Data center interconnection control system based on artificial intelligence

Abstract

The invention discloses a data center interconnection control system based on artificial intelligence, and particularly relates to the technical field of data centers. Comprising a data center interconnection data acquisition module, a data center interconnection data analysis module, a data center interconnection intelligent control module, a data center interconnection control comprehensive analysis module and a data center interconnection control man-machine interaction module. The data center interconnection data acquisition module is used for acquiring data in a data center interconnection process, obtaining various monitoring parameters for analyzing data center interconnection control indexes, and transmitting the various monitoring parameters to the data center interconnection data analysis module; through the artificial intelligence technology, network flow control parameters are accurately analyzed, the data transmission path and rate between data centers can be optimized, and network congestion is effectively avoided; meanwhile, through intelligent scheduling of resource allocation control parameters, it is ensured that resources among the data centers are efficiently utilized, and resource waste is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of data centers, and in particular to an artificial intelligence-based data center interconnection control system. Background Art

[0002] In today's digital age, data centers have become key infrastructure supporting various information technology services. With the rapid development of information technology, the scale and complexity of data centers are increasing. The rapid development of artificial intelligence technology, especially in the fields of deep learning and machine learning, has made major breakthroughs, providing strong support for the intelligentization of data center interconnection control systems.

[0003] Traditional data center interconnection methods usually rely on fixed network architectures and predefined policies, which are difficult to cope with increasingly dynamic and diverse business needs. With the continuous increase in data traffic and the increasing complexity of business types, this traditional method has exposed many limitations. On the one hand, traditional interconnection control cannot perceive and adapt to traffic changes within and between data centers in real time, which may cause network congestion and increased data transmission delays, seriously affecting the normal operation of the business; on the other hand, for data center resource allocation, traditional methods are often not accurate and flexible enough, resulting in idle or overused resources, reducing resource utilization efficiency and overall performance; in addition, as the scale of data centers expands, traditional fault monitoring and recovery mechanisms have slow response speeds, making it difficult to quickly locate and solve problems, which may cause long-term service interruptions and cause huge losses to users.

[0004] Therefore, in this context, by utilizing the powerful learning and prediction capabilities of artificial intelligence, we can achieve real-time and accurate perception of the operating status of the data center, intelligent resource optimization allocation, and rapid fault diagnosis and recovery, thereby improving the efficiency, reliability and flexibility of data center interconnection control and meeting growing business needs. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an artificial intelligence-based data center interconnection control system to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: an artificial intelligence-based data center interconnection control system, comprising:

[0007] Data center interconnection data acquisition module: used to collect data in the data center interconnection process, obtain and analyze various monitoring parameters of data center interconnection control indicators, and transmit various monitoring parameters to the data center interconnection data analysis module;

[0008] Data center interconnection data analysis module: used to analyze the monitoring parameters obtained by the data acquisition module, obtain and analyze the control indicators of the data center interconnection control, and transmit the control indicators to the data center interconnection intelligent control module. The data center interconnection data analysis module includes a data interconnection network flow control analysis unit, a data interconnection resource allocation control analysis unit, a data transmission risk control analysis unit, and a data interconnection fault and response prediction control analysis unit;

[0009] Data center interconnection intelligent control module: used to compare the various control indicators obtained by the data analysis module with the threshold value, perform control according to the comparison results, and transmit the comparison results to the data center interconnection control comprehensive analysis module;

[0010] Data center interconnection control comprehensive analysis module: used to comprehensively analyze the comparison results obtained by the control module, obtain the data center interconnection comprehensive control index, and transmit it to the data center interconnection control human-computer interaction module;

[0011] Data center interconnection control human-computer interaction module: used to transmit the data center interconnection comprehensive control indicators obtained by the comprehensive analysis module to the administrator information terminal for human-computer interaction.

