CN117667589A - Network hardware operation risk monitoring and early warning system - Google Patents
Network hardware operation risk monitoring and early warning system Download PDFInfo
- Publication number
- CN117667589A CN117667589A CN202311671322.4A CN202311671322A CN117667589A CN 117667589 A CN117667589 A CN 117667589A CN 202311671322 A CN202311671322 A CN 202311671322A CN 117667589 A CN117667589 A CN 117667589A
- Authority
- CN
- China
- Prior art keywords
- early warning
- temperature
- temperature state
- analysis
- network hardware
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 48
- 238000000605 extraction Methods 0.000 claims abstract description 11
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000012797 qualification Methods 0.000 claims abstract description 4
- 230000008859 change Effects 0.000 claims description 29
- 238000000034 method Methods 0.000 claims description 20
- 230000008569 process Effects 0.000 claims description 17
- 238000011156 evaluation Methods 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000010992 reflux Methods 0.000 abstract description 12
- 230000002159 abnormal effect Effects 0.000 abstract description 8
- 230000017525 heat dissipation Effects 0.000 abstract description 6
- 238000012549 training Methods 0.000 description 17
- 238000013527 convolutional neural network Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000007664 blowing Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012423 maintenance 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
- 230000004044 response Effects 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Emergency Alarm Devices (AREA)
Abstract
The invention relates to the technical field of network hardware, and discloses a network hardware operation risk monitoring and early warning system, which comprises: the acquisition module is used for acquiring the temperature value in the target server cabinet in real time; the processing module is used for receiving the temperature value, preprocessing the temperature value and then generating a corresponding feature picture according to a preset feature extraction rule; the analysis module is used for receiving the characteristic pictures, inputting the characteristic pictures into a trained temperature state identification model and obtaining a temperature state judgment result; the temperature state judging result comprises qualification and disqualification; and the early warning module is used for receiving the temperature state judgment result and sending an early warning signal to the artificial end when the temperature state judgment result is unqualified. The condition of whether hot air reflux occurs in the cabinet is monitored in real time, so that timely and accurate discovery is achieved, and the problem that the hot air reflux condition is hidden and is possibly discovered when the server has abnormal heat dissipation is solved.
Description
Technical Field
The invention relates to the technical field of network hardware, in particular to a network hardware operation risk monitoring and early warning system.
Background
Faults that may occur in network devices include business faults at the software level and hardware faults at the hardware level, where servers are an important component in network hardware, mainly providing computing services, etc. Since the server needs to respond to the service request and process it, the server should generally have the ability to afford the service and secure the service. The service types provided by the servers are different and are divided into file servers, database servers, application program servers and the like. The main components of the server include a processor, hard disk, memory, system bus, etc., similar to a general purpose computer architecture.
In the big data age, a large amount of IT equipment is centrally placed in data centers. These data centers include servers, storage, switches, and a large number of racks and other infrastructure of each type. Each IT device is composed of various hardware boards, such as a computing module, a storage module, a chassis, a fan module, and the like. The server cabinets are usually densely packed with devices such as servers, switches and storage devices, which consume power and generate heat, and as the performance of the servers increases, the power consumed by the devices is increased, so that very concentrated heat loads are formed in the server cabinets, and the heat generated by the heat loads is very unfavorable to the performance, safety and service life of the devices if not dissipated in time.
When the air quantity of the air return system in the machine room is smaller than the air blowing air quantity of the server cabinet or the air quantity of the air supply system is larger than the suction air quantity of the server cabinet, the air of the hot channel can flow back to the forefront end of the system through the clearance between the side wall of the cabinet and the side edge of the server cabinet, and the hot air backflow is the hot air backflow. The hot air backflow has great influence on the heat dissipation of the server, so that the rotation speed of a fan of the server is increased, the heat dissipation power consumption is increased, and the system components can be overheated to influence the normal use and downtime when serious.
However, because the condition of hot air backflow is hidden, the on-site inspection of maintenance personnel is difficult to discover risks in time, and the problem of hot air backflow of the cabinet is usually discovered when the server has abnormal heat dissipation, therefore, the network hardware operation risk monitoring and early warning system is provided to solve the technical problems.
Disclosure of Invention
The invention aims to provide a network hardware operation risk monitoring and early warning system, which solves the following technical problems:
how to provide a monitoring and early warning system capable of timely and accurately monitoring the temperature state in a server cabinet.
