Unmanned aerial vehicle room monitoring system evaluation method and system

Abstract

The invention relates to the technical field of machine room operation and maintenance, in particular to an unmanned machine room monitoring system assessment method and system, which can provide accurate risk assessment and decision support for a machine room manager and ensure the safety and stability of a machine room. The method comprises the following steps: collecting a machine room environment state feature set and a machine room performance state feature set; the machine room environment state feature set at least comprises temperature, humidity, smoke concentration and electromagnetic interference intensity, and the machine room performance state feature set at least comprises server temperature, CPU utilization rate, memory occupancy rate and hard disk read-write speed; inputting the machine room environment state feature set into a machine room environment state risk evaluation model to obtain a machine room environment state risk level; inputting the machine room performance state feature set into a machine room performance state risk evaluation model to obtain a machine room performance state risk level; and judging whether the machine room environment state risk level is within a preset environment safety threshold range or not to obtain a first risk judgment result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of machine room operation and maintenance, in particular to a method and system for evaluating an unmanned machine room monitoring system. BACKGROUND

[0002] With the rapid development of information technology, unmanned machine rooms, as important places for data storage, processing and transmission, their safety and stability are crucial to ensure the continuity of business and the security of data. However, due to the complex environment and numerous equipment in the machine room, it faces various potential risks, such as overheating of environmental conditions leading to equipment failure, high or low humidity affecting the life of electronic components, fire hazards such as increased smoke concentration, and the impact of electromagnetic interference intensity on signal transmission quality. At the same time, the performance status of IT equipment itself is also a key factor affecting the stable operation of the machine room, such as high server temperature may cause hardware damage, high CPU usage may lead to processing capacity decline, high memory usage may cause system response sluggish, and abnormal hard disk read / write speed may also affect data storage and reading efficiency.

[0003] Existing machine room monitoring systems mostly monitor environmental variables and equipment performance indicators independently, but lack in-depth analysis and comprehensive evaluation of the interaction between the two, and also lack consideration of the impact of ongoing tasks in the machine room on the environment and performance, resulting in inaccurate risk assessment and difficulty in providing accurate risk warning and decision support for machine room managers. SUMMARY

[0004] To solve the above technical problems, the present application provides a method and system for evaluating an unmanned machine room monitoring system, which can provide accurate risk assessment and decision support for machine room managers and ensure the safety and stability of the machine room.

[0005] In a first aspect, the present application provides a method for evaluating an unmanned machine room monitoring system, the method comprising: collecting a set of machine room environmental state features and a set of machine room performance state features; the set of machine room environmental state features at least includes temperature, humidity, smoke concentration and electromagnetic interference intensity, and the set of machine room performance state features at least includes server temperature, CPU usage, memory usage and hard disk read / write speed; inputting the set of machine room environmental state features into a machine room environmental state risk evaluation model to obtain a machine room environmental state risk level; inputting the set of machine room performance state features into a machine room performance state risk evaluation model to obtain a machine room performance state risk level; determining whether the machine room environmental state risk level is within a preset environmental safety threshold range to obtain a first risk determination result; determining whether the machine room performance state risk level is within a preset performance safety threshold range to obtain a second risk determination result; In response to any of the first risk judgment result and the second risk judgment result being unqualified, a machine room task execution parameter is collected; the machine room task execution parameter at least includes a current task load, a task completion degree, a task delay rate, and a task response time; An environmental performance influence analysis is performed on the machine room task execution parameter to obtain a machine room risk influence feature vector; the machine room risk influence feature vector includes an environmental influence factor and a performance influence factor; Based on the machine room risk influence feature vector, an influence correction is performed on a machine room environmental state risk level and a machine room performance state risk level to obtain a corrected machine room environmental state risk level and a corrected machine room performance state risk level; It is respectively judged whether the corrected machine room environmental state risk level and the corrected machine room performance state risk level are within a preset environmental safety threshold range and a preset performance safety threshold range; if there is still any unqualified judgment result, a machine room risk warning is generated and sent.

[0006] Further, the method for constructing the machine room environmental state risk evaluation model includes: An environmental state feature set in the machine room is collected, and the collected environmental state feature set is preprocessed, the preprocessing including data cleaning, denoising, and outlier processing; The collected environmental parameters are subjected to feature extraction and feature selection to construct a training feature set of the machine room environmental state risk evaluation model; A machine learning model is selected as the basis of the model, the machine learning model including a decision tree, a support vector machine, and a random forest; The selected model is trained using the training feature set, and the model is evaluated and verified, and the model is adjusted and optimized according to the evaluation result; After the model construction and verification are completed, the model is deployed to an actual machine room monitoring system.

[0007] Further, the method for collecting the machine room task execution parameter includes: A monitoring software is installed on a server and an IT device, and an alarm threshold is set; An application program log and an API interface are connected to obtain task load, task queue length, and concurrent task number information; A task scheduling system is installed to count task completion degree; A database audit rule is set to record task state changes and calculate task completion degree; An application performance management tool is installed to monitor operation time consumption and evaluate task delay; A network monitoring tool is installed to record request response time and calculate task response time; The collected data is summarized to obtain the machine room task execution parameter.