[0012] Preferably, the monitoring parameters in the data center interconnection data acquisition module include administrator identity authentication information, data interconnection network flow control parameters, data interconnection resource allocation control parameters, data transmission risk control parameters and data interconnection failure and response prediction control parameters, wherein the data interconnection network flow control parameters include the delay time of the data packet, the total number of data packets, the real-time data transmission volume and the maximum data transmission volume of the data center interconnection link, and the minimum and maximum delay time; the data interconnection resource allocation control parameters include the CPU working time and idle time, the used memory and the total memory, the used storage space and the total storage space of the hard disk, the number of tasks waiting to be executed and the average response time of the number of tasks; the data transmission risk control parameters include the average rate of encrypted data transmitted, the number of data packet integrity check failures, the total number of data packets sent, the number of illegal accesses to the data center interconnection system and the total number of accesses; the data interconnection failure and response prediction control parameters include the network equipment data set, the response time when the network equipment fails, the number of retransmitted data packets, the total number of data packets sent and the number of lost data packets.

[0013] Preferably, the data interconnection network flow control analysis unit in the data center interconnection data analysis module: within the control period, firstly obtains the time required for a data packet to travel from one data center to another data center, that is, the data center interconnection delay time t, by using the timestamp technology, and obtains the average data packet delay time t avg , , ti represents the delay time of the ith data packet, and n represents the total number of data packets. Then, the real-time bandwidth utilization Bu of the data center interconnection link is obtained through the network monitoring tool. Bu=Tdv / max_Tdv, Tdv represents the real-time data transmission volume of the data center interconnection link, and max_Tdv represents the maximum data transmission volume that the interconnection link can provide. Finally, the network traffic and delay control index NTCI is obtained through big data analysis technology. , t min and t max They represent the minimum and maximum delay times respectively, and a1 and a2 represent the corresponding weights respectively.

[0014] Preferably, the data interconnection resource allocation control and analysis unit in the data center interconnection data analysis module: within the control period, firstly, through the monitoring tool, monitors the CPU working time t_g and idle time t_k of the data center, the used memory um and the used storage space uss of the hard disk, and obtains the data center resource utilization index RUI, , T_um represents the total memory, T_uss represents the total storage space, b1, b2 and b3 represent the corresponding weights respectively; then the number of tasks waiting to be executed n_t and the average response time of the number of tasks (t_rt) are obtained through the application log avg ,Task response time refers to the time required from task submission to task completion; finally, the resource allocation control index LBCI is obtained through big data analysis technology, .

[0015] Preferably, the data transmission risk control analysis unit in the data center interconnection data analysis module: within the control period, firstly obtain the average rate v_ed of encrypted data transmitted by the data center interconnection link through the network security monitoring tool; then obtain the number of data packet integrity check failures n_vf through the data packet analysis technology, and obtain the data packet integrity check failure rate index VFRI, VFRI=n_vf / Tn_dp, Tn_dp represents the total number of data packets sent; record the update timestamp through the security policy management system and calculate the update delay time t_ud, the update delay time refers to the time required from the release of the security policy update to the application of the update by all data center interconnection nodes; obtain the number of attempts to illegally access the data center interconnection system n_la and the total number of accesses Tn_v through the access control log, and obtain the illegal access attempt rate index IARI, IARI=n_la / Tn_v; finally, obtain the data transmission risk control index DSCI through the big data analysis technology, , t_b represents the time required for the security policy update standard, and c1, c2, and c3 represent the corresponding weights respectively.

[0016] Preferably, the data interconnection fault and response prediction control analysis unit in the data center interconnection data analysis module: within the control cycle, firstly obtain the network equipment data set Ed to be monitored in the data center through the log analysis tool, where Ed = [Ed1, Ed2, ..., Ed j ,...,Ed k ], Ed j represents the jth type of network equipment, and k represents the number of types of network equipment in the data center. Then, the response time t_fr when the network equipment fails is obtained through the performance testing tool. Secondly, the number of retransmitted data packets n_dp, the total number of sent data packets Tn_dp, and the number of lost data packets n_ldp in the data center are obtained through the monitoring tool. Finally, the fault and response prediction control index RPCI is obtained through big data analysis technology. , m j represents the number of failures of the jth network device, (t_fr) j represents the jth network device failure response time. The failure response time refers to the time required from the detection of network device failure to recovery. j Indicates the running time of the jth network device.

