SDN network intelligent routing data transmission method based on distributed deep reinforcement learning

Abstract

The invention discloses a distributed deep reinforcement learning SDN network intelligent routing data transmission method, which realizes fast routing path calculation, maximizes throughput under the condition of guaranteed delay, and solves the problems of slow speed and small throughput of traditional algorithms. The invention uses a reinforcement learning algorithm, which simplifies the routing calculation process into a simple input and output, avoids multiple iterations in the calculation, and realizes the rapid calculation of the routing path. The speed of the routing algorithm reduces the forwarding delay, and the original cause Packets discarded at the expiration of ttl have a higher probability of surviving and successfully forwarding, which increases network throughput. The present invention is provided with two stages of off-line training and on-line training, and the optimal path is selected by updating parameters in a dynamic environment, so it has topology adaptability.

Description

technical field [0001] The invention belongs to the field of data transmission, and in particular relates to an SDN network intelligent routing data transmission method of distributed deep reinforcement learning. Background technique [0002] The current information technology has entered a mature stage. In the SDN network (Software Defined Network) architecture, the data flow is flexible and controllable, and the controller has a view of the entire network and can perceive network status changes in real time (such as traffic distribution, congestion status, and link utilization. situation, etc.), in reality, the routing problem is often solved by the shortest path algorithm, some simple network parameters (such as path hops, delay, etc.) The minimum path is taken as the final goal of the algorithm. A single metric and optimization goal can easily lead to congestion of some key links, resulting in unbalanced network load. Although the shortest routing algorithm based on La...

AI Technical Summary

Problems solved by technology

A single metric and optimization goal can easily lead to congestion of some key links, resulting in unbalanced network load

Although the shortest routing algorithm based on Lagrangian relaxation can find the optimal path with complex multi-constraint conditions when assigning multiple service paths, this type of heuristic routing algorithm must go through multiple iterations to calculate the optimal path, and the convergence speed Slow, poor timeliness, low throughput

Images