CN117873838A - Method and system for monitoring ambient temperature of telecommunication equipment - Google Patents
Method and system for monitoring ambient temperature of telecommunication equipment Download PDFInfo
- Publication number
- CN117873838A CN117873838A CN202410275050.4A CN202410275050A CN117873838A CN 117873838 A CN117873838 A CN 117873838A CN 202410275050 A CN202410275050 A CN 202410275050A CN 117873838 A CN117873838 A CN 117873838A
- Authority
- CN
- China
- Prior art keywords
- data
- history
- historical
- detected
- similarity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012544 monitoring process Methods 0.000 title claims abstract description 30
- 230000002159 abnormal effect Effects 0.000 claims abstract description 26
- 238000012216 screening Methods 0.000 claims abstract description 13
- 230000002547 anomalous effect Effects 0.000 claims abstract description 6
- 230000005856 abnormality Effects 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 21
- 230000006870 function Effects 0.000 claims description 17
- 238000010606 normalization Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 abstract description 5
- 238000012545 processing Methods 0.000 abstract description 3
- 238000010276 construction Methods 0.000 description 12
- 238000004422 calculation algorithm Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 5
- 238000001514 detection method Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 230000002269 spontaneous effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002243 precursor Substances 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a method and a system for monitoring the environmental temperature of telecommunication equipment, wherein the method comprises the steps of acquiring temperature data in the operation environment of the telecommunication equipment; determining the similarity of the temperature data and the historical data of the node at the same time of the history, and the credibility of the historical data; calculating the contribution degree of each data to the whole data according to the similarity and the credibility of the historical data; screening out data to be detected by using the contribution degree to calculate an abnormal score of the data to be detected in the isolated forest binary tree; the anomaly score is compared with a set threshold to determine whether the data to be detected appears anomalous. According to the scheme of the invention, the problems of poor accuracy and low reliability of the current environment temperature monitoring process of the telecommunication equipment are solved.
Description
Technical Field
The present invention relates generally to the field of data processing technology. More particularly, the present invention relates to a method and system for monitoring the ambient temperature of a telecommunications device.
Background
Telecommunication devices refer to hardware and software systems that utilize wired, wireless, electromagnetic or optical transmission, reception, or transmission of voice, text, data, images, or any other information of any nature. During operation of telecommunications equipment, it is desirable to maintain an appropriate temperature range to ensure proper operation and to extend life. Temperature has a direct impact on the lifetime of electronic components, and too high or too low a temperature may negatively impact device performance and even cause hardware failure. The abnormal temperature is often a precursor of equipment failure, potential failure can be predicted by monitoring and analyzing the environmental temperature data in real time, and corresponding preventive and maintenance measures are taken to reduce the occurrence rate of equipment failure. The device can timely find and cope with the overheat condition of the device, ensure the device to operate in a stable temperature range, effectively improve the reliability and stability of a telecommunication system, reduce the maintenance cost, optimize the energy efficiency, meet the industry specification and provide support for the sustainable development of the telecommunication industry.
The method for monitoring the ambient temperature of the telecommunication equipment is mainly realized according to the identification abnormal data, and the identification of the abnormal data needs to have certain timeliness so as to avoid the occurrence of sudden circuit spontaneous combustion disasters caused by overhigh ambient temperature of the telecommunication equipment. In the existing method for identifying abnormal data, an isolated forest algorithm is a relatively efficient algorithm for identifying abnormal data, and the abnormal data is identified by selecting a proper splitting value to continuously divide the data into two types so as to realize the segmentation of the abnormal value. However, when processing time sequence data with huge data volume, the continuous classification efficiency of the whole data is low, the accuracy of the result cannot be ensured, and the judging process of the abnormal data is inaccurate.
Based on the above, how to solve the problems of poor accuracy and low reliability of the current environmental temperature monitoring process of the telecommunication equipment is an important link for guaranteeing the performance of the telecommunication equipment.
Disclosure of Invention
In order to solve one or more of the technical problems, the invention provides that the size of a data set can be reduced, the calculation complexity is reduced, the execution efficiency of an algorithm is improved, the influence of data noise can be reduced by screening the data, and the identification accuracy is improved by participating in the construction of an isolated forest binary tree. To this end, the present invention provides solutions in various aspects as follows.
