Dynamic Link Adaptation in IEEE 802.11ac: A Distributed Learning Based Approach
Authors:
- Raja KarmakarRKRaja Karmakar
- Samiran ChattopadhyaySCSamiran Chattopadhyay
- Sandip ChakrabortySCSandip Chakraborty
- 26 December 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 87-94
Abstract
High throughput wireless access networks based on IEEE 802.11ac show a significant challenge in dynamically selecting the link configuration parameters based on channel conditions due to large pool of design set, like number of spatial streams, channel bonding, guard intervals, frame aggregation and different modulation and coding schemes. In this paper, we develop a learning based approach for link adaptation motivated by the multi-armed bandit based distributed learning algorithm. The proposed link adaptation algorithm, BanditLink, explores different possible configuration options based on observing their impact over the network performance at various channel conditions. We analyze the performance of BanditLink from simulation results, and observe that it performs significantly better compared to other competing mechanisms proposed in the literature.Keywords
This publication has 13 references indexed in Scilit:
- SampleLiteACM SIGCOMM Computer Communication Review, 2015
- Adaptive Modulation and Coding for Interference Alignment With Imperfect CSITIEEE Transactions on Wireless Communications, 2014
- Performance analysis of greedy fast-shift block acknowledgement for high-throughput WLANsWireless Networks, 2014
- Performance Study on a CSMA/CA-Based MAC Protocol for Multi-User MIMO Wireless LANsIEEE Transactions on Wireless Communications, 2014
- Intelligent Channel Bonding in 802.11n WLANsIEEE Transactions on Mobile Computing, 2013
- Evaluation of the Minstrel rate adaptation algorithm in IEEE 802.11g WLANs2013
- Gigabit wireless LANsACM SIGMOBILE Mobile Computing and Communications Review, 2011
- MIMO rate adaptation in 802.11n wireless networks2010
- Open-Loop Link Adaptation for Next-Generation IEEE 802.11n Wireless NetworksIEEE Transactions on Vehicular Technology, 2009
- Finite-time Analysis of the Multiarmed Bandit ProblemMachine Learning, 2002