acquisition module 201 is used to obtain the temperature data and air volume data collected by each sensor device in each monitoring area in the computer room during the monitoring period;

[0086] The environmental anomaly weight determination module 202 is configured to determine the corresponding temperature normality based on the abnormal temperature data fluctuation of each sensor device in each monitoring area; determine the corresponding air volume abnormality based on the relative position of the wind source of each sensor device in each monitoring area and the abnormal sudden change of air volume data; and determine the environmental anomaly weight of each monitoring area based on the temperature normality and air volume abnormality.

[0087] The computer room power environment remote monitoring module 203 is used to determine the corresponding regional characteristic anomaly index based on the linear fitting between the temperature data and the air volume data in each monitoring area and the environmental anomaly weight; and perform remote monitoring of the computer room power environment based on the regional characteristic anomaly index.

[0088] It should be noted that the system provided in the above embodiment is merely an example of the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer equipment can be divided into different functional modules to complete all or part of the functions described above. In addition, the sensor network-based computer room power environment remote monitoring system and the sensor network-based computer room power environment remote monitoring method embodiment provided in the above embodiment are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0089] The present application also provides a computer device. Figure 3 , which shows a schematic diagram of the structure of a computer device provided by an embodiment of the present invention, the computer device includes a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302, wherein when the processor 302 executes the computer program 303, the computer device can execute any of the aforementioned sensor network-based computer room power environment remote monitoring methods.

[0090] An embodiment of the present application also provides a computer program product. When the computer program product is run on a computer device, the computer device can execute any of the aforementioned sensor network-based remote monitoring methods for a computer room power environment.

[0091] An embodiment of the present application also provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer device, the computer device can execute any of the sensor network-based remote monitoring methods for the power environment of a computer room described above.

[0092] In the embodiments provided in the present application, it should be understood that the provided computer devices, computer program products and computer-readable storage media are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the methods provided above and will not be repeated here.

[0093] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0094] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A remote monitoring method for the power environment of a computer room based on a sensor network, characterized in that: The method comprises: During the monitoring period, obtain the temperature data and air volume data collected by each sensor device in each monitoring area in the computer room; Determine the corresponding temperature normality based on the abnormal temperature data fluctuations of each sensor device in each monitoring area; determine the corresponding air volume abnormality based on the relative position of the wind source of each sensor device in each monitoring area and the abnormal sudden change of air volume data; determine the environmental abnormality weight of each monitoring area based on the temperature normality and the air volume abnormality; According to the linear fitting between the temperature data and the air volume data in each monitoring area and the environmental anomaly weight, the corresponding regional characteristic anomaly index is determined; and the power environment of the computer room is remotely monitored according to the regional characteristic anomaly index.

2. A sensor network-based remote monitoring method for a computer room power environment according to claim 1, characterized in that: The process of obtaining the normal temperature level includes: Determine the corresponding temperature abnormal change parameters based on the instantaneous temperature change of each sensor device in each monitoring area; During the monitoring period, the difference between the temperature data collected by each sensor device in each monitoring area at the last sampling moment and the temperature data collected at the first sampling moment is used as the corresponding overall temperature change value; the extreme difference of the temperature data collected by each sensor device in each monitoring area is used as the maximum temperature change value; and the corresponding abnormal change degree is determined based on the ratio between the overall temperature change value and the maximum temperature change value; The reference temperature parameter of each sensor device is determined based on the mean temperature data of each sensor device in each monitoring area during the monitoring time period, the abnormal change degree and the temperature abnormal change parameter; the corresponding temperature normality is determined based on the mean value of the reference temperature parameters of all sensor devices in each monitoring area.