In a first aspect, the present invention provides a method for monitoring the ambient temperature of a telecommunication device, comprising: acquiring temperature data in an operating environment of the telecommunication equipment; determining the similarity of the temperature data and the historical data of the node at the same time of the history and the credibility of the historical data; calculating the contribution degree of each data to the whole data according to the similarity and the credibility of the historical data, wherein the calculation formula of the contribution degree is as follows:in which, in the process,G i the degree of contribution to the ith data,XS i,j for the similarity of the i-th data to the historical data j of the node at the same time as the history,K j for the confidence level of the history data j,na time period representing the history data is represented,norm() Is a standard normalization function; screening out data to be detected by using the contribution degree to calculate an abnormal score of the data to be detected in the isolated forest binary tree; the anomaly score is compared with a set threshold to determine whether the data to be detected appears anomalous.
In one embodiment, wherein the similarity of temperature data to historical data of a node at the same time of the history is calculated using the following formula:，/>in which, in the process,QS i for the trend of the time period for which the ith data is located,x i as the value of the i-th data,x q the value of the remaining data q for the period of time in which the ith data is located,N dt,i when the ith data is locatedThe number of data of the remaining data of interval dt,XS i,j for the similarity of the ith data to the historical data j of the node at the same time of history,QS j as the trend of the time period in which the history data j corresponding to the i-th data is located,x j for the value of the history j, n represents the time period of the history,norm() As a function of the normalization of the standard,exp() Is an exponential function.
In one embodiment, the calculation formula of the credibility of the historical data is as follows:in which, in the process,K j for the confidence level of the history data j,SX zj for the upper limit of the overall data zj obtained by the history data j on the date of its data acquisition,XX zj for the lower limit of the overall data zj obtained by the history data j on the date of its data acquisition,x j as the value of the history data j,P(j,zj) For the frequency of occurrence of the history data j in the overall data zj obtained on the date of its data acquisition,σ zj as the variance of the overall data zj,norm() Is a standard normalization function.
In one embodiment, the screening out the data to be detected by using the contribution degree comprises: comparing the contribution to a contribution threshold; and in response to the contribution degree being smaller than the contribution degree threshold, determining that the contribution degree of the temperature data to the whole data is lower, and taking the whole data as the data to be detected.
In one embodiment, the contribution level threshold is set to 0.23.
In one embodiment, comparing the anomaly score to a set threshold to determine whether the data to be detected appears anomalous comprises: comparing the anomaly score with a set threshold; and in response to the abnormality score being greater than a set threshold, determining that the data to be detected appears abnormal.
In one embodiment, wherein the set threshold is 0.86.
In a second aspect, the present invention also provides a telecommunications device ambient temperature monitoring system, comprising: a processor; a memory storing computer program instructions that when executed by the processor implement a telecommunications device ambient temperature monitoring method in accordance with one or more of the previous embodiments.
The invention has the beneficial effects that: according to the scheme of the invention, the size of the data set can be reduced by screening part of data, so that the computational complexity of constructing a binary tree is reduced, and the method is beneficial to improving the execution efficiency of an algorithm, especially for a large-scale data set or a real-time monitoring system. Meanwhile, the method for establishing the binary tree by screening part of data is beneficial to improving the efficiency and accuracy of the model in monitoring the environmental temperature of the telecommunication equipment. Also, in telecommunications equipment ambient temperature monitoring, noise data may be present, which may mislead the anomaly detection model. By screening the data, the influence of noise can be reduced, and the accuracy of identifying the true abnormality can be improved.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. In the drawings, embodiments of the invention are illustrated by way of example and not by way of limitation, and like reference numerals refer to similar or corresponding parts and in which:
FIG. 1 is a flow chart schematically illustrating a method of monitoring ambient temperature of a telecommunications device in accordance with an embodiment of the present invention;
fig. 2 is a composition diagram schematically showing a method of monitoring an ambient temperature of a telecommunication device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.
Fig. 1 is a flow chart schematically illustrating a method 100 of monitoring an ambient temperature of a telecommunication device according to an embodiment of the invention.
As shown in fig. 1, at step S101, temperature data is acquired. In particular, temperature data in an operating environment of a telecommunications device is obtained. In some embodiments, a plurality of temperature sensors may be provided around the telecommunications device to collect temperature data.
At step S102, similarity and reliability with the history data are determined. Specifically, the similarity between the temperature data and the historical data of the same time node of the history and the credibility of the historical data are determined.