The aim of the invention can be achieved by the following technical scheme:
a network hardware operational risk monitoring and early warning system, comprising:
the acquisition module is used for acquiring the temperature value in the target server cabinet in real time;
the processing module is used for receiving the temperature value, preprocessing the temperature value and then generating a corresponding feature picture according to a preset feature extraction rule;
the analysis module is used for receiving the characteristic pictures, inputting the characteristic pictures into a trained temperature state identification model and obtaining a temperature state judgment result; the temperature state judging result comprises qualification and disqualification;
the early warning module is used for receiving the temperature state judgment result and sending an early warning signal to the artificial end when the temperature state judgment result is unqualified;
wherein the temperature state recognition model is a trained machine learning model.
Preferably, the process of monitoring the temperature value in the target server cabinet in real time is as follows:
monitoring points are respectively arranged on two sides of a front panel facing an air inlet end and two side cabinet walls of the target server cabinet;
and respectively acquiring temperature values of the positions of the monitoring points through the monitoring points.
Preferably, the process of generating the corresponding feature picture according to the preset feature extraction rule after preprocessing the temperature value is as follows:
by the formulaCalculating a temperature change coefficient;
generating a corresponding temperature coefficient change curve Y which changes along with time according to the temperature change coefficient;
coordinate axes corresponding to the temperature coefficient change curves Y are arranged on the blank pictures in a matching mode, and the temperature coefficient change curves Y of the monitoring points at different positions are arranged on the blank pictures according to a preset arrangement sequence;
wherein alpha is t T is the temperature change coefficient at time T t For the temperature value at time T, T 0 Is a preset temperature state value.
Preferably, the monitoring points arranged on the two sides of the front panel and the cabinet walls on the two sides are arranged in a matrix, and the preset arrangement sequence is randomly set according to the positions of the monitoring points.
Preferably, the analysis module further comprises:
comparing the temperature coefficient change curve Y with a corresponding standard interval:
if Y is lower than [ lower, yup ], standard analysis meets the requirements, and early warning analysis is carried out;
otherwise, the standard analysis does not meet the requirements;
here, [ ilow, yup ] represents a standard interval corresponding to a temperature coefficient.
Preferably, the early warning analysis process is as follows:
deriving Y to obtain a time-varying curve Y' of the temperature variation;
comparing Y' with a corresponding variation threshold value:
if Y '< Y' th, the early warning analysis meets the requirements;
otherwise, the early warning analysis does not meet the requirements;
wherein Y' th represents the variation threshold of the temperature.
Preferably, the analysis module further comprises: and evaluating the temperature state according to the temperature state judging result, the standard analysis and the early warning analysis result:
by passing throughCalculating a temperature state evaluation coefficient Con;
wherein, when the temperature state judging result is qualified, phi 1 ＝φ 2 =0, when the temperature state judgment result is unqualified,γ 1 and gamma 2 The weight coefficient is preset;
comparing Con with a preset threshold Clow and Cup:
if Con is more than or equal to Cup, judging that the temperature state is extremely poor;
if Cup > Con > Clow, judging that the temperature state is poor;
preferably, the early warning module further comprises:
receiving the standard analysis and early warning analysis results, and sending an early warning signal to the artificial end when the standard analysis is not in accordance with the requirements and the early warning analysis is not in accordance with the requirements;
receiving the temperature state evaluation result, and sending out a first-level early warning when the temperature state is extremely poor; and when the temperature state is poor, sending out a secondary early warning.
The invention has the beneficial effects that:
according to the network hardware operation risk monitoring and early warning system, the temperature value in the cabinet of the target server is obtained, the corresponding feature picture is generated according to the preset feature extraction rule after the temperature value is preprocessed, then the feature picture generated according to the preset feature extraction rule is input into the trained temperature state recognition model, so that whether hot air reflux occurs in the cabinet can be monitored in real time, the condition of hot air reflux can be timely and accurately found, the possibility of operation risk of the server is timely reduced by intervention, the problem that the hot air reflux condition is hidden is solved, and the problem that the server is likely to find when the heat dissipation abnormality occurs is usually solved.
Drawings
The invention is further described below with reference to the accompanying drawings.
