Machine room power environment remote monitoring method based on sensor network

Abstract

The invention relates to the technical field of machine room abnormity monitoring, in particular to a machine room power environment remote monitoring method based on a sensor network, which comprises the following steps of: firstly, effectively distinguishing normal fluctuation from real abnormity by analyzing instantaneous fluctuation condition and overall change condition of temperature data, and avoiding false alarm caused by temperature jitter in a traditional fixed threshold value method; and then, based on the trend abnormity of the air volume time sequence curve and the relative position weight of the air source, the defect that the air volume is associated with the environment is introduced, and the sensitivity to ventilation faults and other environment abnormity problems is enhanced. Furthermore, environment abnormity is comprehensively reflected in two dimensions of temperature abnormity and air quantity abnormity, and limitation of a single index is overcome. And finally, based on the characteristic that the air quantity and the temperature are linearly changed under the normal condition, a more accurate region feature anomaly index for representing the abnormal condition of each monitoring region is comprehensively determined in combination with an environment anomaly weight, so that the effect of remotely monitoring the power environment of the machine room by the region feature anomaly index is better.

Description

Technical Field

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

[0002] With the rapid development of hardware devices, sensors with miniaturization, low power consumption, and high sensitivity have gradually become popular, making the acquisition of real-time and multi-dimensional data a reality; at the same time, protocols such as LoRa and NB-IoT support long-distance and low-power transmission, and edge computing nodes realize local data processing, reducing the dependence on the cloud. Along with the commercial construction of these hardware devices, the disadvantages of low efficiency and large errors of the traditional method based on manual inspection for computer room environment monitoring have gradually emerged and cannot meet the requirements of users.

[0003] The prior art usually detects abnormalities in each monitoring area by setting a fixed temperature threshold according to the characteristic that the temperature will rise abnormally when there is an abnormality in the computer room environment, and then remotely monitors the power environment of the computer room through the temperature abnormality. However, it is necessary to consider that the temperature may jitter when the sensor collects the temperature, resulting in normal temperature changes being identified as temperature abnormalities, thus affecting the accuracy of abnormality detection in the monitoring area; and the prior art does not consider that abnormal changes in air volume can also reflect abnormalities in the environment in the monitoring area, resulting in a high limitation of the detected abnormalities in the monitoring area and a low accuracy of abnormality detection in the monitoring area; that is, the method of detecting abnormalities in each monitoring area by setting a fixed temperature threshold in the prior art has low accuracy, resulting in poor effect of remote monitoring of the power environment of the computer room. Summary of the Invention

[0004] In order to solve the technical problem of low accuracy of the method in the prior art for detecting abnormalities in each monitoring area by setting a fixed temperature threshold, the purpose of the present application is to provide a remote monitoring method for the power environment of a computer room based on a sensor network, and the specific technical solution adopted is as follows: The first aspect of the present application provides a remote monitoring method for the power environment of a computer room based on a sensor network, including: During a monitoring time period, obtain the temperature data and air volume data collected by each sensor device in each monitoring area of the computer room; Determine the corresponding temperature normality according to the abnormal fluctuation of the temperature data of each sensor device in each monitoring area; determine the corresponding air volume abnormality degree according to the relative position of the air source and the abnormal mutation of the air volume data of each sensor device in each monitoring area; determine the environmental abnormality weight of each monitoring area according to the temperature normality and the air volume abnormality degree; Determine the corresponding regional characteristic anomaly index according to the linear fitting situation between the temperature data and the air volume data in each monitoring area and the environmental anomaly weight; perform remote monitoring of the power environment of the computer room according to the regional characteristic anomaly index.

[0005] Further, the process of obtaining the temperature normality includes: Determine the corresponding temperature anomaly change parameter according to the instantaneous temperature change situation of each sensor device in each monitoring area; During the monitoring time period, take the difference between the temperature data at the last sampling moment and the temperature data at the first sampling moment collected by each sensor device in each monitoring area as the corresponding overall temperature change value; take the range of the temperature data collected by each sensor device in each monitoring area as the maximum temperature change value; determine the corresponding anomaly change degree according to the ratio between the overall temperature change value and the maximum temperature change value. Determine the reference temperature parameter of each sensor device according to the mean value of the temperature data, the anomaly change degree, and the temperature anomaly change parameter of each sensor device in each monitoring area during the monitoring time period; determine the corresponding temperature normality according to the mean value of the reference temperature parameters of all sensor devices in each monitoring area.

