Distributed Traffic Engineering in Hybrid Software Defined Networks: A Multi-agent Reinforcement Learning Framework

TL;DR

This paper introduces a multi-agent reinforcement learning framework for traffic engineering in hybrid SDNs, enabling adaptive, scalable, and efficient routing decisions that outperform traditional centralized methods under dynamic network conditions.

Contribution

It proposes a novel multi-agent reinforcement learning approach with an interactive environment and difference reward mechanism for scalable and adaptive traffic engineering in hybrid SDNs.

Findings

CMRL outperforms traditional methods in dynamic traffic scenarios.

The multi-agent approach reduces computation overhead and reaction time.

Simulation results on real traffic traces validate the effectiveness of CMRL.

Abstract

Traffic Engineering (TE) is an efficient technique to balance network flows and thus improves the performance of a hybrid Software Defined Network (SDN). Previous TE solutions mainly leverage heuristic algorithms to centrally optimize link weight setting or traffic splitting ratios under the static traffic demand. Note that as the network scale becomes larger and network management gains more complexity, it is notably that the centralized TE methods suffer from a high computation overhead and a long reaction time to optimize routing of flows when the network traffic demand dynamically fluctuates or network failures happen. To enable adaptive and efficient routing in TE, we propose a Multi-agent Reinforcement Learning method CMRL that divides the routing optimization of a large network into multiple small-scale routing decisionmaking problems. To coordinate the multiple agents for achieving a global optimization goal, we construct an interactive environment for training the routing agents that own partial link utilization observations. To optimize credit assignment of multi-agent, we introduce the difference reward assignment mechanism for encouraging agents to take better action. Extensive simulations conducted on the real traffic traces demonstrate the superiority of CMRL in improving TE performance, especially when traffic demands change or network failures happen.