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.
翻译:软件定义网络(SDN) 通过将控制和数据平面分离,实现网络的可编程性。 它允许网络管理和控制的灵活性。 能源效率是具有经济和环境影响的具有挑战性的全球性问题之一。 SDN 网络控制器生成了大量信息。 机器学习使计算机有能力从数据中逐步学习而不必写具体指示。 在这项工作中, 我们提议 MERC- SDN: SDN 中交通认知能效路由的机器学习框架。 特性提取、 培训和测试是学习机器的三个主要阶段。 利用SNDlib 的实域网络地形学和动态交通轨迹对Mininet 和 POX 控制器进行了实验。 结果显示,我们的方法在节能超高的超光速运算法的参数预测中,超过70%的精确度将预测值与最佳参数值相匹配, 与粗力法相比, 最高可达 25X 加速 。