Fig. 1 is a schematic diagram of a system module connection according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. 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.
Referring to fig. 1, the present invention is a network hardware running risk monitoring and early warning system, comprising:
the acquisition module is used for acquiring the temperature value in the target server cabinet in real time;
the processing module is used for receiving the temperature value, preprocessing the temperature value and then generating a corresponding feature picture according to a preset feature extraction rule;
the analysis module is used for receiving the characteristic pictures, inputting the characteristic pictures into a trained temperature state identification model and obtaining a temperature state judgment result; the temperature state judgment result comprises qualification and disqualification;
the early warning module is used for receiving the temperature state judgment result and sending an early warning signal to the manual end when the temperature state judgment result is unqualified;
wherein the temperature state recognition model is a trained machine learning model.
Through the technical scheme, the temperature value in the cabinet of the target server is obtained, the corresponding feature picture is generated according to the preset feature extraction rule after the temperature value is preprocessed, then the feature picture generated according to the preset feature extraction rule is input into the trained temperature state recognition model, and whether hot air reflux occurs in the cabinet or not can be monitored in real time, so that the hot air reflux occurs can be timely and accurately found, the possibility of running risk of the server is timely reduced, high-temperature damage to the server is prevented, the problem that the hot air reflux condition is hidden and is likely to be found when heat dissipation abnormality occurs in the server is solved.
The machine learning algorithm adopted in the invention is based on a Convolutional Neural Network (CNN), the convolutional neural network (Convolutional Neural Networks, CNN) is a feedforward neural network (Feedforward Neural Networks) which comprises convolutional calculation and has a depth structure and is commonly used for analyzing visual images, and the machine learning algorithm is mostly used for classifying and searching the images in the practical application process, and has the advantages of sharing convolutional kernels, no pressure on high-dimensional data processing, no need of manually selecting characteristic values and good characteristic classification effect; however, a large number of training samples subjected to classification labeling are required during training, and parameter adjustment is performed in the process.
The process of monitoring the temperature value in the target server cabinet in real time comprises the following steps:
monitoring points are respectively arranged on two sides of a front panel facing an air inlet end and two side cabinet walls on the target server cabinet;
and respectively acquiring temperature values of the positions of the monitoring points through the monitoring points.
The process of generating the corresponding feature picture according to the preset feature extraction rule after preprocessing the temperature value is as follows:
by the formulaCalculating a temperature change coefficient;
generating a corresponding temperature coefficient change curve Y which changes along with time according to the temperature change coefficient;
coordinate axes corresponding to the temperature coefficient change curves Y are matched and set on the blank pictures, and the temperature coefficient change curves Y of the monitoring points at different positions are set on the blank pictures according to a preset arrangement sequence;
wherein alpha is t T is the temperature change coefficient at time T t For the temperature value at time T, T 0 Is a preset temperature state value.
Through the technical scheme, the cabinet on two sides and two sides of the front panel facing the air inlet end on the target server cabinetThe wall is provided with monitoring points so as to monitor the temperatures of the two sides of the front panel facing the air inlet end and the wall positions of the two sides of the target server cabinet in real time, and then preprocess the temperature values, specifically, the temperature values are preprocessed through a formulaCalculating the temperature coefficient of variation alpha t Wherein T is t For the temperature value at time T, T 0 As for the preset temperature state value, it should be noted that the preset temperature state value T 0 According to experimental data fitting calculation, the temperature of the central area of the front panel of the server cabinet can be set according to the temperature condition, and further the temperature change coefficient alpha can be obtained according to t Judging whether hot air reflux occurs in the current server cabinet, and timely and accurately finding out the hot air reflux occurrence;
and then generating a corresponding temperature coefficient change curve Y which changes along with time according to the temperature change coefficient, matching and setting coordinate axes corresponding to the temperature coefficient change curve Y on a blank picture, and setting the temperature coefficient change curves Y of monitoring points at different positions on the blank picture according to a preset arrangement sequence, so that a large number of characteristic pictures can be obtained, and a new characteristic picture can be obtained by changing the preset arrangement sequence, but the temperature coefficient contained in the characteristic picture is unchanged, thereby being beneficial to multiplying training samples in a training stage without manually marking again, and fully improving the quantity and expansion efficiency of the training samples.