In some embodiments, the similarity of temperature data to historical data of a node at the same time of the history is calculated using the following formula:
。
in the method, in the process of the invention,QS i for the trend of the time period for which the ith data is located,x i as the value of the i-th data,x q the value of the remaining data q for the period of time in which the ith data is located,N dt,i for the number of data of the remaining data of the time period dt for which the ith data is located,XS i,j for the similarity of the ith data to the historical data j of the node at the same time of history,QS j as the trend of the time period in which the history data j corresponding to the i-th data is located,x j for the value of the history j, n represents the time period of the history,norm() As a function of the normalization of the standard,exp() Is an exponential function.
The calculation formula of the credibility of the historical data is as follows:
。
in the method, in the process of the invention,K j for the confidence level of the history data j,SX zj for the upper limit of the overall data zj obtained by the history data j on the date of its data acquisition,XX zj for the lower limit of the overall data zj obtained by the history data j on the date of its data acquisition,x j as the value of the history data j,P(j,zj) For the frequency of occurrence of the history data j in the overall data zj obtained on the date of its data acquisition,σ zj as the variance of the overall data zj,norm() Is a standard normalization function.
At step S103, the degree of contribution is calculated. Specifically, the contribution degree of each data to the whole data is calculated according to the similarity and the credibility of the historical data, wherein the calculation formula of the contribution degree is as follows:
。
in the method, in the process of the invention,G i the degree of contribution to the ith data,XS i,j for the similarity of the i-th data to the historical data j of the node at the same time as the history,K j for the confidence level of the history data j,na time period representing the history data is represented,norm() Is a standard normalization function.
At step S104, the screening data builds a binary tree. Specifically, the contribution degree is utilized to screen out data to be detected, so that the abnormal score of the data to be detected in the isolated forest binary tree is calculated.
In some embodiments, the contribution level may be compared to a contribution level threshold. And in response to the contribution degree being smaller than the contribution degree threshold, determining that the contribution degree of the temperature data to the whole data is lower, and taking the whole data as the data to be detected. The contribution level threshold may be set to 0.23.
At step S105, an abnormality is analyzed. Specifically, the anomaly score may be compared with a set threshold to determine whether the data to be detected appears to be anomalous. In some embodiments, the anomaly score may be compared to a set threshold. And in response to the abnormality score being greater than the set threshold, determining that the data to be detected appears abnormal. Wherein the set threshold may be 0.86.
The following will describe the embodiments of the present invention in detail.
The invention mainly aims at an application scene of carrying out anomaly detection on temperature data of the surrounding environment in the operation process of the telecommunication equipment, and automatically adjusting the environment temperature by identifying the anomaly data so as to realize intelligent control and adjustment on the environment temperature in the operation process of the telecommunication equipment.
First, it is necessary to obtain temperature data in the operating environment of the telecommunication device. When monitoring the ambient temperature of the telecommunication device, the energy loss caused by the resistance of the current flowing in the telecommunication device is mainly aimed at in the operation process of the telecommunication device, and the energy loss is expressed as heat, namely, the heat is released in the operation process of the telecommunication device. When the temperature rises to a certain extent, disasters such as spontaneous combustion of a circuit and the like can be caused, so that the disasters can be timely dealt with by monitoring the ambient temperature of the telecommunication equipment, and the operation safety of the equipment is improved.
The ambient temperature data of the telecommunication device needs to be collected first before the monitoring is performed, and the ambient temperature data of the telecommunication device can be collected by installing a temperature sensor in the operating environment of the telecommunication device. For example, the data acquisition time interval can be set to be 2s (empirical value), and the acquired data is transmitted to the anomaly monitoring device so as to monitor the ambient temperature of the telecommunication device.
In the embodiment, the identification of the abnormal data is realized by adopting an isolated forest algorithm. When the isolated forest algorithm detects abnormality of a data set with larger data quantity, the problem of slower efficiency is solved, and the problem can be solved to a certain extent by constructing a binary tree by screening part of data.
Specifically, the contribution degree of each data to the whole data is calculated, and the data to be detected is screened out according to the contribution degree and used for constructing a binary tree in an isolated forest algorithm.
In the process of screening data, in order to further improve the construction efficiency of the binary tree, the data with high abnormality probability is screened to perform abnormality detection on the data, namely the data to be detected is used as the data to be detected to participate in the construction process of the binary tree. The data with larger abnormality degree has a difference expression with a certain characteristic with other normal data, namely the abnormal data has lower contribution degree to the whole data.