[0008] Furthermore, the method for obtaining the feature vector of data center risk impact includes: Preprocessing of data center task execution parameters includes missing value filling, outlier detection and handling, and data standardization; Analyze the correlation between task execution parameters and environmental characteristics in the computer room; Analyze the relationship between data center task execution parameters and data center performance status characteristics; Based on the results of correlation analysis, the impact of task execution on environmental conditions and equipment performance is quantified, and environmental impact factors and performance impact factors are obtained. By organizing environmental impact factors and performance impact factors into a vector, the risk impact feature vector of the data center is obtained.

[0009] Furthermore, methods for correcting the impact of data center environmental status risk levels and data center performance status risk levels include: Based on the risk impact characteristic vector of the computer room, a comprehensive analysis of environmental impact factors and performance impact factors is conducted. Based on the analysis results of the risk impact feature vector of the data center, the degree of impact of each factor on the environmental and performance status is determined; Based on the analysis of influencing factors, the risk levels of the data center environment status and the data center performance status are adjusted. The revised risk levels of the data center environment and performance were verified.

[0010] Furthermore, the factors influencing the setting of the preset environmental safety threshold include temperature, humidity, smoke concentration, and electromagnetic interference intensity; the factors influencing the setting of the preset performance safety threshold include server temperature, CPU utilization, memory usage, and hard disk read / write speed.

[0011] Furthermore, the data center risk warning includes the warning level, risk category, specific risk items, risk impact analysis, and suggested countermeasures.

[0012] On the other hand, this application also provides an evaluation system for an unmanned aerial vehicle (UAV) data center monitoring system, the system comprising: The data acquisition module is used to collect data on the environmental status features and performance status features of the data center. The environmental status features include at least temperature, humidity, smoke concentration, and electromagnetic interference intensity, while the performance status features include at least server temperature, CPU utilization, memory usage, and hard disk read / write speed. The risk assessment module is used to input the data center environment status feature set into the data center environment status risk assessment model to obtain the data center environment status risk level; and to input the data center performance status feature set into the data center performance status risk assessment model to obtain the data center performance status risk level. The risk assessment module is used to determine whether the risk level of the data center environment is within the preset environmental safety threshold range, and obtain the first risk assessment result; and to determine whether the risk level of the data center performance is within the preset performance safety threshold range, and obtain the second risk assessment result. The task parameter acquisition module, in response to either the first risk assessment result or the second risk assessment result being unqualified, acquires the data center task execution parameters; the data center task execution parameters include at least the current task load, task completion rate, task latency rate, and task response time; The impact analysis module is used to perform environmental performance impact analysis on the data center task execution parameters to obtain the data center risk impact feature vector; the data center risk impact feature vector includes environmental impact factors and performance impact factors. The impact correction module is used to correct the impact of the data center environment status risk level and the data center performance status risk level based on the data center risk impact feature vector, and obtain the corrected data center environment status risk level and data center performance status risk level. The risk warning module is used to determine whether the risk level of the corrected data center environment status and the risk level of the data center performance status are within the preset environmental safety threshold range and the preset performance safety threshold range. If either judgment result is still unqualified, a data center risk warning will be generated and sent.

[0013] Thirdly, this application provides an electronic device including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any of the methods described above.

[0014] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: the method comprehensively considers the environmental and performance status of the computer room, as well as the impact of the tasks being performed on the environment and performance, and can comprehensively evaluate the security and stability of the computer room, avoiding the limitations of a single monitoring indicator. By establishing environmental status risk assessment models and performance status risk assessment models, the risk level of the data center can be intelligently assessed and dynamically adjusted based on real-time data, thereby improving the accuracy and timeliness of early warnings. The collected data center task execution parameters include current task load, task completion rate, task latency rate, and task response time. By analyzing these parameters, the risk situation of the data center can be more accurately assessed, providing targeted decision support for managers. The risk levels of environmental and performance states are corrected based on the risk impact feature vector of the data center, making the assessment results closer to the actual situation, improving the accuracy and reliability of the assessment, and helping to identify potential problems in a timely manner and take corresponding measures to optimize them. When the assessment results are unsatisfactory, a data center risk warning will be generated and sent, enabling managers to understand the data center's operating status in a timely manner, take corresponding countermeasures, and ensure the safe operation of the data center. In summary, this method has significant advantages in terms of comprehensiveness, intelligence, targeting, correction and optimization, and early warning functions. It can provide data center managers with accurate risk assessment and decision support, ensuring the security and stability of the data center. Attached Figure Description

[0016] Fig. 1 This is a flowchart of the present invention; Fig. 2 This is a flowchart illustrating the construction method of the data center environment status risk assessment model; Fig. 3 This is a structural diagram of an evaluation system for an unmanned aerial vehicle (UAV) room monitoring system. Detailed Implementation

[0017] As will be apparent to those skilled in the art from the description of this application, this application can be implemented as a method, apparatus, electronic device, and computer-readable storage medium. Therefore, this application can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software. Furthermore, in some embodiments, this application can also be implemented as a computer program product contained in one or more computer-readable storage media, which includes computer program code.

[0018] The aforementioned computer-readable storage medium may be any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, flash memory, optical fiber, optical disc read-only memory, optical storage devices, magnetic storage devices, or any combination thereof. In this application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0019] The acquisition, storage, use, and processing of data in this application all comply with relevant national laws and regulations.

[0020] This application describes the provided methods, apparatus, and electronic devices using flowcharts and / or block diagrams.