In the invention, the acquisition mode of the training sample of the machine learning model is basically the same as that of the feature picture, and manual marking is needed, that is, the data in the training sample is required to be compared by adopting the existing judging mode to determine whether the training sample is qualified or not, and the temperature change coefficient of a period of time before the unqualified judging result appears can be used as the training sample with unqualified labels to train, so that a large number of training samples can be obtained, and although the training process is possibly complicated, once the training is finished, early warning can be provided by the machine learning model when the server has not high-temperature damage.
The monitoring points arranged on the two sides of the front panel and the cabinet walls on the two sides are arranged in a matrix, and the preset arrangement sequence is randomly set according to the positions of the monitoring points.
Through the technical scheme, the monitoring points arranged in the matrix can provide a large number of training samples in the training process of the machine learning model, so that the efficient training of the machine learning model is facilitated, the recognition accuracy of the temperature state recognition model can be ensured, the monitoring points arranged on the cabinet walls on two sides are used for monitoring hot air flowing back to the forefront end of the system through the clearance between the side edges of the server case, the clearance between the clearance is different, the flowing channels of the hot air are different, and therefore, the conditions of response of the monitoring points arranged on the cabinet walls on two sides are different, a large number of training samples are also provided for training, and the recognition accuracy of the temperature state recognition model is improved.
The analysis module further includes:
comparing the temperature coefficient change curve Y with a corresponding standard interval:
if Y is lower than [ lower, yup ], standard analysis meets the requirements, and early warning analysis is carried out;
otherwise, the standard analysis does not meet the requirements;
here, [ ilow, yup ] represents a standard interval corresponding to a temperature coefficient.
Through the above technical scheme, the present embodiment provides a process of performing standard analysis, specifically, comparing a temperature coefficient change curve Y with a corresponding standard interval, so as to determine whether the temperature state of each monitoring point position meets the requirement, where [ low, yup ] represents the standard interval corresponding to the temperature coefficient, and is obtained by fitting and calculating the working state of the server according to experimental data, so that when Y e [ low, yup ], it is indicated that the standard analysis meets the requirement, otherwise, the standard analysis does not meet the requirement, and early warning is required.
The early warning analysis process comprises the following steps:
deriving Y to obtain a time-varying curve Y' of the temperature variation;
comparing Y' with a corresponding variation threshold value:
if Y '< Y' th, the early warning analysis meets the requirements;
otherwise, the early warning analysis does not meet the requirements;
wherein Y' th represents the variation threshold of the temperature.
Through the technical scheme, the embodiment provides a process for performing early warning analysis, specifically, deriving Y to obtain a time-dependent curve Y' of the temperature variation; and comparing the Y' with a corresponding variation threshold value, so that whether the temperature of each monitoring point is abnormal or not can be judged, and further, when the temperature is in a standard range but the variation is abnormal, early warning analysis of the temperature state is realized, and further, the early warning analysis is timely found at the initial stage of abnormal temperature state change, so that the artificial end can be conveniently and timely prevented and controlled, and the server is prevented from causing high-temperature damage.
It should be noted that, during standard analysis and early warning analysis, the temperature state value T is preset 0 The temperature monitoring device can be set to be a normal temperature value in the cabinet, so that the temperature state in the cabinet is monitored while the hot air reflux condition is monitored, other abnormal temperature conditions which are not hot air reflux are monitored, the temperature condition in the cabinet is monitored in a multi-way manner, the running safety of the server is improved, the running risk of the server is reduced, meanwhile, the manual terminal is helped to make corresponding measures according to the conditions, and the working efficiency is improved.
The analysis module further includes: evaluating the temperature state according to the temperature state judging result, the standard analysis and the early warning analysis result:
by passing throughCalculating a temperature state evaluation coefficient Con;
wherein when the temperature state judgment result is qualified,when the temperature state judgment result is disqualified, the method comprises the steps of (1) performing (I)>γ 1 And gamma 2 The weight coefficient is preset;
comparing Con with a preset threshold Clow and Cup:
if Con is more than or equal to Cup, judging that the temperature state is extremely poor;
if Cup > Con > Clow, the temperature state is judged to be poor.
