SDN (Software Defined Network) core network QoS (Quality of Service) routing optimization algorithm based on reinforcement learning

Abstract

The invention discloses an SDN (Software Defined Network) core network QoS (Quality of Service) routing optimization algorithm based on reinforcement learning. The SDN core network QoS routing optimization algorithm comprises the following steps: acquiring network topology and real-time node information and link information through an SDN controller; according to the obtained network topology and real-time node information and link information, calculating a reward matrix by using a QoS network routing optimization model; initializing and updating the Q table; and obtaining a required optimal forwarding path according to the Q table which is iteratively updated. According to the method, multiple QoS intentions such as low delay, low jitter, large bandwidth, preferential use of private lines and service levels can be met, the shortest forwarding path meeting the QoS requirement can be found for each service flow, the link utilization rate is high, network congestion can be effectively prevented and reduced, and the network resource utilization rate is improved.

Description

technical field [0001] The invention belongs to the field of network technology, and relates to an SDN core network QoS routing optimization algorithm based on reinforcement learning. Background technique [0002] In recent years, with the development of cloud technology, mobile terminals, Internet of Things, big data and other related IT technologies, the Internet industry is still in the process of rapid development, network traffic is increasing rapidly, and network applications are becoming more and more diversified. The network poses some new requirements. Especially in recent years, with the rise of applications such as short videos, live broadcast platforms, and online education, the real-time nature of network business interaction has been continuously enhanced, and network bandwidth consumption has continued to increase. demanding. However, in the case of limited network resources, a substantial increase in network burden will bring many problems such as low servi...

AI Technical Summary

Problems solved by technology

However, the current mainstream SDN routing modules basically use the Dijkstra algorithm. This algorithm does not consider the change of the remaining bandwidth of each link when performing routing calculations. All data packets only rely on the shortest path algorithm. If the data flow suddenly It is easy to cause link congestion due to the selection of the same link, which will lead to a significant decrease in network performance

Images