MER-SDN: Machine Learning Framework for Traffic Aware Energy Efficient Routing in SDN

TL;DR

This paper introduces MER-SDN, a machine learning framework that enhances energy-efficient routing in SDN by predicting optimal parameters, reducing feature size, and accelerating heuristic convergence, thereby improving network energy management.

Contribution

The paper presents a novel machine learning framework for traffic-aware energy-efficient routing in SDN, including feature reduction and fast heuristic parameter prediction.

Findings

Achieves over 65% feature size reduction.

Attains more than 70% accuracy in parameter prediction.

Refines heuristics to converge 25 times faster than brute force.

Abstract

Software Defined Networking (SDN) achieves programmability of a network through separation of the control and data planes. It enables flexibility in network management and control. Energy efficiency is one of the challenging global problems which has both economic and environmental impact. A massive amount of information is generated in the controller of an SDN based network. Machine learning gives the ability to computers to progressively learn from data without having to write specific instructions. In this work, we propose MER-SDN: a machine learning framework for traffic-aware energy efficient routing in SDN. Feature extraction, training, and testing are the three main stages of the learning machine. Experiments are conducted on Mininet and POX controller using real-world network topology and dynamic traffic traces from SNDlib. Results show that our approach achieves more than 65\% feature size reduction, more than 70% accuracy in parameter prediction of an energy efficient heuristics algorithm, also our prediction refine heuristics converges the predicted value to the optimal parameters values with up to 25X speedup as compared to the brute force method.