Data center infrastructure operation and maintenance management system and method

Abstract

The invention discloses a data center infrastructure operation and maintenance management system and method, and relates to the technical field of data center management. Comprising a data collection module which is responsible for collecting basic information and operation state data of various facilities in a data center; the feature analysis and label generation module is used for performing feature analysis on each facility based on the collected data and generating a corresponding feature label; each facility corresponds to a plurality of feature tags, including equipment types, performance indexes and fault histories; and the maintenance personnel capability evaluation module is used for establishing a capability model of the maintenance personnel and setting various capability scores for each maintenance personnel according to skill levels and working experience factors of the maintenance personnel. According to the invention, data is collected and analyzed in real time, and managers are helped to know system conditions in time and make better management decisions; according to the condition of the maintenance personnel and the matching degree with the equipment condition, the appropriate maintenance personnel are selected to execute the maintenance operation, so that targeted processing is realized, and the maintenance efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data center management, and in particular to a data center infrastructure operation and maintenance management system and method. Background Art

[0002] With the development of cloud computing and big data technology, the scale and complexity of data centers are increasing, and traditional operation and maintenance methods can no longer meet the needs of modern data centers. Faced with huge data processing needs and complex IT environments, data centers are facing unprecedented operation and maintenance challenges. The stable operation of facilities is crucial to ensuring business continuity, improving service quality, and reducing operational risks. Therefore, how to improve the efficiency and quality of data center operation and maintenance has become an urgent problem to be solved.

[0003] After searching, the application scheme with Chinese patent application number CN202410842361.4 discloses a method and system for IT equipment operation and maintenance management. First, the target operation and maintenance path data including the first IT equipment operation and maintenance event and the second IT equipment operation and maintenance event is obtained, and these IT equipment operation and maintenance events and the collaborative links between them are analyzed through feature connections. Subsequently, feature extraction technology is used to generate feature vectors that reflect the logical process and collaborative parameters of the operation and maintenance events. Based on these feature vectors, the method can accurately determine the collaborative operation vectors between events, and then generate an easy-to-understand operation and maintenance knowledge summary. The operation and maintenance management method in the above patent has the following shortcomings: when human participation is required, relevant personnel cannot be intelligently allocated for targeted processing according to personnel conditions and equipment conditions. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a data center infrastructure operation and maintenance management system and method.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: A data center infrastructure operation and maintenance management system, comprising: Data collection module: responsible for collecting basic information and operating status data of various facilities in the data center; Feature analysis and label generation module: Based on the collected data, feature analysis is performed on each facility and corresponding feature labels are generated; each facility corresponds to multiple feature labels, including equipment type, performance indicators, and fault history; Maintenance personnel competency assessment module: establish a competency model for maintenance personnel and set competency scores for each maintenance personnel based on their skill level and work experience; Matching analysis and task allocation module: Analyzes the matching degree between the propensity score of the feature label and the ability score of the maintenance personnel. When a maintenance task is generated, the task is automatically allocated to the most suitable maintenance personnel based on the matching degree. Monitoring and feedback module: monitors the maintenance process in real time and collects feedback information after the task is completed to optimize the subsequent task allocation strategy; Alarm and emergency response module: set up an early warning mechanism to immediately trigger an alarm when an abnormal situation is detected and initiate the corresponding emergency plan; Report and statistics module: Generate operation and maintenance reports regularly and conduct statistical analysis on system operation status; Knowledge base management module: used to store problem solutions and best practice content.

[0006] Preferably: the data collection module includes: Hardware monitoring unit: real-time monitoring of temperature, humidity, and voltage parameters of physical components of servers and storage devices; Software Performance Tracking Unit: Tracks resource utilization at the operating system level and application response time; Network Traffic Analysis Unit: records the number and size distribution of network packets entering and leaving the data center, and identifies abnormal patterns or potential security threats.

[0007] Preferably: the feature analysis and label generation module includes: Automatic classification engine: uses machine learning algorithms to classify input data into corresponding categories according to preset rules; Trend prediction model: Combine historical records to provide early warning of possible problems in the future; Association rule mining tool: discovers implicit connections between different events and helps understand the behavior patterns of complex systems.