In summary, in the process of screening data, the lower the contribution degree of each data to the whole data is, the greater the possibility of abnormality is, the greater the necessity of abnormality detection is, and the greater the necessity of participating in the construction of a binary tree as the data to be detected is.
In this embodiment, the contribution degree of the data to the whole data may be calculated by the similarity between the data and the historical data corresponding to the same time node of the history, and the reliability corresponding to the historical data. Taking the ith data as an example, the contribution degree of the ith data to the whole data is obtained by the following steps:
(1) Degree of contribution of the ith data
The contribution degree of the ith data is mainly reflected according to the abnormality degree of the ith data. The degree of abnormality of the ith data can be reflected according to the similarity of the ith data and the historical data j corresponding to the same time node of the history and the reliability of the historical data j, and the lower the similarity of the current data and the historical data j corresponding to the same time node of the history is, the greater the degree of abnormality of the ith data is, and the lower the corresponding contribution degree is. The higher the correlation between the historical data j and the whole data of the day collected by the historical data j, the higher the credibility of the historical data j, and the more accurate the contribution degree result of the ith data.
The temperature data change of the telecommunication device environment is greatly affected by the load change and the user use time period, for example, the temperature is lower in the morning, the device is just started, and the environment temperature is in a rising stage. The equipment is then operated normally during the working period, gradually increasing in temperature, and at this time most users are working, the rising trend of the ambient temperature of the telecommunication equipment is different from the trend of change in the morning. As user network usage decreases at night, the device load may decrease and the temperature may drop slightly. That is, whether the current data appears as abnormal data is also related to the trend of the data change and the period of time. Thus, this step is actually to screen out the data to be detected.
The step of obtaining similarity of the ith data and the historical data j of the node at the same time of history and reliability of the historical data j comprises the following steps:
(a1) Similarity to historical same time node data.
With the popularity of internet telecommunication devices, there have been fewer users who can extend the use of telecommunication devices, that is, the number of users of telecommunication devices has grown more slowly. This means that the number of people using the telecommunication device varies over the past several consecutive days to form different laws in different time periods, corresponding to a smaller difference in the ambient temperature of the telecommunication device for the same time period over several consecutive days.
Therefore, the degree of abnormality of the current ith data can be reflected according to the similarity between the ith data and the data at the rest of corresponding time in the time period, and the lower the similarity between the ith data and the data at the rest of corresponding time in the time period is, the greater the degree of abnormality of the current ith data is, and the greater the possibility of taking the ith data as the data to be detected is.
The method comprises the steps of obtaining the similarity of the current ith data and the historical node data at the same time, wherein the method comprises the following steps:
setting the time period of the historical data for analyzing the similarity of the ith data and the historical data at the same time as the past 15 days, traversing all the acquired temperature data, and analyzing the numerical value difference between the ith data and the historical data j acquired at the same acquisition time as the ith data in the previous 15 days, wherein the similarity is lower as the numerical value difference is larger. Meanwhile, the higher the similarity of the data trend of the current ith data in the time period and the data trend of the current ith data in the same time period corresponding to the historical data j in the previous 15 days, the more credible the numerical difference between the current ith data and the historical data j corresponding to the previous 15 days. The current time period in which the ith data is located is set to be 30min before and after the ith data is collected, and the cumulative sum of the first order differences between the ith data and the data q collected in the time period is used for reflecting the data trend of the time period in which the ith data is located (the same time period in which the jth historical data is located).
In summary, the greater the numerical difference between the i-th data and the corresponding historical data j in the time period of the historical data, the lower the similarity between the i-th data and the historical data j, and the greater the corresponding abnormality degree; and, the smaller the difference between the data trend of the time period in which the i-th data is located and the data trend of the time period in which the history data j is located, the more reliable the similarity of the i-th data and the history data j is.