Through the above technical solution, the present embodiment provides a method for evaluating a temperature state, specifically, first, whether the temperature state determination result is qualified is determined, and when the temperature state determination result is qualified, the condition that no hot air backflow occurs is described, thereby makingWhen the temperature state judgment result is disqualified, then let +.> Further, the temperature state evaluation coefficient is adjusted according to the actual temperature condition, and further, the temperature state evaluation coefficient is calculated by the formulaCalculating temperature state evaluation coefficients Con, gamma 1 And gamma 2 The temperature state evaluation coefficient Con can be obtained because the temperature state evaluation coefficient Con is a preset weight coefficient, and the current temperature state can be evaluated by comparing the temperature state evaluation coefficient Con with preset thresholds Clow and Cup.
It should be noted that the preset weight coefficient γ 1 And gamma 2 The values of Clow and Cup are obtained according to the fitting calculation of experimental data, and Cup > Clow.
The early warning module further comprises:
receiving standard analysis and early warning analysis results, and sending an early warning signal to the artificial end when the standard analysis is not in accordance with the requirements and the early warning analysis is not in accordance with the requirements;
receiving a temperature state evaluation result, and sending out a first-level early warning when the temperature state is extremely poor; and when the temperature state is poor, sending out a secondary early warning.
According to the technical scheme, when the standard analysis is not in accordance with the requirements and the early warning analysis is not in accordance with the requirements, the abnormal temperature is indicated, and an early warning signal is timely sent to the manual terminal, so that the manual terminal can process the abnormal condition in time; when the temperature state is very poor, a first-level early warning signal is sent out, and when the temperature state is poor, a second-level early warning signal is sent out, so that a manual terminal can conveniently carry out corresponding treatment measures according to the early warning level, and the working efficiency is improved.
The foregoing describes one embodiment of the present invention in detail, but the description is only a preferred embodiment of the present invention and should not be construed as limiting the scope of the invention. All equivalent changes and modifications within the scope of the present invention are intended to be covered by the present invention.
Claims (8)
1. The utility model provides a network hardware operation risk monitoring early warning system which characterized in that includes:
the acquisition module is used for acquiring the temperature value in the target server cabinet in real time;
the processing module is used for receiving the temperature value, preprocessing the temperature value and then generating a corresponding feature picture according to a preset feature extraction rule;
the analysis module is used for receiving the characteristic pictures, inputting the characteristic pictures into a trained temperature state identification model and obtaining a temperature state judgment result; the temperature state judging result comprises qualification and disqualification;
the early warning module is used for receiving the temperature state judgment result and sending an early warning signal to the artificial end when the temperature state judgment result is unqualified;
wherein the temperature state recognition model is a trained machine learning model.
2. The network hardware operational risk monitoring and early warning system according to claim 1, wherein the process of monitoring the temperature value in the target server cabinet in real time is:
monitoring points are respectively arranged on two sides of a front panel facing an air inlet end and two side cabinet walls of the target server cabinet;
and respectively acquiring temperature values of the positions of the monitoring points through the monitoring points.
3. The network hardware running risk monitoring and early warning system according to claim 2, wherein the process of generating the corresponding feature picture according to the preset feature extraction rule after preprocessing the temperature value is as follows:
by the formulaCalculating a temperature change coefficient;
generating a corresponding temperature coefficient change curve Y which changes along with time according to the temperature change coefficient;
coordinate axes corresponding to the temperature coefficient change curves Y are arranged on the blank pictures in a matching mode, and the temperature coefficient change curves Y of the monitoring points at different positions are arranged on the blank pictures according to a preset arrangement sequence;
wherein alpha is t T is the temperature change coefficient at time T t For the temperature value at time T, T 0 Is a preset temperature state value.
4. The network hardware running risk monitoring and early warning system according to claim 3, wherein monitoring points arranged on two sides of the front panel and cabinet walls on two sides are arranged in a matrix, and the preset arrangement sequence is randomly set according to the positions of the monitoring points.
5. The network hardware operational risk monitoring and early warning system of claim 4, wherein the analysis module further comprises:
comparing the temperature coefficient change curve Y with a corresponding standard interval:
if Y is lower than [ lower, yup ], standard analysis meets the requirements, and early warning analysis is carried out;
otherwise, the standard analysis does not meet the requirements;
here, [ ilow, yup ] represents a standard interval corresponding to a temperature coefficient.