[0008] Preferably, the matching analysis and task allocation module uses ant colony optimization to find the optimal solution; specifically, as follows: Initialization: randomly place m candidates on n tasks, each with an initial position and path list; Path construction: Each candidate selects the next task as the destination according to a certain probability; Pheromone update: After all candidates complete a cycle, the pheromone concentration on the path is updated; Local search: In order to avoid falling into the local optimum, the path is adjusted in combination with the local search algorithm; Iterative optimization: Repeat the above steps until the termination condition is met.

[0009] Preferably: in the path construction, the probability is inversely proportional to the distance between tasks; the probability formula is: in, is the pheromone concentration of candidate i to task j, is the heuristic factor from candidate i to task j, and are parameters that control the importance of pheromone and heuristic factors.

[0010] Preferably, the global update rule for pheromone update is: in, is the pheromone volatility coefficient, is the amount of pheromone that the kth candidate leaves on path ij in this cycle.

[0011] Preferably: the alarm and emergency response module includes: Multi-level alarm unit: different levels of warning signals according to severity; Automated Disposal Unit: Standard operating procedures are pre-set to deal with emergencies.

[0012] Preferably: the report and statistics module includes: Custom report generator: allows users to select data items and combine them into the desired format for output; Trend chart drawing tool: displays the changing trend within a set time span; KPI Calculator: Use to set reasonable goals and track progress.

[0013] A data center infrastructure operation and maintenance management method is implemented based on the above data center infrastructure operation and maintenance management system, comprising the following steps: S1: Data collection, which continuously collects information about hardware status, network traffic, and environmental conditions through sensors and other monitoring devices installed throughout the data center; S2: Feature extraction and label generation, using big data analysis technology and machine learning algorithms to extract information from raw data and convert the extracted information into feature labels; S3: Personnel competency assessment, which determines the expertise level of maintenance personnel in different areas and gives corresponding scores to indicate their overall competency; S4: Intelligent matching and task assignment: the system selects the most suitable maintenance personnel to perform the task; S5: Execution and tracking: the selected maintenance personnel will be notified to go to the site for inspection and repair work.

[0014] Preferably, the intelligent matching and task assignment is specifically performed in the following manner: when a new maintenance demand arises, the system first determines all relevant characteristics involved in the event, and then calculates the scores of each maintenance personnel's ability to solve these problems; then the list of maintenance personnel is arranged in order of scores, and finally the most suitable maintenance personnel is selected to perform the task.

[0015] The beneficial effects of the present invention are: 1. The present invention uses automated decision support technology to achieve intelligent allocation of maintenance tasks, reduce human intervention, and improve operation and maintenance efficiency; it can flexibly adjust maintenance plans according to actual needs to adapt to different business scenarios.

[0016] 2. The present invention collects and analyzes data in real time, helping managers to understand the system status in a timely manner and make better management decisions; according to the individual conditions of the maintenance personnel and the degree of matching with the equipment conditions, suitable maintenance personnel are selected to perform maintenance tasks, achieving targeted processing and improving maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The present invention is a flowchart of a data center infrastructure operation and maintenance management method. DETAILED DESCRIPTION

[0018] The technical solution of the present invention is further described in detail below in conjunction with specific implementation methods.

[0019] Embodiment 1: A data center infrastructure operation and maintenance management system, comprising: Data collection module: responsible for collecting basic information and operating status data of various facilities in the data center; Feature analysis and label generation module: Based on the collected data, feature analysis is performed on each facility and corresponding feature labels are generated; each facility corresponds to multiple feature labels, including but not limited to equipment type, performance indicators, fault history, etc.; Maintenance personnel competency assessment module: Establish a competency model for maintenance personnel and set competency scores for each maintenance personnel based on their skill level, work experience and other factors; Matching analysis and task allocation module: The system analyzes the matching degree between the propensity score of the feature label and the ability score of the maintenance personnel. When a maintenance task is generated, the task is automatically allocated to the most suitable maintenance personnel based on the matching degree. Monitoring and feedback module: monitors the maintenance process in real time and collects feedback information after the task is completed to optimize the subsequent task allocation strategy; Alarm and emergency response module: set up an early warning mechanism to immediately trigger an alarm when an abnormal situation is detected and initiate the corresponding emergency plan; Report and statistics module: Generate operation and maintenance reports regularly, conduct statistical analysis on system operation status, and provide support for management decision-making; Knowledge base management module: used to store problem solutions and best practice content.