Wherein, the similarity of the current ith data and the node data j at the same time of historyXS i,j Expressed as:
。
in the method, in the process of the invention,QS i for the trend of the time period for which the ith data is located,x i as the value of the i-th data,x q the value of the remaining data q for the period of time in which the ith data is located,N dt,i the number of data pieces of the rest data of the time period dt in which the ith data is located;QS j is a trend of a time period in which the history data j corresponding to the i-th data is located (acquisition method and program)QS i Similarly, the details are not repeated here),x j a value of the history data j, 15 represents a time period of the history data;norm() As a function of the normalization of the standard,exp() Is an exponential function.x i －x j For the numerical difference of the i-th data and the history data j,QS i －QS j for the trend difference between the i-th data and the time period in which the history data j is located,the smaller the trend difference between the ith data and the time period where the historical data j is located, the more credible the numerical value difference between the ith data and the historical data j is; />The greater the difference in the values of the ith data and the historical data j, the lower the similarity of the ith data and the historical data j.
(a2) Confidence of the historical data.
The similarity between the current ith data and the historical data j reflects the abnormality degree of the current data i to a certain extent, but when the historical data j is not trusted, the similarity result between the ith data and the historical data j is not trusted, so that the possibility that whether the current ith data participates in the construction of a binary tree to perform abnormality identification is affected.
The credibility of the historical data j can be reflected according to the correlation between the historical data j and the whole data acquired on the day of data acquisition, and the higher the correlation between the historical data j and the whole data acquired on the day of data acquisition, the higher the credibility of the historical data j. Wherein such correlation is expressed as: the difference ratio between the upper limit and the lower limit of the whole data acquired on the day of data acquisition of the history data j reflects the offset degree of the history data j in the whole data.
The larger the difference between the upper limit and the lower limit of the overall data acquired on the day of data acquisition of the historical data j and the lower the correlation between the historical data j and the overall data acquired on the day of data acquisition of the historical data j, the lower the credibility of the corresponding historical data j; meanwhile, the higher the frequency of occurrence of the integral data obtained by the historical data j on the data acquisition day and the smaller the variance of the integral data, the more stable the integral data is distributed, and the more reliable the correlation of the historical data j is.
Wherein, the credibility of the history data jK j Expressed as:
。
in the method, in the process of the invention,SX zj for the upper limit of the overall data zj obtained by the history data j on the day of its data acquisition,XX zj for the lower limit of the overall data zj obtained by the historical data j on the data acquisition day (the method for obtaining the upper and lower limits is a known technique in the box diagram, and will not be described in detail here）；x j As the value of the history data j,P(j,zj) For the frequency of occurrence of the history data j in the overall data zj obtained on the day of its data acquisition,σ zj as the variance of the overall data zj,norm() Is a standard normalization function.
(a3) Degree of data contribution
The higher the credibility of the historical data j is, the similarity of the i-th data with the historical data j of the node at the same time with the historyXS i,j The more accurate the result; similarity of i-th data to historical data j of node at the same time as historyXS i,j The lower the degree of abnormality of the ith data is, the lower the degree of contribution to the collected whole data is, the higher the necessity of abnormal data detection is, and the greater the possibility of taking the abnormal data as data to be detected to participate in binary tree construction is.
Wherein the degree of contribution of the ith dataG i Expressed as:
。
in the method, in the process of the invention,XS i,j for the similarity of the ith data to the historical data j of the node at the same time of history,K j for the confidence level of the history data j, 15 represents the time period of the history data,norm() Is a standard normalization function.
It should be noted that the setting of the time period of the above-mentioned history data to 15 days is merely exemplary and not limitative, and those skilled in the art can set the time period according to actual needs.
(2) Data to be detected participating in binary tree construction
When the contribution degree of the ith data to the whole dataG i If less than 0.23, the i-th data has a low contribution to the overall data, and the higher the necessity of detecting abnormal data, the greater the possibility of participating in binary tree construction as data to be detected. At this time, the ith data is used as the data to be detected to participate in the construction of an isolated forest binary tree, and the construction is carried outAnd detecting the isolated forest abnormality to identify whether the ith data is abnormal data.
And then, calculating an anomaly score of the data to be detected in the isolated forest binary tree, and comparing the anomaly score with a preset threshold value to determine that the data to be detected appears as anomaly data.
(3) Obtaining abnormal data and giving out early warning.
According to the steps, the data to be detected which participate in the construction of the isolated forest binary tree are obtained, and the construction of the isolated forest binary tree is carried out to identify abnormal data. When the abnormal score of the screened data to be detected in the isolated forest binary tree (the prior art in the isolated forest) exceeds the set threshold value of 0.86, the data to be detected can be considered to be abnormal, and an early warning is sent out to remind relevant staff to process in time so as to monitor the environmental temperature of the telecommunication equipment.