6. The network hardware running risk monitoring and early warning system according to claim 5, wherein the early warning analysis process is as follows:
deriving Y to obtain a time-varying curve Y' of the temperature variation;
comparing Y' with a corresponding variation threshold value:
if Y '< Y' th, the early warning analysis meets the requirements;
otherwise, the early warning analysis does not meet the requirements;
wherein Y' th represents the variation threshold of the temperature.
7. The network hardware operational risk monitoring and early warning system of claim 6, wherein the analysis module further comprises: and evaluating the temperature state according to the temperature state judging result, the standard analysis and the early warning analysis result:
by passing throughCalculating a temperature state evaluation coefficient Con;
wherein when the temperature state judgment result is qualified,when the temperature state judgment result is disqualified, the method comprises the steps of (1) performing (I)>γ 1 And gamma 2 The weight coefficient is preset;
comparing Con with a preset threshold Clow and Cup:
if Con is more than or equal to Cup, judging that the temperature state is extremely poor;
if Cup > Con > Clow, the temperature state is judged to be poor.
8. The network hardware operational risk monitoring and early warning system of claim 7, wherein the early warning module further comprises:
receiving the standard analysis and early warning analysis results, and sending an early warning signal to the artificial end when the standard analysis is not in accordance with the requirements and the early warning analysis is not in accordance with the requirements;
receiving the temperature state evaluation result, and sending out a first-level early warning when the temperature state is extremely poor; and when the temperature state is poor, sending out a secondary early warning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311671322.4A CN117667589A (en) | 2023-12-07 | 2023-12-07 | Network hardware operation risk monitoring and early warning system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311671322.4A CN117667589A (en) | 2023-12-07 | 2023-12-07 | Network hardware operation risk monitoring and early warning system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117667589A true CN117667589A (en) | 2024-03-08 |
Family
ID=90086054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311671322.4A Pending CN117667589A (en) | 2023-12-07 | 2023-12-07 | Network hardware operation risk monitoring and early warning system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117667589A (en) |
-
2023
- 2023-12-07 CN CN202311671322.4A patent/CN117667589A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11513480B2 (en) | Method and device for automatically diagnosing and controlling apparatus in intelligent building | |
| CN109800066B (en) | Energy-saving scheduling method and system for data center | |
| Li et al. | A data-driven strategy for detection and diagnosis of building chiller faults using linear discriminant analysis | |
| US20130191676A1 (en) | Operation management method of information processing system | |
| US20090113246A1 (en) | Apparatus for and Method of Implementing system Log Message Ranking via System Behavior Analysis | |
| CN108518804A (en) | A kind of machine room humiture environmental forecasting method and system | |
| CN107133286B (en) | Method and system for generating and analyzing three-dimensional graph of temperature parameter distribution field of machine room | |
| CN117539727B (en) | Computer running state monitoring method and system | |
| Asgari et al. | A data-driven approach to simultaneous fault detection and diagnosis in data centers | |
| CN116182233A (en) | High-efficiency energy-saving heating and ventilation control device based on Internet of things | |
| CN111814388A (en) | CFD simulation verification method for lower air supply data center based on neural network | |
| CN109684385B (en) | Data center power distribution warning method, device, equipment and storage medium | |
| CN117234301A (en) | Server thermal management method based on artificial intelligence | |
| CN113029234B (en) | Method and system for detecting temperature and humidity environment of computer room for data center | |
| CN111191851A (en) | Data center energy efficiency optimization method based on knowledge graph | |
| Liu et al. | An efficient algorithm for server thermal fault diagnosis based on infrared image | |
| CN117667589A (en) | Network hardware operation risk monitoring and early warning system | |
| CN115907138B (en) | Method, system and medium for predicting PUE value of data center | |
| JP2004234302A (en) | Process management device | |
| Kumar et al. | Power usage efficiency (PUE) optimization with counterpointing machine learning techniques for data center temperatures | |
| Marwah et al. | Anomalous thermal behavior detection in data centers using hierarchical pca | |
| Ardebili et al. | Rule-Based Thermal Anomaly Detection for Tier-0 HPC Systems | |
| CN113110981B (en) | Air conditioner room health energy efficiency detection method for data center | |
| Acquaviva et al. | Rule-Based Thermal Anomaly Detection for Tier-0 HPC Systems | |
| CN115686108B (en) | Multi-level cloud management and control method and system for edge data machine room |
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 |