[0021] It should be understood that each block of a flowchart and / or block diagram, as well as combinations of blocks in a flowchart and / or block diagram, can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine that, when executed by a computer or other programmable data processing apparatus, creates means for implementing the functions / operations specified in the blocks of the flowchart and / or block diagram.

[0022] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to function in a particular manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction apparatus product that includes the functions / operations specified in the blocks of a flowchart and / or block diagram.

[0023] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus or other device to produce a computer-implemented process, such that the instructions that execute on the computer or other programmable data processing apparatus provide a process for implementing the functions / operations specified in the blocks of a flowchart and / or block diagram.

[0024] This application will now be described with reference to the accompanying drawings.

[0025] Example 1: As Figs. 1-2 As shown, the present invention provides an evaluation method for an unmanned aerial vehicle (UAV) room monitoring system, which specifically includes the following steps: S1. Collect the data center environmental status feature set and the data center performance status feature set; the data center environmental status feature set includes at least temperature, humidity, smoke concentration and electromagnetic interference intensity, and the data center performance status feature set includes at least server temperature, CPU utilization, memory usage and hard disk read / write speed. The collection of data center environment and performance status characteristics in step S1 requires the use of various sensors and monitoring equipment. It is crucial to ensure the accurate, reliable, and secure transmission and storage of the collected data to support subsequent risk assessment and decision support. The following is a detailed description of step S1: S11. Environmental Status Feature Set Collection A. Temperature monitoring: Precision temperature and humidity sensors, including platinum resistance thermometers, thermocouples, and infrared sensors, are deployed in key locations within the computer room to monitor and record the overall temperature of the computer room and the temperature data of local hot spots in real time. B. Humidity monitoring: Also using an integrated temperature and humidity sensor, the relative humidity in the computer room is measured and recorded synchronously. The sensor should be installed in a humidity-sensitive area and ensured to be dustproof and waterproof to ensure data accuracy.

[0026] C. Smoke concentration monitoring: Deploy smoke detectors to detect smoke particles and smoke components in the air to determine if there is a fire hazard; smoke detectors should cover every corner of the computer room, especially areas with concentrated electrical equipment and near flammable materials, to ensure early fire warning.

[0027] D. Electromagnetic interference intensity monitoring: Regularly monitor the electromagnetic interference level in the computer room using an electromagnetic field strength meter. If necessary, combine it with a spectrum analyzer to determine the frequency characteristics of the interference source so that targeted shielding, filtering and other measures can be taken. In addition, key signal transmission lines are regularly inspected to ensure that they meet anti-interference standards. S12. Data Center Performance Status Feature Set Collection a) Server temperature monitoring: Real-time temperature data of various internal components of the server is obtained through the server's built-in temperature sensors and external smart hardware; these sensors are usually integrated with the server management system and can be read remotely through standard interfaces. b. CPU utilization monitoring: Use performance monitoring tools provided by the operating system (such as Windows PerformanceMonitor, Linux top / htop commands, Unix sar commands, etc.) or dedicated server monitoring software (such as Nagios, Zabbix, PRTG, etc.) to periodically capture CPU utilization data. These tools can display and record the overall CPU utilization and the usage of each core in real time, which is convenient for analyzing whether the CPU resource allocation is reasonable and whether there is excessive load. c. Memory usage monitoring: Similarly, use operating system performance monitoring tools or dedicated monitoring software to monitor and record indicators such as total server memory usage, used memory, and free memory in real time, and calculate the memory usage rate; pay attention to details such as memory fragmentation and page swapping activity to determine whether memory resources are tight and whether there are problems such as memory leaks. d. Hard drive read / write speed monitoring: Use disk performance monitoring tools (such as iostat, diskperf, PerfMon) or server monitoring software to regularly collect hard drive read / write speeds, IOPS, queue depth, average service time, and other performance metrics. This data helps identify hard drive bottlenecks, predict storage system performance trends, and detect abnormal read / write behavior in a timely manner. In this step, the use of sophisticated sensors and monitoring equipment ensures accurate monitoring and recording of the data center's environmental status characteristics. Utilizing built-in server sensors and external smart hardware, real-time acquisition of server performance status characteristics ensures data reliability and timeliness. Deploying smoke detectors and electromagnetic interference monitoring equipment promptly detects fire hazards and electromagnetic interference within the data center, improving its security and reducing potential risks. Ensuring secure communication protocols and encryption technologies are used for data transmission and storage prevents data tampering or leakage, maintaining the confidentiality and integrity of data. Regular monitoring and recording of the data center's environmental and performance status characteristics allows for the identification of potential problems and timely preventative measures, reducing the risk of equipment failure and performance degradation, and improving the reliability and stability of data center equipment. The collected environmental and performance data provides crucial information for subsequent risk assessment and decision-making. Analysis and comprehensive evaluation of the data provide accurate risk warnings and decision support, helping data center managers make timely and correct decisions to ensure the safe and stable operation of the data center. In summary, the benefits of step S1 include improving data accuracy and reliability, enhancing data center security, enabling preventative maintenance, and providing data analysis and decision support, thus providing strong support for the stable operation of the data center and business continuity.