[0017] Preferably, the data center interconnection intelligent control in the data center interconnection intelligent control module includes the following steps:

[0018] Step 1: Compare the network traffic and delay control index NTCI with the threshold NTCI0 to obtain the efficiency factor η(NTCI) of network traffic and delay control, η(NTCI)=(NTCI-NTCI0) / NTCI0. If η(NTCI)≤0, it is considered that η(NTCI)=0. Otherwise, it is determined whether η(NTCI) exceeds the set range. If so, the data center interconnection network traffic control is performed. If not, it means that the data center interconnection network traffic and delay control are good.

[0019] Step 2: Compare the resource allocation control index LBCI with the threshold LBCI0 to obtain the efficiency factor η(LBCI) of resource allocation control, η(LBCI)=|LBCI-LBCI0| / LBCI0. If η(LBCI)=0, no control is required. Otherwise, determine whether η(LBCI) exceeds the set range. If so, perform data center resource allocation control. Otherwise, it means that the data center interconnection resource allocation control is good.

[0020] Step 3: Compare the data transmission risk control index DSCI with the threshold DSCI0 to obtain the efficiency factor η(DSCI) of data transmission risk control, η(DSCI)=(DSCI-DSCI0) / DSCI0. If η(DSCI)≤0, it is considered that η(DSCI)=0. Otherwise, it is determined whether η(DSCI) exceeds the set range. If so, data center interconnection data transmission risk control is performed. Otherwise, it means that data center interconnection data transmission risk control is good.

[0021] Step 4: Compare the fault and response prediction control index RPCI with the threshold RPCI0 to obtain the efficiency factor η(RPCI) of the fault and response prediction control, η(RPCI)=(RPCI-RPCI0) / RPCI0. If η(RPCI)≤0, it is considered that η(RPCI)=0. Otherwise, determine whether η(RPCI) exceeds the set range. If so, perform data center interconnect fault and response control. Otherwise, it means that the data center interconnect fault and response control is good.

[0022] Preferably, the comprehensive analysis model in the data center interconnection control comprehensive analysis module is: DC_cci=w1×η(NTCI)+w2×η(LBCI)+w3×η(DSCI)+w4×η(RPCI), DC_cci represents the data center interconnection comprehensive control index, w1 represents the weight of the efficiency factor η(NTCI) of network traffic and delay control, w2 represents the weight of the efficiency factor η(LBCI) of resource allocation control, w3 represents the weight of the efficiency factor η(DSCI) of data transmission risk control, and w4 represents the weight of the efficiency factor η(RPCI) of fault and response prediction control.

[0023] Technical effects and advantages of the present invention:

[0024] 1. The present invention uses artificial intelligence technology to accurately analyze network traffic control parameters, optimize the data transmission path and rate between data centers, effectively avoid network congestion, and improve data transmission efficiency; at the same time, through intelligent scheduling of resource allocation control parameters, the system can dynamically adjust resource allocation according to actual business needs, ensure that resources between data centers are efficiently utilized, and reduce resource waste;

[0025] 2. The present invention uses artificial intelligence technology to monitor and analyze data flows in real time, and promptly discover and respond to potential security threats. Through in-depth analysis of data transmission risk control parameters, the system can take targeted security measures to effectively prevent data leakage and illegal access, and further enhance the overall security of the data center interconnection system.

[0026] 3. Through the analysis of data interconnection faults and response prediction control parameters, the artificial intelligence technology of the present invention can predict the types of faults that may occur and the time of occurrence in the data center interconnection system, so as to prevent the faults before they occur, or quickly locate and repair the problems after they occur, while reducing the impact of the faults on the data center interconnection system. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a schematic diagram of the overall process of the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] See also Figure 1 As shown, the present invention provides an artificial intelligence-based data center interconnection control system, including a data center interconnection data acquisition module, a data center interconnection data analysis module, a data center interconnection intelligent control module, a data center interconnection control comprehensive analysis module and a data center interconnection control human-computer interaction module.

[0030] The data center interconnection data acquisition module is connected to the data center interconnection data analysis module, the data center interconnection intelligent control module is respectively connected to the data center interconnection control comprehensive analysis module and the data center interconnection data analysis module, and the data center interconnection control human-computer interaction module is respectively connected to the data center interconnection control comprehensive analysis module and the data center interconnection intelligent control module.