Fig. 2 is a composition diagram schematically showing a method of monitoring an ambient temperature of a telecommunication device according to an embodiment of the present invention.
The invention also provides a telecommunication equipment environment temperature monitoring system. As shown in fig. 2, the system comprises a processor and a memory storing computer program instructions which, when executed by the processor, implement a method of monitoring the ambient temperature of a telecommunication device according to the foregoing.
The system further comprises other components known to those skilled in the art, such as a communication bus and a communication interface, the arrangement and function of which are known in the art and are therefore not described in detail herein.
In the context of this patent, the foregoing memory may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, the computer readable storage medium may be any suitable magnetic or magneto-optical storage medium, such as, for example, resistance change Memory RRAM (Resistive Random Access Memory), dynamic Random Access Memory DRAM (Dynamic Random Access Memory), static Random Access Memory SRAM (Static Random-Access Memory), enhanced dynamic Random Access Memory EDRAM (Enhanced Dynamic Random Access Memory), high-Bandwidth Memory HBM (High-Bandwidth Memory), hybrid storage cube HMC (Hybrid Memory Cube), etc., or any other medium that may be used to store the desired information and that may be accessed by an application, a module, or both. Any such computer storage media may be part of, or accessible by, or connectable to, the device. Any of the applications or modules described herein may be implemented using computer-readable/executable instructions that may be stored or otherwise maintained by such computer-readable media.
In the description of the present specification, the meaning of "a plurality", "a number" or "a plurality" is at least two, for example, two, three or more, etc., unless explicitly defined otherwise.
While various embodiments of the present invention have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Many modifications, changes, and substitutions will now occur to those skilled in the art without departing from the spirit and scope of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in practicing the invention.
Claims (8)
1. A method for monitoring the ambient temperature of a telecommunications device, comprising:
acquiring temperature data in an operating environment of the telecommunication equipment;
determining the similarity of the temperature data and the historical data of the node at the same time of the history and the credibility of the historical data;
calculating the contribution degree of each data to the whole data according to the similarity and the credibility of the historical data, wherein the calculation formula of the contribution degree is as follows:
in the method, in the process of the invention,G i is the firsti degrees of data contribution,XS i,j for the similarity of the i-th data to the historical data j of the node at the same time as the history,K j for the confidence level of the history data j,na time period representing the history data is represented,norm() Is a standard normalization function;
screening out data to be detected by using the contribution degree to calculate an abnormal score of the data to be detected in the isolated forest binary tree;
the anomaly score is compared with a set threshold to determine whether the data to be detected appears anomalous.
2. The method of claim 1, wherein the similarity between the temperature data and the historical data of the same historical time node is calculated using the following formula:
in the method, in the process of the invention,QS i for the trend of the time period for which the ith data is located,x i as the value of the i-th data,x q the value of the remaining data q for the period of time in which the ith data is located,N dt,i for the number of data of the remaining data of the time period dt for which the ith data is located,XS i,j for the similarity of the ith data to the historical data j of the node at the same time of history,QS j as the trend of the time period in which the history data j corresponding to the i-th data is located,x j for the value of the history j, n represents the time period of the history,norm() As a function of the normalization of the standard,exp() Is an exponential function.
3. The method for monitoring the ambient temperature of a telecommunications device of claim 1, wherein the confidence level of the historical data is calculated as:
in the method, in the process of the invention,K j for the confidence level of the history data j,SX zj for the upper limit of the overall data zj obtained by the history data j on the date of its data acquisition,XX zj for the lower limit of the overall data zj obtained by the history data j on the date of its data acquisition,x j as the value of the history data j,P(j,zj) For the frequency of occurrence of the history data j in the overall data zj obtained on the date of its data acquisition,σ zj as the variance of the overall data zj,norm() Is a standard normalization function.
4. The method for monitoring the ambient temperature of a telecommunication device according to claim 1, wherein the step of screening out the data to be detected by using the contribution degree comprises the steps of:
comparing the contribution to a contribution threshold;
and in response to the contribution degree being smaller than the contribution degree threshold, determining that the contribution degree of the temperature data to the whole data is lower, and taking the whole data as the data to be detected.
5. The telecommunications device ambient temperature monitoring method of claim 4, wherein the contribution level threshold is set to 0.23.