[0028] S2. Input the data center environment status feature set into the data center environment status risk assessment model to obtain the data center environment status risk level; input the data center performance status feature set into the data center performance status risk assessment model to obtain the data center performance status risk level. Step S2 uses a specially constructed data center environment status risk assessment model and a data center performance status risk assessment model to transform the real-time monitored environmental status feature set and performance status feature set into corresponding quantitative risk levels. These two models combine professional knowledge, industry standards and data-driven analysis methods in the field of data center operation and maintenance, and can objectively and accurately assess the environmental risks and equipment performance risks currently faced by the data center, providing a scientific basis for subsequent risk judgment, impact analysis and early warning decision-making. The method for constructing the data center environment status risk assessment model includes: S211. Collect the environmental status feature set in the computer room, and preprocess the collected environmental status feature set. The preprocessing includes data cleaning, noise reduction and outlier processing. S212. Extract and select features from the collected environmental parameters to construct a training feature set for the data center environmental status risk assessment model; S213. Select a machine learning model as the basis of the model, wherein the machine learning model includes decision tree, support vector machine and random forest; S214. Train the selected model using the training feature set, evaluate and validate the model, and adjust and optimize the model based on the evaluation results. S215. After completing the model construction and verification, deploy the model to the actual data center monitoring system to monitor the environmental status in real time and conduct risk assessment based on the risk level output by the model. The method for constructing the data center performance status risk assessment model includes: S221. Collect data on the performance status characteristics of the computer room, and perform numerical feature standardization and normalization on the collected data; S222. Extract and select features from the processed data center performance status characteristics to construct a training feature set for the data center performance status risk assessment model. S223. Choose a deep learning model as the basis of the model, such as linear regression model, logistic regression model, gradient boosting tree and neural network. S224. Train the selected model using the training feature set, evaluate and validate the model, and adjust and optimize the model based on the evaluation results. S225. Embed the trained performance status risk assessment model into the data center monitoring system to achieve real-time risk level assessment of the data center performance status feature set.

[0029] In this step, the data center environment status risk assessment model and the data center performance status risk assessment model transform the real-time monitored environmental status feature sets and performance status feature sets into corresponding quantitative risk levels. This allows for a more accurate assessment of the environmental and equipment performance risks currently facing the data center, providing a scientific basis for risk judgment, impact analysis, and early warning decisions. The two models combine professional knowledge, industry standards, and data-driven analysis methods in the field of data center operation and maintenance. The models consider industry best practices and standards while utilizing real-time monitoring data for analysis, making the assessment more objective and accurate. Data preprocessing, feature extraction, and feature selection were performed during the construction of the environmental and performance status models. The selection process ensured data quality and modeling effectiveness; reduced the model's sensitivity to noise and outliers, improving its stability and generalization ability; selected suitable machine learning and deep learning models as the foundation, and trained, evaluated, and validated the models; ensured good fitting and generalization capabilities, accurately capturing the complex relationship between environmental and performance states; after model construction and validation, the model was deployed to a real-time data center monitoring system, enabling real-time monitoring and risk assessment of environmental and performance states; and promptly identified potential risks and problems, taking corresponding preventative measures to ensure the safe and stable operation of the data center. In summary, the benefits of this step include improved accuracy and scientific rigor in assessing the data center environment and performance status, providing data center managers with more reliable risk warnings and decision support.

[0030] S3. Determine whether the risk level of the data center environment status is within the preset environmental safety threshold range to obtain the first risk assessment result; determine whether the risk level of the data center performance status is within the preset performance safety threshold range to obtain the second risk assessment result. Step S3 compares the risk level of the data center environment status and the risk level of the data center performance status with the preset security threshold range to make a compliance judgment on the data center environment and equipment performance status, ensuring the accuracy and objectivity of the risk assessment, and providing a clear basis for subsequent risk management and decision support. The factors influencing the setting of the preset environmental safety threshold include: Temperature is a critical environmental factor in the computer room. If the temperature is too high, it will cause the equipment to overheat and malfunction. If the temperature is too low, it will cause the performance of some electronic components to degrade. The ideal temperature range for a computer room is usually between 18°C ​​and 27°C, and the threshold should be set within this range. Humidity has a significant impact on the lifespan and performance of equipment in the computer room. Excessive humidity can lead to equipment corrosion and short circuits, while excessively low humidity can cause static electricity buildup and damage to electronic equipment. The ideal humidity range is between 40% and 60%, and the threshold should be set according to this range. Smoke concentration, and changes in smoke concentration, indicate potential fire hazards; when using smoke detectors for monitoring, the threshold should be set at a very low level so that fires can be detected in their early stages. Electromagnetic interference intensity affects signal transmission quality and equipment performance; the threshold should be set according to the specific equipment and signal transmission requirements of the computer room to ensure that the interference is within a controllable range. The factors influencing the setting of the preset performance safety threshold include: Server temperature settings should take into account the rated operating temperature range of the server hardware. CPU utilization should be set based on the server's processing capacity and workload; excessively high CPU utilization indicates that the server is overloaded, which can lead to decreased processing capacity or even system crash. Memory utilization should be set considering the server's memory capacity and the needs of running applications; excessively high memory utilization can lead to sluggish system response or even system crashes. Hard drive read / write speed should be set according to the specifications and performance of the server hard drive; abnormal hard drive read / write speed indicates hard drive failure or storage system performance problems, which can lead to decreased data read / write efficiency or data loss.