[0031] Data center interconnection data acquisition module: used to collect data in the data center interconnection process, obtain and analyze various monitoring parameters of data center interconnection control indicators, and transmit various monitoring parameters to the data center interconnection data analysis module;

[0032] It should be specifically explained in this embodiment that various monitoring parameters include administrator identity authentication information, data interconnection network flow control parameters, data interconnection resource allocation control parameters, data transmission risk control parameters and data interconnection failure and response prediction control parameters, wherein the data interconnection network flow control parameters include the delay time of the data packet, the total number of data packets, the real-time data transmission volume and the maximum data transmission volume of the data center interconnection link, and the minimum and maximum delay time; the data interconnection resource allocation control parameters include the CPU working time and idle time, the used memory and total memory, the used storage space and total storage space of the hard disk, the number of tasks waiting to be executed, and the average response time of the number of tasks; the data transmission risk control parameters include the average rate of encrypted data transmitted, the number of data packet integrity check failures, the total number of data packets sent, the number of illegal accesses to the data center interconnection system, and the total number of accesses; the data interconnection failure and response prediction control parameters include the network device data set, the response time when the network device fails, the number of retransmitted data packets, the total number of data packets sent, and the number of lost data packets.

[0033] Data center interconnection data analysis module: used to analyze the monitoring parameters obtained by the data acquisition module, obtain and analyze the control indicators of the data center interconnection control, and transmit the control indicators to the data center interconnection intelligent control module. The data center interconnection data analysis module includes a data interconnection network flow control analysis unit, a data interconnection resource allocation control analysis unit, a data transmission risk control analysis unit, and a data interconnection fault and response prediction control analysis unit. Obtaining various control indicators includes the following steps:

[0034] What needs to be specifically explained in this embodiment is that the data interconnection network flow control analysis unit is used to calculate the data interconnection network flow control parameters, the data interconnection resource allocation control analysis unit is used to calculate the data interconnection resource allocation control parameters, the data transmission risk control analysis unit is used to calculate the data transmission risk control parameters, and the data interconnection fault and response prediction control analysis unit is used to calculate the data interconnection fault and response prediction control parameters.

[0035] Step 1: Data interconnection network traffic control analysis unit: During the control period, firstly, the time required for a data packet to travel from one data center to another is obtained through the timestamp technology, that is, the data center interconnection delay time t, and the average data packet delay time t is obtained. avg , , t irepresents the delay time of the ith data packet, and n represents the total number of data packets. Then, the real-time bandwidth utilization Bu of the data center interconnection link is obtained through the network monitoring tool. Bu=Tdv / max_Tdv, Tdv represents the real-time data transmission volume of the data center interconnection link, and max_Tdv represents the maximum data transmission volume that the interconnection link can provide. Finally, the network traffic and delay control index NTCI is obtained through big data analysis technology. , t min and t max Represent the minimum and maximum delay times respectively, a1 and a2 represent the corresponding weights respectively, for example, a1=0.6 and a2=0.4;

[0036] What needs to be specifically explained in this embodiment is that: by reasonably planning the network structure of the data center, using high-quality cables such as high-speed optical fiber, and optimizing equipment configuration, the packet delay can be reduced; by monitoring the real-time bandwidth utilization, when the bandwidth utilization is too high, it indicates that the network data transmission pressure is high and may cause network congestion, the network performance can be optimized, the throughput can be improved, and the delay and packet loss can be reduced.

[0037] Step 2: Data interconnection resource allocation control and analysis unit: During the control cycle, firstly, the CPU working time t_g and idle time t_k, used memory um and used storage space uss of the data center are monitored by the monitoring tool to obtain the data center resource utilization index RUI. , T_um represents the total memory, T_uss represents the total storage space, b1, b2 and b3 represent the corresponding weights, for example, b1=0.4, b2=0.3 and b3=0.3; then the number of tasks waiting to be executed n_t and the average response time of the number of tasks (t_rt) are obtained through the application log avg ,Task response time refers to the time required from task submission to task completion; finally, the resource allocation control index LBCI is obtained through big data analysis technology, ;

[0038] What needs to be specifically explained in this embodiment is that in a data center, the CPU is responsible for executing various computing tasks; the level of memory utilization has an important impact on the performance and stability of the system; storage resources are components used to store data in a data center, and their utilization directly affects the storage capacity of the data and the speed at which the data is accessed; by monitoring changes in the number of task queues, the problem of unbalanced resource allocation can be discovered; by monitoring task response time, the processing capacity and response speed of the system can be evaluated, and then the system performance can be quantitatively analyzed; when resource utilization is too high, it may cause task processing delays or system crashes; and when resource utilization is too low, it may mean that computing resources are not fully utilized, resulting in energy waste.

[0039] Step 3: Data transmission risk control analysis unit: During the control period, firstly, the average rate v_ed of encrypted data transmitted by the data center interconnect link is obtained through the network security monitoring tool; then, the number of data packet integrity check failures n_vf is obtained through the data packet analysis technology, and the data packet integrity check failure rate index VFRI is obtained, VFRI=n_vf / Tn_dp, Tn_dp represents the total number of data packets sent; the update timestamp is recorded and the update delay time t_ud is calculated through the security policy management system, and the update delay time refers to the time required from the release of the security policy update to the application of the update by all data center interconnect nodes. The security policy update includes updating the firewall policy according to the changes in the data center, adjusting the identity authentication and access control policy, etc.; the number of attempts to illegally access the data center interconnect system n_la and the total number of accesses Tn_v are obtained through the access control log, and the illegal access attempt rate index IARI is obtained, IARI=n_la / Tn_v, the number of attempts to illegally access the data center interconnect system refers to the number of attempts to enter, operate or obtain protected resources in the data center interconnect system without authorization or in violation of security policies; finally, the data transmission risk control index DSCI is obtained through big data analysis technology. , t_b represents the time required for the security policy update standard, c1, c2 and c3 represent the corresponding weights, for example, c1=0.4, c2=0.3 and c3=0.3;

[0040] What needs to be specifically explained in this embodiment is that by monitoring the encrypted data transmission rate, it can ensure that the data center interconnection link can meet business needs; by regularly monitoring and analyzing the data packet integrity check failure rate, potential problems in data transmission can be discovered and resolved in a timely manner; by monitoring the security policy update delay, it can ensure that the data center interconnection system can respond to new security challenges in a timely manner; by strengthening the analysis of the intrusion detection system and access control logs, illegal access attempts can be discovered and blocked in a timely manner, thereby improving the security of the data center interconnection system.

[0041] Step 4: Data interconnection fault and response prediction control analysis unit: In the control cycle, firstly, the data set Ed of the network equipment to be monitored in the data center is obtained through the log analysis tool, where Ed = [Ed1, Ed2, ..., Ed j ,...,Ed k ], Ed jrepresents the jth type of network equipment, k represents the number of types of network equipment in the data center, and network equipment includes servers, storage devices, switches, routers, etc. Then, the response time t_fr when the network equipment fails is obtained through the performance testing tool; secondly, the number of retransmitted data packets n_dp, the total number of sent data packets Tn_dp and the number of lost data packets n_ldp in the data center are obtained through the monitoring tool; finally, the fault and response prediction control index RPCI is obtained through big data analysis technology. , m j represents the number of failures of the jth network device, (t_fr) j represents the jth network device failure response time. The failure response time refers to the time required from the detection of network device failure to recovery. j represents the running time of the jth network device;

[0042] What needs to be specifically explained in this embodiment is that by analyzing the failure rate, it is possible to identify equipment and time periods with frequent failures, thereby optimizing maintenance plans and reducing the impact of failures on data center operations; by monitoring the retransmission rate, it is possible to ensure the reliability of data transmission and reduce data loss and errors; by analyzing the packet loss rate, it is possible to identify bottlenecks and weaknesses in the network, thereby optimizing the network structure and improving overall performance.

[0043] Data center interconnection intelligent control module: used to compare the various control indicators obtained by the data analysis module with the threshold value, perform control according to the comparison results, and transmit the comparison results to the data center interconnection control comprehensive analysis module. The data center interconnection intelligent control includes the following steps:

[0044] Step 1: Compare the network traffic and delay control index NTCI with the threshold NTCI0 to obtain the efficiency factor η(NTCI) of network traffic and delay control, η(NTCI)=(NTCI-NTCI0) / NTCI0. If η(NTCI)≤0, it is considered that η(NTCI)=0. Otherwise, it is determined whether η(NTCI) exceeds the set range. If so, data center interconnect network traffic control is performed, such as expanding network bandwidth, optimizing resource allocation and other measures. Otherwise, it means that the data center interconnect network traffic and delay control are good.

[0045] Step 2: Compare the resource allocation control index LBCI with the threshold LBCI0 to obtain the efficiency factor η(LBCI) of resource allocation control, η(LBCI)=|LBCI-LBCI0| / LBCI0. If η(LBCI)=0, no control is required. Otherwise, determine whether η(LBCI) exceeds the set range. If so, perform data center resource allocation control, such as adjusting the resource allocation strategy to balance the load of each queue. Otherwise, it means that the data center interconnection resource allocation control is good.

[0046] Step 3: Compare the data transmission risk control index DSCI with the threshold DSCI0 to obtain the efficiency factor η(DSCI) of data transmission risk control, η(DSCI)=(DSCI-DSCI0) / DSCI0. If η(DSCI)≤0, it is considered that η(DSCI)=0. Otherwise, determine whether η(DSCI) exceeds the set range. If so, perform data center interconnection data transmission risk control, such as optimizing the security policy update process and management system, strengthening the analysis of the intrusion detection system and access control logs, etc. Otherwise, it means that the data center interconnection data transmission risk control is good.

[0047] Step 4: Compare the fault and response prediction control index RPCI with the threshold RPCI0 to obtain the efficiency factor η(RPCI) of the fault and response prediction control, η(RPCI)=(RPCI-RPCI0) / RPCI0. If η(RPCI)≤0, it is considered that η(RPCI)=0. Otherwise, determine whether η(RPCI) exceeds the set range. If so, perform data center interconnect fault and response control, such as optimizing routing, increasing bandwidth, upgrading equipment, etc. Otherwise, it means that the data center interconnect fault and response control is good.

[0048] Data center interconnection control comprehensive analysis module: used to comprehensively analyze the comparison results obtained by the control module, obtain the data center interconnection comprehensive control index DC_cci, and transmit it to the data center interconnection control human-computer interaction module. Its comprehensive analysis model is: DC_cci=w1×η(NTCI)+w2×η(LBCI)+w3×η(DSCI)+w4×η(RPCI), w1 represents the weight of the efficiency factor η(NTCI) of network traffic and delay control, w2 represents the weight of the efficiency factor η(LBCI) of resource allocation control, w3 represents the weight of the efficiency factor η(DSCI) of data transmission risk control, and w4 represents the weight of the efficiency factor η(RPCI) of fault and response prediction control, for example, w1=0.25, w2=0.25, w3=0.25 and w4=0.25;

[0049] Data center interconnection control human-computer interaction module: used to transmit the data center interconnection comprehensive control indicators obtained by the comprehensive analysis module to the administrator information terminal for human-computer interaction. If the data center interconnection comprehensive control indicators are within the set allowable range, it means that the data center interconnection control is good. Otherwise, the administrator is prompted to take timely measures, such as optimizing server configuration, such as increasing memory, replacing faster hard drives, upgrading processors, etc., to improve server performance and response speed; perform network optimization, improve network transmission speed and bandwidth utilization, reduce network delay and packet loss rate, and thus improve the performance and stability of the data center.

[0050] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0051] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. The data center interconnection control system based on artificial intelligence is characterized by: include: Data center interconnection data acquisition module: used to collect data in the data center interconnection process, obtain and analyze various monitoring parameters of data center interconnection control indicators, and transmit various monitoring parameters to the data center interconnection data analysis module; Data center interconnection data analysis module: used to analyze the monitoring parameters obtained by the data acquisition module, obtain and analyze the control indicators of the data center interconnection control, and transmit the control indicators to the data center interconnection intelligent control module. The data center interconnection data analysis module includes a data interconnection network flow control analysis unit, a data interconnection resource allocation control analysis unit, a data transmission risk control analysis unit, and a data interconnection fault and response prediction control analysis unit; Data center interconnection intelligent control module: used to compare the various control indicators obtained by the data analysis module with the threshold value, perform control according to the comparison results, and transmit the comparison results to the data center interconnection control comprehensive analysis module; Data center interconnection control comprehensive analysis module: used to comprehensively analyze the comparison results obtained by the control module, obtain the data center interconnection comprehensive control index, and transmit it to the data center interconnection control human-computer interaction module; Data center interconnection control human-computer interaction module: used to transmit the data center interconnection comprehensive control indicators obtained by the comprehensive analysis module to the administrator information terminal for human-computer interaction.

2. The data center interconnection control system based on artificial intelligence according to claim 1 is characterized in that: The monitoring parameters in the data center interconnection data acquisition module include administrator identity authentication information, data interconnection network flow control parameters, data interconnection resource allocation control parameters, data transmission risk control parameters, and data interconnection failure and response prediction control parameters, wherein the data interconnection network flow control parameters include the delay time of the data packet, the total number of data packets, the real-time data transmission volume and the maximum data transmission volume of the data center interconnection link, and the minimum and maximum delay time; the data interconnection resource allocation control parameters include the CPU working time and idle time, the used memory and total memory, the used storage space and total storage space of the hard disk, the number of tasks waiting to be executed, and the average response time of the number of tasks; Data transmission risk control parameters include the average rate of encrypted data transmission, the number of data packet integrity check failures, the total number of data packets sent, the number of illegal accesses to the data center interconnection system, and the total number of accesses; data interconnection failure and response prediction control parameters include network device data sets, response time when network equipment fails, the number of retransmitted data packets, the total number of data packets sent, and the number of lost data packets.

3. The data center interconnection control system based on artificial intelligence according to claim 1 is characterized in that: The data interconnection network flow control analysis unit in the data center interconnection data analysis module: within the control period, firstly, the time required for a data packet to travel from one data center to another data center is obtained by using the timestamp technology, that is, the data center interconnection delay time t, and the average data packet delay time t is obtained. avg , , t i represents the delay time of the ith data packet, and n represents the total number of data packets. Then, the real-time bandwidth utilization Bu of the data center interconnection link is obtained through the network monitoring tool. Bu=Tdv / max_Tdv, Tdv represents the real-time data transmission volume of the data center interconnection link, and max_Tdv represents the maximum data transmission volume that the interconnection link can provide. Finally, the network traffic and delay control index NTCI is obtained through big data analysis technology. , t min and t max They represent the minimum and maximum delay times respectively, and a1 and a2 represent the corresponding weights respectively.

4. The data center interconnection control system based on artificial intelligence according to claim 1 is characterized in that: The data interconnection resource allocation control and analysis unit in the data center interconnection data analysis module: within the control period, firstly, the CPU working time t_g and idle time t_k, the used memory um and the used storage space uss of the hard disk of the data center are monitored by the monitoring tool to obtain the data center resource utilization index RUI, , T_um represents the total memory, T_uss represents the total storage space, b1, b2 and b3 represent the corresponding weights respectively; then the number of tasks waiting to be executed n_t and the average response time of the number of tasks (t_rt) are obtained through the application log avg ,Task response time refers to the time required from task submission to task completion; finally, the resource allocation control index LBCI is obtained through big data analysis technology, .

5. The data center interconnection control system based on artificial intelligence according to claim 1 is characterized in that: The data transmission risk control analysis unit in the data center interconnection data analysis module: within the control period, firstly obtain the average rate v_ed of encrypted data transmitted by the data center interconnection link through the network security monitoring tool; then obtain the number of data packet integrity check failures n_vf through the data packet analysis technology, and obtain the data packet integrity check failure rate index VFRI, VFRI=n_vf / Tn_dp, Tn_dp represents the total number of data packets sent; record the update timestamp through the security policy management system and calculate the update delay time t_ud, the update delay time refers to the time required from the release of the security policy update to the application of the update by all data center interconnection nodes; obtain the number of attempts to illegally access the data center interconnection system n_la and the total number of accesses Tn_v through the access control log, and obtain the illegal access attempt rate index IARI, IARI=n_la / Tn_v; finally, obtain the data transmission risk control index DSCI through the big data analysis technology, , t_b represents the time required for the security policy update standard, and c1, c2, and c3 represent the corresponding weights respectively.