[0006] Further, the process of obtaining the temperature anomaly change parameter includes: During the monitoring time period, take 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 as the instantaneous temperature change value at each sampling moment; when the maximum value of the instantaneous temperature change values at all sampling moments is greater than or equal to the preset temperature fluctuation threshold, set the temperature anomaly change parameter of the corresponding sensor device to the preset first threshold; When the maximum value of the instantaneous temperature change values at all sampling moments is less than the preset temperature fluctuation threshold, set the temperature anomaly change parameter of the corresponding sensor device to the preset second threshold; where the preset first threshold is greater than the preset second threshold.

[0007] Further, the process of obtaining the reference temperature parameter includes: Perform a negative correlation mapping on the product of the mean value of the temperature data, the anomaly change degree, and the temperature anomaly change parameter of each sensor device in each monitoring area during the monitoring time period to determine the reference temperature parameter of each sensor device.

[0008] Further, the process of obtaining the air volume anomaly degree 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 abnormal fluctuation according to 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 air source outlets. Normalize 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 value, and the degree of abnormal fluctuation to determine the air volume anomaly parameter of each sensor device. Determine the corresponding air volume anomaly degree according to the mean value of the air volume anomaly parameters of all sensor devices in each monitoring area.

[0009] Furthermore, the process of obtaining the degree of abnormal fluctuation includes: On the air volume data time series curve, take the mean value of the absolute values of the tangent slopes at all sampling moments as the degree of abnormal fluctuation.

[0010] Furthermore, the process of obtaining the environmental anomaly weight includes: Determine the environmental anomaly weight of each monitoring area according to the product of the negative correlation mapping value of the temperature normality and the air volume anomaly degree.

[0011] Furthermore, the process of obtaining the regional characteristic anomaly index includes: Determine the corresponding temperature-air volume linear parameter according to the change correlation between the temperature data and the air volume data of each sensor device in each monitoring area during the monitoring period. Normalize the product of the negative correlation mapping value of the mean value of the temperature-air volume linear parameters of all sensor devices in each monitoring area and the environmental anomaly weight to determine the regional characteristic anomaly index of each monitoring area.

[0012] Furthermore, the process of obtaining the temperature-air volume linear parameter includes: Arrange all the temperature data of each sensor device in each monitoring area in chronological order during the monitoring period to obtain a temperature data time series; arrange all the air volume data of each sensor device in each monitoring area in chronological order during the monitoring period to obtain an air volume data time series; determine the temperature-air volume linear parameter according to the normalized value of the Pearson correlation coefficient between the temperature data time series and the air volume data time series.

[0013] Further, the process of remotely monitoring the power environment of the computer room according to the regional feature anomaly index includes: Regarding the monitoring areas with regional feature anomaly indexes greater than the preset anomaly threshold as high-risk areas; remotely monitoring the power environment of the computer room based on the high-risk areas.

[0014] In a second aspect, the present application provides a remote monitoring system for the power environment of a computer room based on a sensor network. The system includes: A data acquisition module, configured to obtain the temperature data and air volume data collected by each sensor device in each monitoring area of the computer room during the monitoring time period; An environmental anomaly weight determination module, configured to determine the corresponding temperature normality according to the abnormal fluctuation of the temperature data of each sensor device in each monitoring area; determine the corresponding air volume anomaly degree according to the relative position of the air source and the abnormal mutation of the air volume data of each sensor device in each monitoring area; determine the environmental anomaly weight of each monitoring area according to the temperature normality and the air volume anomaly degree; A remote monitoring module for the power environment of the computer room, configured to determine the corresponding regional feature anomaly index according to the linear fitting situation between the temperature data and the air volume data in each monitoring area and the environmental anomaly weight; remotely monitor the power environment of the computer room according to the regional feature anomaly index.

[0015] In a third aspect, the present application provides a computer device, including a memory and a processor. The memory is used to store computer program code, and the processor is used to call and run the computer program code from the memory to execute the method as described in the first aspect or any embodiment of the first aspect of the present application.

