Research Article
An Adaptive Measurement Method for Flow Traffic in Software Defined Networking
@INPROCEEDINGS{10.1007/978-3-030-32216-8_11, author={Liuwei Huo and Dingde Jiang and Xiangnan Zhu and Huibin Jia}, title={An Adaptive Measurement Method for Flow Traffic in Software Defined Networking}, proceedings={Simulation Tools and Techniques. 11th International Conference, SIMUtools 2019, Chengdu, China, July 8--10, 2019, Proceedings}, proceedings_a={SIMUTOOLS}, year={2019}, month={10}, keywords={Software Defined Networking Adaptive network measurement Traffic matrix Artificial Intelligence}, doi={10.1007/978-3-030-32216-8_11} }- Liuwei Huo
Dingde Jiang
Xiangnan Zhu
Huibin Jia
Year: 2019
An Adaptive Measurement Method for Flow Traffic in Software Defined Networking
SIMUTOOLS
Springer
DOI: 10.1007/978-3-030-32216-8_11
Abstract
In Software Defined Networking (SDN), the fine-grained measurements are crucial for network management and design. However, the measurement overhead and accuracy are contradiction, how to accurately measure the network traffic with low overhead has become a hot topic. Artificial Intelligence (AI) has been used to predict the traffic in networks. Then, we propose an AI-based Lightweight Adaptive Measurement Method (ALAMM) for traffic measurement in SDN with low overhead and high measurement accuracy. Firstly, we use measurements in the front to train the AI-based traffic prediction model and utilize the model to predict traffic in SDN. Then, we obtain the sequence of sampling points by judging the change of traffic prediction and send the measurement primitive to switches to obtain coarse-grained measurements. At last, we utilize the interpolation theory to fill the coarse-grained measurement and propose an optimization function to optimize the fine-grained measurement. Simulation results show that the ALAMM is feasible, and the measurement overhead of ALAMM is low.