[0031] In this step, by comparing the data center's environmental and equipment performance status with preset safety thresholds, the compliance of these statuses can be accurately assessed. This helps ensure that the data center operates in a safe and stable environment, meeting relevant regulations and standards. Comparing the risk levels of the data center's environmental and equipment performance status with preset safety thresholds allows for a more accurate assessment of the data center's risk level. This helps in the timely detection of potential security risks and performance issues, enabling prompt action to address them and reduce the likelihood of incidents. It also provides a clear basis for subsequent risk management and decision-making. Data center managers can adjust their operational strategies based on the risk level assessments of the environment and performance status, taking necessary measures for risk management and prevention to ensure the safe operation of the data center. In summary, step S3 provides crucial decision support for data center management by accurately assessing the compliance of the data center environment and performance status, which helps ensure the stable operation of data center equipment and business continuity.

[0032] S4. In response to either the first risk assessment result or the second risk assessment result being unqualified, collect the data center task execution parameters; the data center task execution parameters include at least the current task load, task completion rate, task latency rate, and task response time; When the risk level of the data center environment or the risk level of the data center performance exceeds the preset safety threshold range, it indicates that there may be potential operational risks in the data center, and further investigation of the cause of the problem and corresponding measures are required. Step S4 is to collect data center task execution parameters in real time in order to more comprehensively understand the current actual operating status of the data center and the factors that may affect environmental and performance risks. Current workload is an important indicator for measuring the workload undertaken by IT equipment in the data center. It is quantified by statistically analyzing multi-dimensional data such as processor utilization, memory usage, disk I / O activity, and network traffic. High workload indicates that equipment resources are strained and that complex computing tasks are being performed. This can not only lead to performance bottlenecks but also exacerbate equipment overheating, thus becoming related to environmental conditions. Task completion rate is an indicator that reflects the efficiency of IT systems in the data center in executing tasks. It is calculated as the proportion of completed tasks to the total number of tasks. A decrease in task completion rate means that the system's processing capacity has decreased, resource contention is severe, or there are fault nodes. These situations are directly related to environmental risks and performance risks. Task latency rate refers to the percentage of time a task takes longer than expected from submission to completion. It reflects the timeliness of the IT system's response to requests within the data center. High task latency rates are caused by insufficient memory, slow hard drive read / write speeds, and network congestion. Task response time, which is the time required from when a user sends a request to when the system begins to process the request, is a key indicator for measuring the speed at which data center IT services respond to external requests. Excessive response time stems from performance issues such as limited CPU processing power, increased memory access latency, and low I / O operation efficiency. The methods for collecting the data center task execution parameters include: S41. Install monitoring software on servers and IT equipment to automatically collect CPU, memory, disk, and network performance data, and set alarm thresholds; S42. Connect to application logs and API interfaces to obtain information such as task load, task queue length, and number of concurrent tasks; S43. Install a task scheduling system and track task completion rates; S44. Set up database audit rules, record task status changes, and use the query function to calculate task completion rate; S45. Install application performance management tools to monitor operation time and assess task latency; S46. Install network monitoring tools to record request response times and calculate task response times; S47. Summarize the collected data to obtain the data center task execution parameters.

[0033] In this step, by collecting task execution parameters from the data center, a comprehensive understanding of the current operational status of the data center can be obtained, thus helping managers gain a deeper understanding of the internal operation of the data center. When the risk level of the data center environment status or the risk level of the data center performance status exceeds the preset safety threshold range, step S4 can help to promptly identify potential operational risks. By collecting task execution parameters in real time, factors that may lead to environmental and performance risks can be identified in a timely manner, providing an important basis for further troubleshooting and taking countermeasures. By analyzing task load, completion rate, latency rate, and response time parameters, managers can quickly locate problems and take corresponding adjustment and optimization measures. By monitoring task execution parameters in real time, data center managers can adjust resource allocation in a timely manner, optimize task scheduling, and improve data center operation and maintenance efficiency. This helps to reduce data center operational risks and ensure the continuous and stable operation of the data center. In conclusion, implementing the S4 steps can effectively improve data center managers' understanding of data center operations, promptly identify potential risks, and provide effective countermeasures, thereby ensuring the safe and stable operation of the data center. S5. Perform environmental performance impact analysis on the data center task execution parameters to obtain the data center risk impact feature vector; the data center risk impact feature vector includes environmental impact factors and performance impact factors; Step S5, through in-depth analysis of data center task execution parameters, reveals the intrinsic relationship between task execution and environmental conditions and equipment performance, quantifying the direct contribution of tasks to the overall risk status of the data center. These results are presented in the form of a data center risk impact feature vector, providing a scientific basis for subsequent risk level correction, helping to more accurately assess the overall risk situation of the data center, and improving the effectiveness of risk warning and decision support. The method for obtaining the feature vector of the risk impact on the computer room includes: S51. Preprocess the data center task execution parameters, including missing value filling, outlier detection and processing, and data standardization. S52. Analyze the correlation between data center task execution parameters and environmental status characteristics; identify the changing trends of environmental parameters under specific task load levels; S53. Analyze the relationship between data center task execution parameters and data center performance characteristics; explore the causal relationship between task load, task completion rate, task latency, task response time and various performance indicators. S54. Based on the results of correlation analysis, quantify the specific impact of task execution on environmental conditions and equipment performance; S55. Organize the environmental impact factors and performance impact factors into a vector to obtain the risk impact feature vector of the computer room.