[0016] In a fourth aspect, the present application provides a computer program product, which includes computer program code. When the computer program code is executed, it executes the method as described in the first aspect or any embodiment of the first aspect of the present application.

[0017] 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 executes the method as described in the first aspect or any embodiment of the first aspect of the present application.

[0018] The present application has the following beneficial effects: 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 anomalies of the air volume time series curve and the relative position weights of the air sources, 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. Further, environmental anomalies are comprehensively reflected in two dimensions of temperature anomaly and air volume anomaly, overcoming the limitations of a single indicator. And finally, based on the characteristic that the air volume and temperature will show linear changes under normal conditions, combined with the environmental anomaly weight, the regional characteristic anomaly index that more accurately represents the anomaly situation of each monitoring area is comprehensively determined, making the effect of remote monitoring of the computer room power environment by the regional characteristic anomaly index better. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0020] Figure 1 It is a flowchart of a method for remote monitoring of the power environment of a computer room based on a sensor network provided by an embodiment of the present invention; Figure 2 It is a structural diagram of a system for remote monitoring of the power environment of a computer room based on a sensor network provided by an embodiment of the present invention; Figure 3 It is a schematic structural diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details the specific implementation manners, structures, features, and effects of a method for remote monitoring of the power environment of a computer room based on a sensor network proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment, and specific features, structures, or characteristics in one or more embodiments can 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 indicating relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs.

[0023] The following specifically describes the specific solution of a remote monitoring method for the power environment of a computer room based on a sensor network provided by the present invention with reference to the accompanying drawings.

[0024] An embodiment of the present application provides a remote monitoring method for the power environment of a computer room based on a sensor network. Please refer to Figure 1 , which shows a flowchart of a remote monitoring method for the power environment of a computer room based on a sensor network provided by an embodiment of the present invention. The method includes: Step S101: In a monitoring time period, obtain the temperature data and air volume data collected by each sensor device in each monitoring area of the computer room.

[0025] In a specific implementation manner of the embodiment of the present invention, a square area centered on each computer room device (such as a server, a switch, a hardware gateway, etc.) in the computer room 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 diagonals of the square area of the monitoring area. The sensor device includes a temperature sensor and an air volume sensor, and 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 through a low-power wide area network for data processing. It should be noted that the division of the monitoring area and the position setting of the sensor device can be adjusted according to the specific implementation environment and will not be further elaborated here.

[0026] In a specific implementation manner of the embodiment of the present invention, a monitoring time period is set every 10 seconds. After all the temperature data and air volume data in a monitoring time period are collected, an analysis and calculation of the regional feature anomaly index are performed, and remote monitoring of the power environment of the computer room is carried out based on the regional feature anomaly index; in addition, the sampling frequency is set to collect once per second, and the length of the monitoring time period and the sampling frequency can be adjusted according to the specific implementation environment.

[0027] Step S102: Determine the corresponding temperature normality according to the abnormal fluctuation of the temperature data of each sensor device in each monitoring area; determine the corresponding air volume anomaly degree according to the relative position of the air source and the abnormal mutation of the air volume data of each sensor device in each monitoring area; determine the environmental anomaly weight of each monitoring area according to the temperature normality and the air volume anomaly degree.

[0028] For the computer room environment, a slow increase in the environmental temperature in the computer room is normal and linear. However, a relatively high instantaneous temperature increase may correspond to abnormal temperature changes or may be temperature jitter that belongs to normal temperature changes. Therefore, this application analyzes the abnormal fluctuations in the temperature data of each sensor in the monitored area, and determines the temperature performance in the monitored area based on the normal degree of temperature.

[0029] Preferably, in some possible implementation manners of the embodiments of the present invention, the process of obtaining the normal degree of temperature includes: According to the instantaneous temperature change situation of each sensor device in each monitored area, determine the corresponding temperature abnormal change parameter; wherein, the process of obtaining the temperature abnormal change parameter includes: During the monitoring time period, the difference between the temperature data of each sensor device in each monitored 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 at all sampling moments is greater than or equal to the preset temperature fluctuation threshold, set the temperature abnormal change parameter of the corresponding sensor device to the preset first threshold; when the maximum value of the instantaneous temperature change values at all sampling moments is less than the preset temperature fluctuation threshold, set the temperature abnormal change parameter of the corresponding sensor device to the preset second threshold; wherein, the preset first threshold is greater than the preset second threshold.