3. A sensor network-based remote monitoring method for a computer room power environment according to claim 2, characterized in that: The process of obtaining the abnormal temperature change parameter includes: During the monitoring period, the difference between the temperature data of each sensor device at each sampling moment and the temperature data at the previous sampling moment in each monitoring area is used as the instantaneous temperature change value at each sampling moment; when the maximum value of the instantaneous temperature change values ​​of all sampling moments is greater than or equal to the preset temperature fluctuation threshold, the temperature abnormal change parameter of the corresponding sensor device is set to the preset first threshold; When the maximum value of the instantaneous temperature change value at all sampling moments is less than the preset temperature fluctuation threshold, the temperature abnormal change parameter of the corresponding sensor device is set to the preset second threshold; wherein the preset first threshold is greater than the preset second threshold.

4. The method for remote monitoring of a computer room power environment based on a sensor network according to claim 2, characterized in that: The process of obtaining the reference temperature parameter includes: A negative correlation mapping is performed on the product of the temperature data mean value of each sensor device in each monitoring area in the monitoring time period, the abnormal change degree and the temperature abnormal change parameter to determine the reference temperature parameter of each sensor device.

5. The method for remote monitoring of a computer room power environment based on a sensor network according to claim 1, characterized in that: The process of obtaining the degree of abnormal air volume includes: Arrange all the air volume data collected by each sensor device in each monitoring area in chronological order and perform curve fitting to determine the corresponding air volume data time series curve; determine the degree of fluctuation abnormality based on the abnormal change trend of the air volume data time series curve; The difference between the air volume data at the first sampling moment and the air volume data at the last sampling moment on the air volume data time series curve is used as the corresponding overall air volume change value; Determine the corresponding distance weight according to the negative correlation mapping value of the minimum distance between each sensor device and all wind source outlets; Normalizing the product of the wind volume data range at all sampling moments on the wind volume data time series curve, the distance weight, the overall wind volume change value, and the fluctuation abnormality degree to determine the wind volume abnormality parameter of each sensor device; The corresponding degree of air volume abnormality is determined based on the mean value of the air volume abnormality parameters of all sensor devices in each monitoring area.

6. A sensor network-based remote monitoring method for a computer room power environment according to claim 5, characterized in that: The process of obtaining the degree of fluctuation anomaly includes: On the wind volume data time series curve, the average of the absolute values ​​of the slopes at all sampling moments is used as the degree of fluctuation abnormality.

7. The method for remote monitoring of a computer room power environment based on a sensor network according to claim 1, characterized in that: The process of obtaining the environmental anomaly weight includes: The environmental abnormality weight of each monitoring area is determined according to the product of the negative correlation mapping value of the temperature normality and the wind volume abnormality.

8. The method for remotely monitoring the power environment of a computer room based on a sensor network according to claim 1, characterized in that: The process of obtaining the regional characteristic anomaly index includes: Determine the corresponding temperature and air volume linear parameters based on the correlation between the temperature data and air volume data of each sensor device in each monitoring area during the monitoring period; The product of the negative correlation mapping value of the mean value of the temperature and air volume linear parameters of all sensor devices in each monitoring area and the environmental anomaly weight is normalized to determine the regional characteristic anomaly index of each monitoring area.

9. A sensor network-based remote monitoring method for a computer room power environment according to claim 8, characterized in that: The process of obtaining the temperature and air volume linear parameters includes: Arrange all temperature data of each sensor device in each monitoring area during the monitoring time period in chronological order to obtain a temperature data time series sequence; arrange all air volume data of each sensor device in each monitoring area during the monitoring time period in chronological order to obtain an air volume data time series sequence; determine the temperature and air volume linear parameters based on the normalized value of the Pearson correlation coefficient between the temperature data time series sequence and the air volume data time series sequence.

10. The method for remote monitoring of a computer room power environment based on a sensor network according to claim 1, characterized in that: The process of remotely monitoring the power environment of the computer room according to the regional characteristic abnormality index includes: The monitoring area with a regional characteristic abnormality index greater than a preset abnormality threshold is regarded as a high-risk area; remote monitoring of the power environment of the computer room is carried out based on the high-risk area.

Images