DSpace logo

Please use this identifier to cite or link to this item: http://dspace.bits-pilani.ac.in:8080/jspui/xmlui/handle/123456789/9970
Title: Multiagent Autonomous Learning for Distributed Channel Allocation in Wireless Networks
Authors: Zafaruddin, S.M.
Keywords: EEE
Distributed channel allocation
Multiplayer multi-armed bandit
Online learning
Dynamic spectrum accesses
Resource management
Wireless networks
Issue Date: Jul-2019
Publisher: IEEE
Abstract: In distributed networks such as ad-hoc and device-to-device (D2D) networks, no base station exists and conveying global channel state information (CSI) between users is costly or simply impractical. When the CSI is time-varying and unknown to the users, the users face the challenge of both learning the channel statistics online and converging to good channel allocation. This introduces a multi-armed bandit (MAB) scenario with multiple decision makers. If two or more users choose the same channel, a collision occurs and they all receive zero reward. We propose a distributed channel allocation algorithm in which each user converges to the optimal allocation while achieving an order optimal regret of O (log T), where T denotes the length of time horizon. The algorithm is based on a carrier sensing multiple access (CSMA) implementation of the distributed auction algorithm. It does not require any exchange of information between users. Users need only to observe a single channel at a time and sense if there is a transmission on that channel, without decoding the transmissions or identifying the transmitting users. We compare the performance of the proposed algorithm with the state-of-the-art scheme using simulations of realistic long term evolution (LTE) channels.
URI: https://ieeexplore.ieee.org/abstract/document/8815567
http://dspace.bits-pilani.ac.in:8080/xmlui/handle/123456789/9970
Appears in Collections:Department of Electrical and Electronics Engineering

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.