[0030] In a specific implementation manner of the embodiments 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 indicates that there is a large temperature change in a short period of time, and the possibility of corresponding temperature abnormality is relatively high. Therefore, the role of the temperature abnormal change parameter here is to judge whether there is an abnormality in the instantaneous temperature. When the maximum value of the instantaneous temperature change value is greater than or equal to the preset temperature fluctuation threshold, it indicates that there is an abnormal instantaneous temperature change in the monitoring time period. Therefore, the amplitude is 1 to further analyze whether there is a real temperature abnormality; when the maximum value of the instantaneous temperature change value is less than the preset temperature fluctuation threshold, it indicates that the overall temperature change is relatively stable and there is no significant temperature change abnormality, and no further analysis is required. Therefore, the value is assigned 0 to not consider the subsequent analysis situation.

[0031] During the monitoring period, the difference between the temperature data at the last sampling moment and the temperature data at the first sampling moment collected by each sensor device in each monitoring area is used as the corresponding overall temperature change value; the range of the temperature data collected by each sensor device in each monitoring area is used as the maximum temperature change value; according to the ratio between the overall temperature change value and the maximum temperature change value, the corresponding abnormal change degree is determined. For temperature jitter, temperature jitter usually occurs instantaneously. Therefore, after the temperature shows an abnormal change, it usually returns to normal within a short period of time. Therefore, if the overall temperature change value is significantly smaller than the maximum temperature change value, it means that the temperature returns to normal after a short period of abnormal change, and the temperature still shows a normal change trend as a whole. So the corresponding abnormal change degree should be smaller; if the overall temperature change value is relatively close to the maximum temperature change value, it means that there may be an abnormal temperature rise that does not return to the normal temperature. Therefore, the corresponding abnormal change degree should be larger.

[0032] According to the temperature data mean, abnormal change degree, and temperature abnormal change parameter of each sensor device in each monitoring area during the monitoring period, the reference temperature parameter of each sensor device is determined; among them, the process of obtaining the reference temperature parameter includes: performing a negative correlation mapping on the product of the temperature data mean, abnormal change degree, 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 temperature data mean, the higher the overall temperature level, and thus the higher the possibility of temperature abnormality. Therefore, based on the temperature data mean, combined with the abnormal change degree representing temperature abnormality and the temperature abnormal change parameter for comprehensive analysis, and through the negative correlation mapping method, the smaller the obtained reference temperature parameter, the more likely it corresponds to the temperature abnormal situation. Therefore, finally, according to the mean of the reference temperature parameters of all sensor devices in each monitoring area, the corresponding temperature normality degree is determined.

[0033] In a specific implementation manner of the embodiment of the present invention, the process of obtaining the reference temperature parameter is expressed by the formula: ; where is the reference temperature parameter of the th sensor device in the th monitoring area; is the mean value of the temperature data of the th sensor device in the th monitoring area during the monitoring period; is the temperature abnormal change parameter corresponding to the th sensor device in the th monitoring area; is the th in the The temperature data of the last sampling moment of a sensor device during the monitoring period; For the th The temperature data of the first sampling moment of a sensor device in the th For the th The overall temperature change value corresponding to the th th The maximum temperature data of the th th sensor device in the monitoring period; For the th The minimum temperature data of the th th sensor device in the monitoring period; Is the linear normalization function. It should be noted that to ensure the meaningfulness of the calculation results, in the embodiments of the present invention, when performing fractional operations, in the case of a denominator of 0, a tuning factor greater than 0 needs to be added to the denominator for addition to prevent the denominator from being 0. In a specific implementation manner of the embodiments of the present invention, the tuning factor is set to 0.1; the value of the tuning factor can be set by the implementer according to the actual situation, and this application does not make special restrictions.

