IEEE 802.11n, IEEE 802.11ax etc. are known as High Throughput Wireless Local Area Networks standards. These standards are extended versions of the popular IEEE 802.11 standard and they have been developed to support high physical datarate. Consequently, these high throughput wireless standards are also known as High Throughput Wireless Local Area Networks (HT-WLANs). A large number of novel link configuration parameters at both Physical (PHY) and Medium Access Control (MAC) layers have been incorporated in these standards. Some such novel features include Multiple Input Multiple Output (MIMO) technology, channel bonding, Short Guard Interval (SGI), advanced Modulation and Coding Scheme (MCS) at the physical layer and frame aggregation, Block Acknowledgement (BACK) etc at the MAC layer. These new parameters can help to enhance physical data rate so that Gigabits of data can be sent per second. However, an adaptive transmission in response to time-varying channel condition is a key challenge to achieve both high throughput and transmission reliability in wireless communication links. In addition, due to a large pool of available design set of aforesaid link parameters, the high throughput standards reveal a significant challenge to adapt link configuration parameters dynamically by considering the present channel condition. In high throughput wireless standards, all enhancements of PHY/MAC also have their internal trade-offs influencing the channel quality that, in turn, affect throughput in practical scenarios. This tutorial explores several research directions to enhance the performance of HT-WLANs. The objective of this article is to introduce a number of new machine learning methods to adaptively tune different link configuration parameters based on the present network condition. This article attempts to establish a fusion of two apparently disparate topics such as machine learning and wireless network performance that will keep the readers engrossed in an uneasy quietness.
[1]
Samiran Chattopadhyay,et al.
SmartBond: A Deep Probabilistic Machinery for Smart Channel Bonding in IEEE 802.11ac
,
2020,
IEEE INFOCOM 2020 - IEEE Conference on Computer Communications.
[2]
Samiran Chattopadhyay,et al.
Intelligent MU-MIMO User Selection With Dynamic Link Adaptation in IEEE 802.11ax
,
2019,
IEEE Transactions on Wireless Communications.
[3]
Samiran Chattopadhyay,et al.
SmartLA: Reinforcement learning-based link adaptation for high throughput wireless access networks
,
2017,
Comput. Commun..
[4]
Samiran Chattopadhyay,et al.
Impact of IEEE 802.11n/ac PHY/MAC High Throughput Enhancements on Transport and Application Protocols—A Survey
,
2017,
IEEE Communications Surveys & Tutorials.
[5]
Sandip Chakraborty,et al.
An online learning approach for auto link-Configuration in IEEE 802.11ac wireless networks
,
2020,
Comput. Networks.
[6]
Sandip Chakraborty,et al.
A Deep Probabilistic Control Machinery for Auto-Configuration of WiFi Link Parameters
,
2020,
IEEE Transactions on Wireless Communications.