6. The method of claim 1, wherein comparing the anomaly score to a set threshold to determine whether the data to be detected appears anomalous comprises:
comparing the anomaly score with a set threshold;
and in response to the abnormality score being greater than a set threshold, determining that the data to be detected appears abnormal.
7. The telecommunications device ambient temperature monitoring method of claim 6, wherein the set threshold is 0.86.
8. A telecommunications device ambient temperature monitoring system, comprising:
a processor;
a memory storing computer program instructions which, when executed by the processor, implement a telecommunications device ambient temperature monitoring method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410275050.4A CN117873838B (en) | 2024-03-12 | 2024-03-12 | Method and system for monitoring ambient temperature of telecommunication equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410275050.4A CN117873838B (en) | 2024-03-12 | 2024-03-12 | Method and system for monitoring ambient temperature of telecommunication equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117873838A true CN117873838A (en) | 2024-04-12 |
| CN117873838B CN117873838B (en) | 2024-05-24 |
Family
ID=90597061
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410275050.4A Active CN117873838B (en) | 2024-03-12 | 2024-03-12 | Method and system for monitoring ambient temperature of telecommunication equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117873838B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007173907A (en) * | 2005-12-19 | 2007-07-05 | Nippon Telegr & Teleph Corp <Ntt> | Abnormal traffic detection method and device |
| CN105071961A (en) * | 2015-07-30 | 2015-11-18 | 中国人民解放军信息工程大学 | Method and device for predicting service quality of Web service |
| CN109298697A (en) * | 2018-11-13 | 2019-02-01 | 远光软件股份有限公司 | Thermal power plant's various parts working state evaluation method based on DBM Dynamic Baseline Model |
| CN110135495A (en) * | 2019-05-15 | 2019-08-16 | 国网湖南省电力有限公司 | What a kind of grid equipment was efficiently ablated ice necessity sentences knowledge method and system |
| CN110728458A (en) * | 2019-10-18 | 2020-01-24 | 支付宝(杭州)信息技术有限公司 | Target object risk monitoring method and device and electronic equipment |
| US20210209467A1 (en) * | 2018-09-25 | 2021-07-08 | Ennew Digital Technology Co., Ltd. | Method and device for predicting thermal load of electrical system |
| US11281553B1 (en) * | 2021-04-16 | 2022-03-22 | Vignet Incorporated | Digital systems for enrolling participants in health research and decentralized clinical trials |
| CN115840897A (en) * | 2023-02-09 | 2023-03-24 | 广东吉器电子有限公司 | Temperature sensor data exception handling method |
| WO2023061342A1 (en) * | 2021-10-13 | 2023-04-20 | 中兴通讯股份有限公司 | Data trend detection method, electronic device, and storage medium |
| CN116628617A (en) * | 2023-07-25 | 2023-08-22 | 值数科技(北京)有限公司 | Method for realizing miniature strain monitoring based on nanocomposite |
| CN116701983A (en) * | 2023-08-03 | 2023-09-05 | 青岛冠成软件有限公司 | Cold-chain logistics real-time monitoring data processing method and system |
| CN117200241A (en) * | 2023-11-06 | 2023-12-08 | 南通威森新能源科技有限公司 | New forms of energy intelligent voltage regulation system that is incorporated into power networks |
| CN117312825A (en) * | 2023-09-26 | 2023-12-29 | 航天信息股份有限公司 | Target behavior detection method and device, electronic equipment and storage medium |
-
2024
- 2024-03-12 CN CN202410275050.4A patent/CN117873838B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007173907A (en) * | 2005-12-19 | 2007-07-05 | Nippon Telegr & Teleph Corp <Ntt> | Abnormal traffic detection method and device |
| CN105071961A (en) * | 2015-07-30 | 2015-11-18 | 中国人民解放军信息工程大学 | Method and device for predicting service quality of Web service |
| US20210209467A1 (en) * | 2018-09-25 | 2021-07-08 | Ennew Digital Technology Co., Ltd. | Method and device for predicting thermal load of electrical system |
| CN109298697A (en) * | 2018-11-13 | 2019-02-01 | 远光软件股份有限公司 | Thermal power plant's various parts working state evaluation method based on DBM Dynamic Baseline Model |
| CN110135495A (en) * | 2019-05-15 | 2019-08-16 | 国网湖南省电力有限公司 | What a kind of grid equipment was efficiently ablated ice necessity sentences knowledge method and system |
