Abstract
In recent years, as a new subject in the computer field, artificial intelligence has developed rapidly, especially in reinforcement learning (RL) and deep reinforcement learning. Combined with the characteristics of Software Defined Network (SDN) for centralized control and scheduling, resource scheduling based on artificial intelligence becomes possible. However, the current SDN routing algorithm has the problem of low link utilization and is unable to update and adjust according to the real-time network status. This paper aims to address these problems by proposing a reinforcement learning-based multipath routing for SDN (RLMR) scheme. RLMR uses Markov Decision Process (MDP) and Q-Learning for training. Based on the real-time information of network state and flow characteristics, RLMR performs routing for different flows. When there is no link that meets the bandwidth requirements, the remaining flows are redistributed according to the Quality of Service (QoS) priority to complete the multipath routing. In addition, this paper defines the forward efficiency (FE) to measure the link bandwidth utilization (LBU) under multipath routing. Simulation results show that compared with the current mainstream shortest path algorithm and ECMP algorithm, the routing algorithm in RLMR has advantages in FE, jitter, and packet loss rate. It can effectively improve the efficiency and quality of routing.
Highlights
As the rapid development of the Internet, people are increasingly dependent on the network, and the amount of data in the network is exploding
In traditional network, existing multipath routing such as ECMP [1] and WCMP is less efficient in matching the current data flow requirements for Quality of Service (QoS) [2, 3] and collecting real-time operating status of the network
Its flow engineering system is the idea of multipath routing for each different flow. e maximum-minimum fair bandwidth allocation algorithm is provided to greatly improve the system link bandwidth utilization (LBU)
Summary
As the rapid development of the Internet, people are increasingly dependent on the network, and the amount of data in the network is exploding. In traditional network, existing multipath routing such as ECMP [1] and WCMP is less efficient in matching the current data flow requirements for QoS [2, 3] and collecting real-time operating status of the network. RLMR is proposed to perform multipath routing of network flow based on the current network status information and flow characteristics. Simulation shows that this scheme can find multiple. At the same time, compared with the existing flow scheduling algorithm, the flow scheduling scheme proposed in this paper can effectively reduce the network delay and reduce the network packet loss rate.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have