[0034] In a specific implementation manner of the embodiments of the present invention, the process of obtaining the temperature normality is expressed by the formula: ; where Is the temperature normality of the th For the The number of sensor devices in the th th The reference temperature parameter of the sensor device in the monitoring area;

[0035] For the air volume data, when the change in the air volume collected by the sensor is large, it indicates that there may be a malfunction in the equipment corresponding to the air source in the environment, such as a malfunction in the air conditioner used for refrigeration. For the sensors closer to the air source, the more credible the abnormal change in the air volume they reflect, so the higher the weight corresponding to the analysis of the abnormal air volume data. Therefore, the abnormal degree of the air volume comprehensively characterized by the relative position of the air source and the abnormal mutation of the air volume data further determines the abnormal situation of the air volume data.

[0036] Preferably, in some possible implementation manners of the embodiments of the present invention, the process of obtaining the abnormal degree of the 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 according to the abnormal situation of the change trend of the air volume data time series curve. The process of obtaining the degree of fluctuation abnormality includes: on the air volume data time series curve, take the mean value of the absolute values of the tangent slopes at all sampling moments as the degree of fluctuation abnormality.

[0037] For the air volume data, under normal circumstances, the air volume data is usually relatively stable and shows a relatively slow change when changing; according to the definition of the slope, the larger the absolute value of the tangent slope at each sampling moment on the air volume data time series curve, the more prominent the change in the overall air volume data, so the greater the degree of fluctuation abnormality, the more abnormal the air volume data change is from the normal situation, and the more abnormal the environment is in the dimension of the air volume data.

[0038] 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 air source outlets; among them, the larger the overall air volume change value, the greater the overall change in the air volume data after the monitoring time period, and the more likely it is that the air source device cannot ensure that the air volume data returns to the normal data after a malfunction, so the higher the abnormal degree of the environment in the air volume data. Since the sensors closer to the air source have a higher weight in analyzing the abnormal air volume data, the minimum distance between the sensor device and all air source outlets is negatively correlated and mapped, so that the larger the determined distance weight, the higher the weight of the corresponding sensor in analyzing the abnormal air volume data.

[0039] When the range of air volume data is larger, it indicates that there is a large numerical span in the air volume data during the monitoring period. Therefore, the range of air volume data characterizes the mutation of air volume data. Correspondingly, the larger the range of air volume data, the more serious the abnormal situation corresponding to the air volume data when it is abnormal. Therefore, similar to the overall air volume change value and the degree of fluctuation abnormality, the range of air volume data is also positively correlated with the abnormal performance of air volume data. Further, the product of the range of air volume data, distance weight, overall air volume change value, and degree of fluctuation abnormality at all sampling times on the air volume data time series curve is normalized to determine the air volume abnormality parameter of each sensor device. The larger the air volume abnormality parameter, the more serious the environmental abnormality reflected by the corresponding sensor device in the dimension of air volume data. Finally, according to the average value of the air volume abnormality parameters of all sensor devices in each monitoring area, the air volume abnormality degree of each monitoring area is comprehensively determined.

[0040] In a specific implementation manner of the embodiment of the present invention, the acquisition process of the air volume abnormality parameter is expressed by the formula: ; where is the air volume abnormality parameter of the th sensor device in the th monitoring area; is the range of air volume data at all sampling times on the air volume data time series curve of the th sensor device in the th monitoring area; is the average value of the absolute values of the tangent slopes at all sampling times on the air volume data time series curve of the th sensor device in the th monitoring area, that is, the corresponding degree of fluctuation abnormality; is the air volume data at the last sampling time on the air volume data time series curve of the th sensor device in the th monitoring area; is the air volume data at the first sampling time on the air volume data time series curve of the th sensor device in the th monitoring area; is the overall air volume change value of the th sensor device in the th monitoring area; is the minimum distance between the th sensor device in the th monitoring area and all air source outlets; is the exponential function with the natural constant as the base; is the distance weight corresponding to the th sensor device in the th monitoring area.

[0041] In a specific implementation manner of the embodiment of the present invention, the process of obtaining the air volume abnormality degree is expressed by the formula: ; where is the air volume abnormality degree of the th monitoring area; is the number of sensor devices in the th monitoring area; is the th sensor device in the th monitoring area, and is the air volume abnormality parameter of the sensor device.

[0042] When the temperature normality degree is smaller, it indicates that the temperature performance of the corresponding monitoring area is more abnormal; when the air volume abnormality degree is larger, it indicates that the air volume performance of the corresponding monitoring area is more abnormal; therefore, when comprehensively characterizing the environmental abnormality situation from two aspects of temperature and air volume, the smaller the corresponding temperature normality degree and the larger the air volume abnormality degree, the greater the environmental abnormality weight for characterizing the environmental abnormality situation should be. Specifically, the process of obtaining the environmental abnormality weight includes: Determine the environmental abnormality weight of each monitoring area according to the product between the negative correlation mapping value of the temperature normality degree and the air volume abnormality degree. In a specific implementation manner of the embodiment of the present invention, the process of obtaining the environmental abnormality weight is expressed by the formula: ; where is the environmental abnormality weight of the th monitoring area; is the air volume abnormality degree of the th monitoring area; is the temperature normality degree of the th monitoring area; is the exponential function with the natural constant as the base.

[0043] Step S103: Determine the corresponding area characteristic abnormality index according to the linear fitting situation between the temperature data and the air volume data in each monitoring area and the environmental abnormality weight; perform remote monitoring of the computer room power environment according to the area characteristic abnormality index.

[0044] In addition to characterizing the computer room environment abnormality situation based on the abnormality of the air volume data and the abnormality of the temperature data, it is also necessary to consider that under normal circumstances, the air volume output of the air source in the computer room corresponds to the temperature in the environment. When the temperature is higher, the air volume output is larger, and when the temperature is lower, the air volume output is smaller, that is, the corresponding air volume data and temperature data should maintain a certain positive correlation linear relationship in time series. Therefore, further analysis is carried out by combining the linear fitting situation between the air volume data and the temperature data, that is, the correlation situation, on the basis of the environmental abnormality weight.

[0045] Preferably, in some possible implementation manners of the embodiments of the present invention, the process of obtaining the regional feature anomaly index includes: According to the change correlation between the temperature data and the air volume data of each sensor device in each monitoring area during the monitoring time period, determine the corresponding temperature-air volume linear parameter; the process of obtaining the corresponding temperature-air volume linear parameter includes: Arrange all the temperature data of each sensor device in each monitoring area in chronological order during the monitoring time period to obtain a temperature data time series; arrange all the air volume data of each sensor device in each monitoring area in chronological order during the monitoring time period to obtain an air volume data time series; determine the temperature-air volume linear parameter according to the normalized value of the Pearson correlation coefficient between the temperature data time series and the air volume data time series. According to the properties of the Pearson correlation coefficient, the larger the corresponding temperature-air volume linear parameter, the more positively linearly correlated the temperature data time series and the air volume data time series are, and the more the corresponding temperature change and air volume change conform to the normal situation; therefore, the smaller the temperature-air volume linear parameter, the more abnormal the environment reflected by the data collected by the corresponding sensor device.

[0046] Further, combining the temperature-air volume linear parameters of all sensor devices, normalize the product of the negative correlation mapping value of the average value of the temperature-air volume linear parameters of all sensor devices in each monitoring area and the environmental anomaly weight to determine the regional feature anomaly index of each monitoring area; the larger the regional feature anomaly index, the more prominent the environmental anomaly performance of the corresponding monitoring area.

[0047] In a specific implementation manner of the embodiments of the present invention, the process of obtaining the regional feature anomaly index is expressed by the formula: ; where is the regional feature anomaly index of the th monitoring area; is the environmental anomaly weight of the th monitoring area; is the number of sensor devices in the th monitoring area; is the Pearson correlation coefficient between the temperature data time series and the air volume data time series of the th sensor device in the th monitoring area; is the temperature-air volume linear parameter of the th sensor device in the th monitoring area; is the exponential function with the natural constant as the base. Among them, through normalization, the value range of the regional feature anomaly index is restricted within 0 to 1, making the representation of the environmental anomaly situation in the monitoring area more intuitive and facilitating the subsequent screening of high-risk areas.

[0048] Preferably, in a specific implementation manner of the embodiment of the present invention, the process of remotely monitoring the power environment of the computer room according to the regional feature anomaly index includes: regarding the monitoring area with the regional feature anomaly index greater than the preset anomaly threshold as a high-risk area; remotely monitoring the power environment of the computer room according to the high-risk area. In a specific implementation manner of the 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 elaborated further here. Since the larger the regional feature anomaly index, the more abnormal the environment of the corresponding monitoring area, the monitoring areas with larger regional feature anomaly indexes are selected as high-risk areas for remotely monitoring the power environment of the computer room.

[0049] In a specific implementation manner of the embodiment of the present invention, when a high-risk area is detected, the server information corresponding to the high-risk area is sent to the manager's terminal, and a risk alarm is issued to promptly handle the situation of environmental anomalies.

[0050] In summary, the remote monitoring method for the power environment of the computer room based on the sensor network first effectively distinguishes normal fluctuations from real anomalies by analyzing the instantaneous fluctuation and overall change 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 anomaly problems such as ventilation failures. Further, it comprehensively reflects environmental anomalies in two dimensions of temperature anomaly and air volume anomaly, overcoming the limitations of a single index. And finally, based on the characteristic that the air volume and temperature will show a linear change under normal circumstances, combined with the environmental anomaly weight, the regional feature anomaly index that more accurately represents the anomaly situation of each monitoring area is comprehensively determined, making the effect of remotely monitoring the power environment of the computer room using the regional feature anomaly index better.

[0051] This application also provides a remote monitoring system for the power environment of a computer room based on a sensor network. Please refer to Figure 2 , which shows the structural diagram of a remote monitoring system for the power environment of a computer room 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 remote monitoring module 203 for the power environment of the computer room.

[0052] 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; The environmental anomaly weight determination module 202 is configured to determine the corresponding temperature normality degree according to the temperature data fluctuation anomaly conditions of each sensor device in each monitoring area; determine the corresponding air volume anomaly degree according to the relative position of the air source and the abnormal mutation conditions of the air volume data of each sensor device in each monitoring area; and determine the environmental anomaly weight of each monitoring area according to the temperature normality degree and the air volume anomaly degree. The computer room power environment remote monitoring module 203 is configured to determine the corresponding regional feature anomaly index according to the linear fitting condition 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 according to the regional feature anomaly index.

[0053] It should be noted that the system provided in the above embodiments is only illustrated by the division of the above functional modules. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, a computer room power environment remote monitoring system based on a sensor network and a method embodiment of a computer room power environment remote monitoring method based on a sensor network provided in the above embodiments belong to the same concept. For the specific implementation process, please refer to the method embodiment and will not be elaborated here.

[0054] An embodiment of the present application also provides a computer device. Please refer to Figure 3 FIG. 10, which shows a schematic structural diagram of a computer device provided in 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. When the processor 302 executes the computer program 303, the computer device can execute any one of the above-described computer room power environment remote monitoring methods based on a sensor network.

[0055] An embodiment of the present application also provides a computer program product. When the computer program product runs on a computer device, the computer device can execute any one of the above-described computer room power environment remote monitoring methods based on a sensor network.

[0056] An embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium stores computer program code. When the computer program code runs on a computer device, the computer device can execute any one of the above-described computer room power environment remote monitoring methods based on a sensor network.

[0057] In the embodiments provided in the present application, it should be understood that the provided computer device, computer program product, and computer-readable storage medium are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the methods provided above, and will not be elaborated here.

[0058] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0059] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and 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 includes: In the monitoring time period, obtaining the temperature data and air volume data collected by each sensor device in each monitoring area of the computer room; According to the abnormal temperature data fluctuations of each sensor device in each monitoring area, determining the corresponding temperature normality degree; according to the relative positions of the air sources of each sensor device in each monitoring area and the abnormal mutation of the air volume data, determining the corresponding air volume abnormality degree; according to the temperature normality degree and the air volume abnormality degree, determining the environmental abnormality weight of each monitoring area; According to the linear fitting situation between the temperature data and the air volume data in each monitoring area and the environmental abnormality weight, determining the corresponding regional characteristic abnormality index; performing remote monitoring of the computer room power environment according to the regional characteristic abnormality index.