[0034] This step, through in-depth analysis of data center task execution parameters, reveals the intrinsic relationship between task execution and environmental conditions and equipment performance. This helps to understand the direct impact of task execution on data center operations, providing a more comprehensive perspective for subsequent risk assessment. By correlating task execution parameters with environmental conditions and equipment performance factors, the direct contribution of tasks to the overall risk status of the data center can be quantified. This helps to identify key factors and provides targeted suggestions for risk correction and decision-making. By obtaining the data center risk impact feature vector, the risk level can be corrected to more accurately reflect the actual situation of the data center. This improves the scientific rigor and reliability of risk assessment, helping data center managers to better formulate response strategies. Through comprehensive analysis of data center task execution parameters, the overall risk situation of the data center can be more accurately assessed, providing data-driven risk warnings and decision support. This helps to promptly identify potential risks and take corresponding measures, thereby improving the security and stability of the data center. In summary, the beneficial effect of the S5 step lies in revealing the relationship between the task and the environmental state and equipment performance through in-depth analysis of task execution parameters, providing a scientific basis for assessing data center risks, thereby improving the effectiveness of risk warning and decision support.

[0035] S6. Based on the risk impact feature vector of the data center, the risk level of the data center environment status and the risk level of the data center performance status are corrected to obtain the corrected risk level of the data center environment status and the risk level of the data center performance status. Step S6 dynamically adjusts the environmental status risk level and performance status risk level by using the data center risk impact feature vector and combining it with the risk level correction model. This process fully considers the impact of task execution on the data center risk status, making the risk assessment closer to the actual situation, thereby improving the accuracy and pertinence of risk warning and decision support. Methods for correcting the impact of data center environmental status risk level and data center performance status risk level include: S61. Based on the risk impact characteristic vector of the computer room, conduct a comprehensive analysis of environmental impact factors and performance impact factors; S62. Based on the analysis results of the risk impact characteristic vector of the computer room, determine the degree of impact of each factor on the environmental state and performance state; S63. Based on the analysis of influencing factors, adjust the risk level of the data center environment status and the risk level of the data center performance status; S64. Verify the corrected risk level of the data center environment status and the risk level of the data center performance status to ensure that the correction results are within the preset environmental safety threshold range and the preset performance safety threshold range.

[0036] In this step, by utilizing the data center risk impact feature vector and combining it with a risk level correction model, the risk levels of the data center environment and performance can be dynamically adjusted. This makes the risk assessment more closely reflect reality and can promptly reflect the current risk status of the data center. Through the analysis of task execution parameters, the corrected risk level can more accurately reflect the impact of task execution on the environmental and performance states, improving the accuracy and reliability of the risk assessment. The corrected risk level is more in line with reality and can more accurately warn of potential risks. This helps data center managers take timely measures to address possible risks, reduce the likelihood of accidents, and ensure the safe operation of the data center. The corrected risk level can provide more targeted guidance for decision-making. Based on more accurate risk assessment results, managers can develop targeted response strategies and measures to ensure the stable operation of the data center and data security. In summary, the S6-step approach can effectively improve the accuracy and relevance of risk assessment in data center monitoring systems, providing data center managers with more reliable risk warnings and decision support, thereby ensuring the safe operation and business continuity of the data center.

[0037] S7. Determine whether the corrected risk level of the data center environment status and the risk level of the data center performance status are within the preset environmental safety threshold range and the preset performance safety threshold range, respectively. If either judgment result is still unqualified, generate a data center risk warning and send it. In the S7 phase, threshold judgments are made on the revised risk levels to generate targeted data center risk warnings, which are then sent to relevant personnel through diverse communication channels. This ensures that risk information can be conveyed to decision-makers in a timely and accurate manner, helping them to make quick and effective response decisions and ensuring the safe and stable operation of unattended data centers. The revised risk level of the data center environment is compared with the preset environmental security threshold. If the risk level of the environment exceeds the preset security threshold, the environment is considered to be at risk. The revised risk level of the data center performance status is compared with the preset performance security threshold. If the risk level of the performance status exceeds the preset security threshold range, the performance status is considered to be at risk. For each unqualified risk level, a corresponding data center risk warning is automatically generated. These risk warnings include: Alert levels are determined based on the severity of the risk, so that managers can quickly identify the urgency of the problem; The risk category clearly indicates whether the warning involves environmental risk, performance risk, or both, helping managers quickly pinpoint the source of the problem; Specific risk items describe the specific environmental or performance characteristics that exceed the standard, and provide detailed risk details; Risk impact analysis estimates the potential consequences of risks, such as the probability of equipment failure, the possibility of business interruption, and data security threats, which helps managers assess the impact of risks on business. Suggested countermeasures and preliminary emergency response recommendations, such as adjusting air conditioning settings, optimizing task allocation, and activating backup systems, provide action guidelines for managers to respond quickly.

[0038] In this step, by real-time monitoring and assessment of the risks to the data center's environment and performance, and by making judgments based on preset security thresholds, targeted data center risk warnings can be generated in a timely manner. This helps managers understand the data center's security status promptly, make quick and effective decisions to address potential risks and problems, and ensure the safe and stable operation of the data center. The generated data center risk warnings can be sent to relevant personnel through diverse communication channels, ensuring that risk information is conveyed to decision-makers in a timely and accurate manner. By determining the warning level, managers can quickly identify the urgency and importance of the problem. Different warning levels help them prioritize the most serious issues, ensuring that important risks receive timely attention and resolution. The warnings clearly indicate the risk category and specific risk items, helping managers quickly locate the source of the problem. This enables them to take more effective targeted measures to solve the problem and prevent its recurrence. The detailed risk details and impact analysis provided in the warnings help managers fully understand the possible consequences of the risks, better assess the impact of the risks on business, and take corresponding measures to deal with them. The response suggestions provided in the warnings offer managers a preliminary emergency response guide, enabling them to take swift action to address risks and ensure the safe and stable operation of the data center.