| CN110728458A (en) * | 2019-10-18 | 2020-01-24 | 支付宝(杭州)信息技术有限公司 | Target object risk monitoring method and device and electronic equipment |
| US11281553B1 (en) * | 2021-04-16 | 2022-03-22 | Vignet Incorporated | Digital systems for enrolling participants in health research and decentralized clinical trials |
| WO2023061342A1 (en) * | 2021-10-13 | 2023-04-20 | 中兴通讯股份有限公司 | Data trend detection method, electronic device, and storage medium |
| CN115840897A (en) * | 2023-02-09 | 2023-03-24 | 广东吉器电子有限公司 | Temperature sensor data exception handling method |
| CN116628617A (en) * | 2023-07-25 | 2023-08-22 | 值数科技(北京)有限公司 | Method for realizing miniature strain monitoring based on nanocomposite |
| CN116701983A (en) * | 2023-08-03 | 2023-09-05 | 青岛冠成软件有限公司 | Cold-chain logistics real-time monitoring data processing method and system |
| CN117312825A (en) * | 2023-09-26 | 2023-12-29 | 航天信息股份有限公司 | Target behavior detection method and device, electronic equipment and storage medium |
| CN117200241A (en) * | 2023-11-06 | 2023-12-08 | 南通威森新能源科技有限公司 | New forms of energy intelligent voltage regulation system that is incorporated into power networks |
Non-Patent Citations (2)
| Title |
|---|
| DEEPAK AHLAWAT等: "Enhancement of the Accuracy and QoS in Clustering of Data", 《2020 8TH INTERNATIONAL CONFERENCE ON RELIABILITY, INFOCOM TECHNOLOGIES AND OPTIMIZATION (TRENDS AND FUTURE DIRECTIONS) (ICRITO)》, 5 June 2020 (2020-06-05), pages 849 - 853, XP033827301, DOI: 10.1109/ICRITO48877.2020.9197774 * |
| 韩康，李雪源，马晓晨: "基于时间序列的音频采集通道故障检测研究", 《航空计算技术》, vol. 52, no. 05, 31 October 2022 (2022-10-31), pages 106 - 113 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117873838B (en) | 2024-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022068645A1 (en) | Database fault discovery method, apparatus, electronic device, and storage medium | |
| WO2021213247A1 (en) | Anomaly detection method and device | |
| CN116992399B (en) | Power equipment operation and maintenance assessment method based on power data analysis | |
| CN110188015B (en) | Host access relation abnormal behavior self-adaptive detection device and monitoring method thereof | |
| CN112188531A (en) | Abnormality detection method, abnormality detection device, electronic apparatus, and computer storage medium | |
| CN103746829A (en) | Cluster-based fault perception system and method thereof | |
| CN115865649B (en) | Intelligent operation and maintenance management control method, system and storage medium | |
| US20210209189A1 (en) | System and methods monitoring the technical status of technical equipment | |
| CN112884199A (en) | Method and device for predicting faults of hydropower station equipment, computer equipment and storage medium | |
| CN115085994A (en) | Information centralized safety management system of internal physical machine of cloud computing | |
| CN116955091A (en) | Data center fault detection system based on machine learning | |
| CN116502166A (en) | Prediction method, device, equipment and medium based on other equipment data | |
| CN117041019A (en) | Log analysis method, device and storage medium of content delivery network CDN | |
| CN116311829B (en) | Remote alarm method and device for data machine room | |
| CN117873838B (en) | Method and system for monitoring ambient temperature of telecommunication equipment | |
| CN116594446B (en) | Temperature control method and system for big data center | |
| CN116071902B (en) | Method, equipment and medium for monitoring power equipment of machine room | |
| CN113568950A (en) | Index detection method, device, equipment and medium | |
| CN112905419B (en) | Index data monitoring threshold range determining method and device and readable storage medium | |
| CN117585554B (en) | Equipment inspection method and inspection system | |
| Wang et al. | Anomaly monitoring in high-density data centers based on gaussian distribution anomaly detection algorithm | |
| CN115242611B (en) | Network fault alarm level management method, device, equipment and storage medium | |
| CN114553558B (en) | Data processing method and device | |
| CN117053619B (en) | Cooling tower operation monitoring system and control method | |
| Zhang et al. | An improved OAKR approach to condition monitoring of rotating machinery |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |