Search

CN-122002392-A - Communication big data resource management method, device and equipment

CN122002392ACN 122002392 ACN122002392 ACN 122002392ACN-122002392-A

Abstract

The invention provides a communication big data resource management method, a device and equipment, wherein the method comprises the steps of constructing an equipment association map based on association relations and association weights among equipment in a communication network, carrying out operation state prediction based on real-time operation state data and historical operation state data of each equipment node to obtain operation state prediction data of each equipment node, carrying out path planning on data to be transmitted in the equipment association map based on the operation state prediction data, and determining a transmission path. By constructing the device association map capable of reflecting the inter-device internal connection and combining with the prediction of the future running state of the device, the transmission path planning process of the data to be transmitted is realized. The method can effectively foresee and avoid future network congestion and resource bottleneck, dynamically guide the data flow to the optimal path, thereby remarkably improving the overall utilization rate of communication network resources, reducing transmission delay and enhancing the stability and service quality of the network.

Inventors

  • YU JIE
  • LIU MENGLONG

Assignees

  • 浪潮通信信息系统有限公司

Dates

Publication Date
20260508
Application Date
20260122

Claims (10)

  1. 1. A method for managing communication big data resources, comprising: constructing a device association map of a communication network based on association relations among devices in the communication network and association weights among the devices; based on the real-time running state data and the historical running state data of each equipment node in the equipment association map, running state prediction is carried out on each equipment node to obtain running state prediction data of each equipment node; And carrying out path planning on the data to be transmitted in the equipment association map based on the running state prediction data, and determining the transmission path of the data to be transmitted.
  2. 2. The method for managing communication big data resources according to claim 1, wherein the constructing a device association map of the communication network based on association relationships between devices in the communication network and association weights between the devices comprises: Constructing an initial association map of the communication network by taking all devices in the communication network as nodes and the association relation among all the devices as edges; Determining association weights among the devices based on the interaction frequencies among the devices and the similarity of interaction contents among the devices; and weighting each equipment node in the initial association map based on the association weight among the equipment to obtain the equipment association map.
  3. 3. The method for managing communication big data resources according to claim 2, further comprising, after said constructing a device association map of said communication network: determining a time sequence attenuation factor of each device based on the communication time interval of each device; and updating the association weight based on the time sequence attenuation factor, and updating the equipment association map based on the updated association weight.
  4. 4. The method for managing communication big data resources according to claim 1, wherein the performing path planning on the data to be transmitted in the device association map based on the operation state prediction data, and determining the transmission path of the data to be transmitted, includes: Constructing a future state topology of the communication network based on the operational state prediction data and the device association graph; And carrying out path planning on the data to be transmitted in the future state topology based on a path planning algorithm, and determining an optimal transmission path of the data to be transmitted.
  5. 5. The method of claim 4, wherein the objective function constraints of the path planning algorithm include one or more of network latency minimization, bandwidth utilization maximization, and link importance score.
  6. 6. The method for managing communication big data resources according to claim 5, wherein the determining of the link importance score includes: Aggregating the neighbor node characteristics of each device in the device association graph, and generating a node embedding vector for each device node; And determining the link importance score of each link in the equipment association map based on the node embedding vector of each equipment node.
  7. 7. The method for managing big data resources for communication according to claim 6, wherein after determining the link importance score of each link in the device association map based on the node embedding vector of each device node, further comprising: determining nodes in the links with the link importance scores larger than a first preset threshold value as key hub nodes, and determining nodes in the links with the link importance scores smaller than a second preset threshold value as abnormal link nodes; And updating the association weight based on the key hub node and the abnormal link node, and updating the equipment association map based on the updated association weight.
  8. 8. The method for managing communication big data resources according to claim 1, wherein obtaining real-time operation state data of each device node in the device association map includes: Based on an acquisition agent deployed at an edge computing node of the communication network, real-time running state data of each device in the communication network is acquired.
  9. 9. A communication big data resource management device, comprising: The map construction module is used for constructing a device association map of the communication network based on the association relation between devices in the communication network and the association weight between the devices; The prediction module is used for predicting the running state of each equipment node based on the real-time running state data and the historical running state data of each equipment node in the equipment association graph to obtain the running state prediction data of each equipment node; And the path planning module is used for planning a path of the data to be transmitted in the equipment association map based on the running state prediction data and determining a transmission path of the data to be transmitted.
  10. 10. An electronic device comprising a memory, a processor and a computer program stored on the memory and running on the processor, characterized in that the processor implements the communication big data resource management method according to any of claims 1 to 8 when executing the computer program.

Description

Communication big data resource management method, device and equipment Technical Field The present invention relates to the field of communications technologies, and in particular, to a method, an apparatus, and a device for managing a communication big data resource. Background In the technical field of communication, with the rapid development of technologies such as 5G, internet of things and edge computing, the data flow and the number of device connections in a network are explosively increased, and efficient resource management is performed on massive communication big data, so that the method has become a core link for guaranteeing network service quality and improving operation efficiency. The resource management for communicating big data in the existing method is realized by relying on a traditional network management system. The network management system mainly monitors key performance indexes of each network device and alarms and passive resource adjustment according to preset static thresholds and curing rules. The existing adjustment mode has obvious hysteresis, and can only respond after congestion or performance bottleneck occurs, so that the network is in a low-load running state most of the time, and huge waste of network resources is caused, thereby causing lower resource utilization rate of the communication network. Disclosure of Invention The invention provides a method, a device and equipment for managing communication big data resources, which are used for solving the defect that the resource utilization rate of a communication network is low because the response can be made after congestion or performance bottleneck occurs based on obvious hysteresis in the resource management process of a network management system in the prior art and improving the resource utilization rate of the communication network. The invention provides a communication big data resource management method, which comprises the following steps: constructing a device association map of a communication network based on association relations among devices in the communication network and association weights among the devices; based on the real-time running state data and the historical running state data of each equipment node in the equipment association map, running state prediction is carried out on each equipment node to obtain running state prediction data of each equipment node; And carrying out path planning on the data to be transmitted in the equipment association map based on the running state prediction data, and determining the transmission path of the data to be transmitted. According to the invention, a device association map of a communication network is constructed based on association relations among devices in the communication network and association weights among the devices, and the method comprises the following steps: Constructing an initial association map of the communication network by taking all devices in the communication network as nodes and the association relation among all the devices as edges; Determining association weights among the devices based on the interaction frequencies among the devices and the similarity of interaction contents among the devices; and weighting each equipment node in the initial association map based on the association weight among the equipment to obtain the equipment association map. According to the invention, after the communication big data resource management is performed, the device association map of the communication network is constructed, the method further comprises the following steps: determining a time sequence attenuation factor of each device based on the communication time interval of each device; and updating the association weight based on the time sequence attenuation factor, and updating the equipment association map based on the updated association weight. According to the communication big data resource management provided by the invention, the path planning is performed on the data to be transmitted in the equipment association map based on the running state prediction data, and the transmission path of the data to be transmitted is determined, which comprises the following steps: Constructing a future state topology of the communication network based on the operational state prediction data and the device association graph; And carrying out path planning on the data to be transmitted in the future state topology based on a path planning algorithm, and determining an optimal transmission path of the data to be transmitted. According to one embodiment of the present invention, the objective function constraint of the path planning algorithm includes one or more of minimizing network latency, maximizing bandwidth utilization, and scoring link importance. According to the invention, the determining process of the link importance score comprises the following steps: Aggregating the neighbor node characteristics of each device in the