[0039] Example 2: Fig. 3 As shown, the evaluation system for unmanned aerial vehicle (UAV) room monitoring system of the present invention specifically includes the following modules; The data acquisition module is used to collect data on the environmental status features and performance status features of the data center. The environmental status features include at least temperature, humidity, smoke concentration, and electromagnetic interference intensity, while the performance status features include at least server temperature, CPU utilization, memory usage, and hard disk read / write speed. The risk assessment module is used to input the data center environment status feature set into the data center environment status risk assessment model to obtain the data center environment status risk level; and to input the data center performance status feature set into the data center performance status risk assessment model to obtain the data center performance status risk level. The risk assessment module is used to determine whether the risk level of the data center environment is within the preset environmental safety threshold range, and obtain the first risk assessment result; and to determine whether the risk level of the data center performance is within the preset performance safety threshold range, and obtain the second risk assessment result. The task parameter acquisition module, in response to either the first risk assessment result or the second risk assessment result being unqualified, acquires the data center task execution parameters; the data center task execution parameters include at least the current task load, task completion rate, task latency rate, and task response time; The impact analysis module is used to perform environmental performance impact analysis on the data center task execution parameters to obtain the data center risk impact feature vector; the data center risk impact feature vector includes environmental impact factors and performance impact factors. The impact correction module is used to correct the impact of the data center environment status risk level and the data center performance status risk level based on the data center risk impact feature vector, and obtain the corrected data center environment status risk level and data center performance status risk level. The risk warning module is used to determine whether the risk level of the corrected data center environment status and the risk level of the data center performance status are within the preset environmental safety threshold range and the preset performance safety threshold range. If either judgment result is still unqualified, a data center risk warning will be generated and sent.

[0040] By simultaneously collecting and evaluating the environmental and performance characteristics of the data center, the system can gain a comprehensive understanding of the overall operation of the data center; by comprehensively evaluating the data center environment and equipment performance, the system can better identify and prevent potential risks, thereby improving the security and stability of the data center. By conducting in-depth analysis and comprehensive evaluation of the interaction between environmental and performance states, potential risk factors can be identified more accurately, helping managers to make targeted optimizations and improvements. The unique advantage of this system is that it considers the impact of tasks being executed in the computer room on the environment and performance. By monitoring and analyzing task execution parameters, it can more accurately assess risks, promptly identify the impact of tasks on system operation, and provide targeted decision support for managers. The system can correct the risk level of environmental and performance status based on the analysis results of task execution parameters and provide corrected assessment results; at the same time, the system can generate risk warnings in a timely manner to help managers take quick countermeasures and ensure the safe operation of the data center. By setting preset environmental safety thresholds and performance safety thresholds, the system can make judgments based on actual assessment results, thereby providing real-time risk warnings. This real-time monitoring and warning mechanism helps managers respond quickly to potential risks and reduce the likelihood of accidents. In summary, this unmanned data center monitoring and evaluation system provides an effective solution through comprehensive data collection, integrated assessment, task impact analysis, and risk early warning mechanisms. It helps data center managers ensure business continuity and data security, and improve data center operation and maintenance efficiency and management level.

[0041] The various variations and specific embodiments of the unmanned room monitoring system evaluation method in the aforementioned Embodiment 1 are also applicable to the unmanned room monitoring system evaluation system in this embodiment. Through the foregoing detailed description of the unmanned room monitoring system evaluation method, those skilled in the art can clearly understand the implementation method of the unmanned room monitoring system evaluation system in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0042] In addition, this application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected via the bus. When the computer program is executed by the processor, it implements the various processes of the above-described method embodiment for controlling output data and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0043] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for evaluating an unmanned aerial vehicle (UAV) room monitoring system, characterized in that, The method includes: Collect data from the data center's environmental status feature set and performance status feature set; the data center's environmental status feature set includes at least temperature, humidity, smoke concentration, and electromagnetic interference intensity, and the data center's performance status feature set includes at least server temperature, CPU utilization, memory usage, and hard disk read / write speed; Input the data center environment status feature set into the data center environment status risk assessment model to obtain the data center environment status risk level; input the data center performance status feature set into the data center performance status risk assessment model to obtain the data center performance status risk level. Determine whether the risk level of the data center environment status is within the preset environmental safety threshold range to obtain the first risk assessment result; determine whether the risk level of the data center performance status is within the preset performance safety threshold range to obtain the second risk assessment result. If either the first risk assessment result or the second risk assessment result is unqualified, the data center task execution parameters are collected; the data center task execution parameters include at least the current task load, task completion rate, task latency rate, and task response time; An environmental performance impact analysis is performed on the task execution parameters in the data center to obtain a risk impact feature vector for the data center; the risk impact feature vector for the data center includes environmental impact factors and performance impact factors. Based on the risk impact feature vector of the data center, the risk level of the data center environment status and the risk level of the data center performance status are corrected to obtain the corrected risk level of the data center environment status and the risk level of the data center performance status. The system determines whether the corrected risk level of the data center environment status and the risk level of the data center performance status are within the preset environmental safety threshold and the preset performance safety threshold, respectively. If either determination result is still unqualified, a data center risk warning is generated and sent.