[0020] Wherein, the data collection module includes: Hardware monitoring unit: real-time monitoring of temperature, humidity, voltage and other parameters of physical components such as servers and storage devices; Software Performance Tracking Unit: Tracks key indicators such as resource utilization at the operating system level (such as CPU usage, memory usage) and application response time; Network Traffic Analysis Unit: records information such as the number and size distribution of network packets entering and leaving the data center, and identifies abnormal patterns or potential security threats.

[0021] Wherein, the feature analysis and label generation module includes: Automatic classification engine: uses machine learning algorithms to classify input data into corresponding categories according to preset rules; Trend prediction model: Combine historical records to provide early warning of possible problems in the future; Association rule mining tool: discovers implicit connections between different events and helps understand the behavior patterns of complex systems.

[0022] The matching analysis and task allocation module uses ant colony optimization to find the optimal solution; specifically, as follows: Initialization: randomly place m candidates on n tasks, each with an initial position and path list; Path construction: Each candidate selects the next task as the destination with a certain probability, which is inversely proportional to the distance between tasks; the probability formula is: in, is the pheromone concentration of candidate i to task j, is the heuristic factor from candidate i to task j (usually the inverse of the distance), and are parameters that control the importance of pheromone and heuristic factors.

[0023] Pheromone update: After all candidates complete a cycle, the pheromone concentration on the path is updated; the global update rule is: in, is the pheromone volatility coefficient, is the amount of pheromone that the kth candidate leaves on path ij in this cycle.

[0024] Local search: In order to avoid falling into the local optimum, the path is adjusted by combining local search algorithms (such as 2-opt or 3-opt); Iterative optimization: Repeat the above steps until the termination condition is met (such as reaching the maximum number of iterations or the quality of the solution no longer improves).

[0025] Wherein, the alarm and emergency response module includes: Multi-level alarm unit: different levels of warning signals according to severity; Automated Disposal Unit: Standard operating procedures are pre-set to deal with emergencies.

[0026] Wherein, the report and statistics module includes: Custom report generator: allows users to select data items and combine them into the desired format for output; Trend chart drawing tool: displays the changing trend within a set time span; KPI Calculator: Use to set reasonable goals and track progress.

[0027] Embodiment 2: A data center infrastructure operation and maintenance management method, comprising the following steps: S1: Data collection, which continuously collects information about key parameters such as hardware status, network traffic, and environmental conditions through sensors and other monitoring devices installed throughout the data center; S2: Feature extraction and label generation: Use big data analysis technology and machine learning algorithms to extract valuable information from raw data, such as device health score and potential risk point identification, and convert this information into feature labels; for example, "CPU temperature is too high" and "memory utilization is close to saturation" exist as separate feature labels; S3: Personnel capability assessment: Based on each maintenance personnel's professional background, training experience, and past work performance records, the maintenance personnel's expertise in different fields is determined, and corresponding scores are given accordingly to indicate their overall capability. For example, for a technician who is good at solving network problems but not very familiar with storage systems, he will get a higher score in "network troubleshooting" and a relatively lower score in "storage optimization"; S4: Intelligent matching and task assignment. When a new maintenance demand arises (such as a server suddenly crashes), the system will first determine all the relevant characteristics involved in the event (such as "operating system crash", "hard disk damage", etc.), and then calculate the scores of each maintenance personnel's ability to solve these problems; then the list of maintenance personnel is sorted in order of scores, and finally the most suitable maintenance personnel is selected to perform the task; S5: Execution and tracking: the selected maintenance personnel will be notified to go to the site for inspection and repair work.

