Rate Adaptation Techniques Using Contextual Bandit Approach for Mobile Wireless LAN Users

Rate adaptation (RA) is used in IEEE 802.11 WLANs to determine the optimal datarate for a particular channel condition. It becomes especially difficult to determine the optimal datarate for the new High-Throughput WLANs since the number of available datarates in these standards are very high. Moreover, a mobile environment poses additional challenge in RA as the channel conditions will keep on changing from time to time. In this paper, we propose a Contextual Bandits based Rate Adaptation (ContRA) algorithm for mobile users in IEEE 802.11ac standard. Based on the Received Signal Strength Indicator (RSSI) range that the receiver is currently in, the RA algorithm tries to determine the optimal rate from the rate set suitable for packet transmission in that RSSI range. Performance studies show that the proposed RA algorithm is able to adapt to changing channel conditions and quickly choose a suitable datarate for those channel conditions.

[1]  R. Srikant,et al.  Low-Complexity, Low-Regret Link Rate Selection in Rapidly-Varying Wireless Channels , 2018, IEEE INFOCOM 2018 - IEEE Conference on Computer Communications.

[2]  Donggyu Yun,et al.  Optimal Rate Sampling in 802.11 Systems: Theory, Design, and Implementation , 2019, IEEE Transactions on Mobile Computing.

[3]  Shipra Agrawal,et al.  Thompson Sampling for Contextual Bandits with Linear Payoffs , 2012, ICML.

[4]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[5]  Atilla Eryilmaz,et al.  Link Rate Selection using Constrained Thompson Sampling , 2019, IEEE INFOCOM 2019 - IEEE Conference on Computer Communications.

[6]  Mahesh K. Marina,et al.  SampleLite: A Hybrid Approach to 802.11n Link Adaptation , 2015, CCRV.

[7]  Kang G. Shin,et al.  Post-CCA and Reinforcement Learning Based Bandwidth Adaptation in 802.11ac Networks , 2018, IEEE Transactions on Mobile Computing.

[8]  Xiangming Wen,et al.  Rate Adaptation With Thompson Sampling in 802.11ac WLAN , 2019, IEEE Communications Letters.