6. The data center interconnection control system based on artificial intelligence according to claim 1, characterized in that: The data interconnection fault and response prediction control analysis unit in the data center interconnection data analysis module: within the control cycle, firstly obtain the data center network equipment data set Ed to be monitored through the log analysis tool, Ed = [Ed1, Ed2, ..., Ed j ,...,Ed k ], Ed j represents the jth type of network equipment, and k represents the number of types of network equipment in the data center. Then, the response time t_fr when the network equipment fails is obtained through the performance testing tool. Secondly, the number of retransmitted data packets n_dp, the total number of sent data packets Tn_dp, and the number of lost data packets n_ldp in the data center are obtained through the monitoring tool. Finally, the fault and response prediction control index RPCI is obtained through big data analysis technology. , m j represents the number of failures of the jth network device, (t_fr) j represents the jth network device failure response time. The failure response time refers to the time required from the detection of network device failure to recovery. j Indicates the running time of the jth network device.

7. The data center interconnection control system based on artificial intelligence according to claim 1 is characterized in that: The data center interconnection intelligent control in the data center interconnection intelligent control module includes the following steps: Step 1: Compare the network traffic and delay control index NTCI with the threshold NTCI0 to obtain the efficiency factor η(NTCI) of network traffic and delay control, η(NTCI)=(NTCI-NTCI0) / NTCI0. If η(NTCI)≤0, it is considered that η(NTCI)=0. Otherwise, it is determined whether η(NTCI) exceeds the set range. If so, the data center interconnection network traffic control is performed. If not, it means that the data center interconnection network traffic and delay control are good. Step 2: Compare the resource allocation control index LBCI with the threshold LBCI0 to obtain the efficiency factor η(LBCI) of resource allocation control, η(LBCI)=|LBCI-LBCI0| / LBCI0. If η(LBCI)=0, no control is required. Otherwise, determine whether η(LBCI) exceeds the set range. If so, perform data center resource allocation control. Otherwise, it means that the data center interconnection resource allocation control is good. Step 3: Compare the data transmission risk control index DSCI with the threshold DSCI0 to obtain the efficiency factor η(DSCI) of data transmission risk control, η(DSCI)=(DSCI-DSCI0) / DSCI0. If η(DSCI)≤0, it is considered that η(DSCI)=0. Otherwise, it is determined whether η(DSCI) exceeds the set range. If so, data center interconnection data transmission risk control is performed. Otherwise, it means that data center interconnection data transmission risk control is good. Step 4: Compare the fault and response prediction control index RPCI with the threshold RPCI0 to obtain the efficiency factor η(RPCI) of the fault and response prediction control, η(RPCI)=(RPCI-RPCI0) / RPCI0. If η(RPCI)≤0, it is considered that η(RPCI)=0. Otherwise, determine whether η(RPCI) exceeds the set range. If so, perform data center interconnect fault and response control. Otherwise, it means that the data center interconnect fault and response control is good.

8. The data center interconnection control system based on artificial intelligence according to claim 1, characterized in that: The comprehensive analysis model in the data center interconnection control comprehensive analysis module is: DC_cci=w1×η(NTCI)+w2×η(LBCI)+w3×η(DSCI)+w4×η(RPCI), DC_cci represents the data center interconnection comprehensive control index, w1 represents the weight of the efficiency factor η(NTCI) of network traffic and delay control, w2 represents the weight of the efficiency factor η(LBCI) of resource allocation control, w3 represents the weight of the efficiency factor η(DSCI) of data transmission risk control, and w4 represents the weight of the efficiency factor η(RPCI) of fault and response prediction control.

Images