2. The remote monitoring method for the power environment of a computer room based on a sensor network according to claim 1, characterized in that The process of obtaining the temperature normality degree includes: According to the instantaneous temperature change situation of each sensor device in each monitoring area, determining the corresponding temperature abnormal change parameter; In the monitoring time period, taking the difference between the temperature data at the last sampling moment and the temperature data at the first sampling moment collected by each sensor device in each monitoring area as the corresponding overall temperature change value; taking the range of the temperature data collected by each sensor device in each monitoring area as the maximum temperature change value; determining the corresponding abnormal change degree according to the ratio between the overall temperature change value and the maximum temperature change value; According to the average temperature data of each sensor device in each monitoring area in the monitoring time period, the abnormal change degree and the temperature abnormal change parameter, determining the reference temperature parameter of each sensor device; according to the average value of the reference temperature parameters of all sensor devices in each monitoring area, determining the corresponding temperature normality degree.

3. The remote monitoring method for the power environment of a computer room based on a sensor network according to claim 2, characterized in that, The process of obtaining the temperature abnormal change parameter includes: In the monitoring time period, taking 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 as the temperature instantaneous change value at each sampling moment; when the maximum value of the temperature instantaneous change values at all sampling moments is greater than or equal to the preset temperature fluctuation threshold, setting the temperature abnormal change parameter of the corresponding sensor device as the preset first threshold; When the maximum value of the temperature instantaneous change values at all sampling moments is less than the preset temperature fluctuation threshold, setting the temperature abnormal change parameter of the corresponding sensor device as the preset second threshold; where the preset first threshold is greater than the preset second threshold.

4. A remote monitoring method for the power environment of a computer room based on a sensor network according to claim 2, characterized in that, The process of obtaining the reference temperature parameter includes: Performing negative correlation mapping on the product of the average temperature data 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. A remote monitoring method for the power environment of a computer room based on a sensor network according to claim 1, characterized in that, The process of obtaining the air volume abnormality degree includes: Arranging all the air volume data collected by each sensor device in each monitoring area in chronological order and performing curve fitting to determine the corresponding air volume data time series curve; determining the fluctuation abnormality degree according to the abnormal change situation of the 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 time series curve of the air volume data 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 air source outlets; Normalize the product of the range of the air volume data at all sampling moments on the time series curve of the air volume data, the distance weight, the overall air volume change value, and the degree of fluctuation anomaly to determine the air volume anomaly parameter of each sensor device; Determine the corresponding degree of air volume anomaly according to the mean value of the air volume anomaly parameters of all sensor devices in each monitoring area; 6. The remote monitoring method for the power environment of a computer room based on a sensor network according to claim 5, characterized in that, The acquisition process of the degree of fluctuation anomaly includes: On the time series curve of the air volume data, the mean value of the absolute values of the tangent slopes at all sampling moments is used as the degree of fluctuation anomaly; 7. A remote monitoring method for the power environment of a computer room based on a sensor network according to claim 1, characterized in that The acquisition process of the environmental anomaly weight includes: Determine the environmental anomaly weight of each monitoring area according to the product of the negative correlation mapping value of the temperature normality degree and the degree of air volume anomaly; 8. A remote monitoring method for the power environment of a computer room based on a sensor network according to claim 1, characterized in that The acquisition process of the regional characteristic anomaly index includes: Determine the corresponding temperature-air volume linear parameter according to the change correlation between the temperature data and the air volume data of each sensor device in each monitoring area during the monitoring period; Normalize the product of the negative correlation mapping value of the mean value of the temperature-air volume linear parameters of all sensor devices in each monitoring area and the environmental anomaly weight to determine the regional characteristic anomaly index of each monitoring area; 9. A remote monitoring method for the power environment of a computer room based on a sensor network according to claim 8, characterized in that, The acquisition process of the temperature-air volume linear parameter includes: Arrange all the temperature data of each sensor device in each monitoring area in chronological order during the monitoring period to obtain a temperature data time series; arrange all the air volume data of each sensor device in each monitoring area in chronological order during the monitoring period to obtain an air volume data time series; determine the temperature-air volume linear parameter according to the normalized value of the Pearson correlation coefficient between the temperature data time series and the air volume data time series; 10. A remote monitoring method for the power environment of a computer room based on a sensor network according to claim 1, characterized in that, The process of remotely monitoring the computer room power environment according to the regional characteristic anomaly index includes: Regard the monitoring area with a regional characteristic anomaly index greater than the preset anomaly threshold as a high-risk area; remotely monitor the computer room power environment according to the high-risk area;

Images