2. The evaluation method for an unmanned aerial vehicle (UAV) room monitoring system as described in claim 1, characterized in that, The method for constructing the data center environment status risk assessment model includes: The environmental status feature set in the computer room is collected, and the collected environmental status feature set is preprocessed, including data cleaning, noise reduction and outlier processing. Feature extraction and feature selection are performed on the collected environmental parameters to construct a training feature set for the data center environmental status risk assessment model; Machine learning models are selected as the basis for the model, including decision trees, support vector machines, and random forests. The selected model is trained using the training feature set, and the model is evaluated and validated. The model is then adjusted and optimized based on the evaluation results. After completing the model building and verification, the model will be deployed to the actual data center monitoring system.

3. The evaluation method for an unmanned aerial vehicle (UAV) room monitoring system as described in claim 1, characterized in that, The methods for collecting the data center task execution parameters include: Install monitoring software on servers and IT equipment, and set alarm thresholds; Connect to application logs and API interfaces to obtain information such as task load, task queue length, and number of concurrent tasks; Install a task scheduling system and track task completion rates; Set up database audit rules to record task status changes and calculate task completion rate; Install application performance management tools to monitor operation time and assess task latency; Install network monitoring tools to record request response times and calculate task response times; The collected data is summarized to obtain the data center task execution parameters.

4. The evaluation method for an unmanned aerial vehicle (UAV) room monitoring system as described in claim 1, characterized in that, The method for obtaining the feature vector of the risk impact on the computer room includes: Preprocessing of data center task execution parameters includes missing value filling, outlier detection and handling, and data standardization; Analyze the correlation between task execution parameters and environmental characteristics in the computer room; Analyze the relationship between data center task execution parameters and data center performance status characteristics; Based on the results of correlation analysis, the impact of task execution on environmental conditions and equipment performance is quantified, and environmental impact factors and performance impact factors are obtained. By organizing environmental impact factors and performance impact factors into a vector, the risk impact feature vector of the data center is obtained.

5. The evaluation method for an unmanned aerial vehicle (UAV) room monitoring system as described in claim 1, characterized in that, Methods for correcting the impact of data center environmental status risk level and data center performance status risk level include: Based on the risk impact characteristic vector of the computer room, a comprehensive analysis of environmental impact factors and performance impact factors is conducted. Based on the analysis results of the risk impact feature vector of the data center, the degree of impact of each factor on the environmental and performance status is determined; Based on the analysis of influencing factors, the risk levels of the data center environment status and the data center performance status are adjusted. The revised risk levels of the data center environment and performance were verified.

6. The evaluation method for an unmanned aerial vehicle (UAV) room monitoring system as described in claim 1, characterized in that, The factors influencing the setting of the preset environmental safety threshold include temperature, humidity, smoke concentration, and electromagnetic interference intensity; the factors influencing the setting of the preset performance safety threshold include server temperature, CPU utilization, memory usage, and hard disk read / write speed.

7. The evaluation method for an unmanned aerial vehicle (UAV) room monitoring system as described in claim 1, characterized in that, The data center risk warning includes the warning level, risk category, specific risk items, risk impact analysis, and suggested countermeasures.

8. An evaluation system for an unmanned aerial vehicle (UAV) room monitoring system, characterized in that, The system includes: The data acquisition module is used to collect data on the environmental status features and performance status features of the data center. The environmental status features include at least temperature, humidity, smoke concentration, and electromagnetic interference intensity, while the performance status features include at least server temperature, CPU utilization, memory usage, and hard disk read / write speed. The risk assessment module is used to input the data center environment status feature set into the data center environment status risk assessment model to obtain the data center environment status risk level; and to input the data center performance status feature set into the data center performance status risk assessment model to obtain the data center performance status risk level. The risk assessment module is used to determine whether the risk level of the data center environment is within the preset environmental safety threshold range, and obtain the first risk assessment result; and to determine whether the risk level of the data center performance is within the preset performance safety threshold range, and obtain the second risk assessment result. The task parameter acquisition module, in response to either the first risk assessment result or the second risk assessment result being unqualified, acquires the data center task execution parameters; the data center task execution parameters include at least the current task load, task completion rate, task latency rate, and task response time; The impact analysis module is used to perform environmental performance impact analysis on the data center task execution parameters to obtain the data center risk impact feature vector; the data center risk impact feature vector includes environmental impact factors and performance impact factors. The impact correction module is used to correct the impact of the data center environment status risk level and the data center performance status risk level based on the data center risk impact feature vector, and obtain the corrected data center environment status risk level and data center performance status risk level. The risk warning module is used to determine whether the risk level of the corrected data center environment status and the risk level of the data center performance status are within the preset environmental safety threshold range and the preset performance safety threshold range. If either judgment result is still unqualified, a data center risk warning will be generated and sent.

9. An electronic device for evaluating an unmanned aerial vehicle (UAV) room monitoring system, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, characterized in that, When the computer program is executed by the processor, it implements the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1-7.

Images