[0028] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A data center infrastructure operation and maintenance management system, characterized in that: include: Data collection module: responsible for collecting basic information and operating status data of various facilities in the data center; Feature analysis and label generation module: Based on the collected data, feature analysis is performed on each facility and corresponding feature labels are generated; each facility corresponds to multiple feature labels, including equipment type, performance indicators, and fault history; Maintenance personnel competency assessment module: establish a competency model for maintenance personnel and set competency scores for each maintenance personnel based on their skill level and work experience; Matching analysis and task allocation module: Analyzes the matching degree between the propensity score of the feature label and the ability score of the maintenance personnel. When a maintenance task is generated, the task is automatically allocated to the most suitable maintenance personnel based on the matching degree. Monitoring and feedback module: monitors the maintenance process in real time and collects feedback information after the task is completed to optimize the subsequent task allocation strategy; Alarm and emergency response module: set up an early warning mechanism to immediately trigger an alarm when an abnormal situation is detected and initiate the corresponding emergency plan; Report and statistics module: Generate operation and maintenance reports regularly and conduct statistical analysis on system operation status; Knowledge base management module: used to store problem solutions and best practice content.

2. A data center infrastructure operation and maintenance management system according to claim 1, characterized in that: The data collection module includes: Hardware monitoring unit: real-time monitoring of temperature, humidity, and voltage parameters of physical components of servers and storage devices; Software Performance Tracking Unit: Tracks resource utilization at the operating system level and application response time; Network Traffic Analysis Unit: records the number and size distribution of network packets entering and leaving the data center, and identifies abnormal patterns or potential security threats.

3. A data center infrastructure operation and maintenance management system according to claim 1, characterized in that: The feature analysis and label generation module includes: Automatic classification engine: uses machine learning algorithms to classify input data into corresponding categories according to preset rules; Trend prediction model: Combine historical records to provide early warning of possible problems in the future; Association rule mining tool: discovers implicit connections between different events and helps understand the behavior patterns of complex systems.

4. A data center infrastructure operation and maintenance management system according to claim 1, characterized in that: The matching analysis and task allocation module: uses ant colony optimization to find the optimal solution; the details are as follows: Initialization: randomly place m candidates on n tasks, each with an initial position and path list; Path construction: Each candidate selects the next task as the destination according to a certain probability; Pheromone update: After all candidates complete a cycle, the pheromone concentration on the path is updated; Local search: In order to avoid falling into the local optimum, the path is adjusted in combination with the local search algorithm; Iterative optimization: Repeat the above steps until the termination condition is met.

5. A data center infrastructure operation and maintenance management system according to claim 4, characterized in that: In the path construction, the probability is inversely proportional to the distance between tasks; the probability formula is: in, is the pheromone concentration of candidate i to task j, is the heuristic factor from candidate i to task j, and are parameters that control the importance of pheromone and heuristic factors.

6. A data center infrastructure operation and maintenance management system according to claim 5, characterized in that: The global update rule for the pheromone update is: in, is the pheromone volatility coefficient, is the amount of pheromone that the kth candidate leaves on path ij in this cycle.

7. A data center infrastructure operation and maintenance management system according to claim 6, characterized in that: The alarm and emergency response module includes: Multi-level alarm unit: different levels of warning signals according to severity; Automated Disposal Unit: Standard operating procedures are pre-set to deal with emergencies.

8. A data center infrastructure operation and maintenance management system according to claim 7, characterized in that: The reporting and statistics module includes: Custom report generator: allows users to select data items and combine them into the desired format for output; Trend chart drawing tool: displays the changing trend within a set time span; KPI Calculator: Use to set reasonable goals and track progress.

9. A data center infrastructure operation and maintenance management method, characterized in that: The data center infrastructure operation and maintenance management system according to any one of claims 1 to 8 is implemented, comprising the following steps: S1: Data collection, which continuously collects information about hardware status, network traffic, and environmental conditions through sensors and other monitoring devices installed throughout the data center; S2: Feature extraction and label generation, using big data analysis technology and machine learning algorithms to extract information from raw data and convert the extracted information into feature labels; S3: Personnel competency assessment, which determines the expertise level of maintenance personnel in different areas and gives corresponding scores to indicate their overall competency; S4: Intelligent matching and task assignment: the system selects the most suitable maintenance personnel to perform the task; S5: Execution and tracking: the selected maintenance personnel will be notified to go to the site for inspection and repair work.

10. A data center infrastructure operation and maintenance management method according to claim 9, characterized in that: The specific method of intelligent matching and task assignment is as follows: when a new maintenance demand arises, the system first determines all relevant characteristics involved in the event, and then calculates the problem-solving ability scores of each maintenance personnel for these problems; then the list of maintenance personnel is arranged in order of scores, and finally the most suitable maintenance personnel is selected to perform the task.

Images