Optimization of reinforcement routing for wireless mesh network using machine learning and high‐performance computing
Authors:
- 23 March 2022
- journal article
- research article
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 34 (15)
Abstract
In the modern world, wireless mesh networks (WMN) are widely used in Internet of Things (IoT) applications. It is a dynamic, infrastructure‐less multihop network with mobility features. In WMN, to design an effective and strong routing protocol is a challenge. Conventional protocols for routing using a remote vector or link‐state routing are not ideal for a wireless network. The shortest routing path is used with all current traditional routing protocols to pick a route with a minimum number of hops. The decisions must be done in real‐time in high‐traffic networks for the route selection and for the packets to be diversified into other routes. The routing protocols should adapt to the traffic conditions, that is, the network load changes and the route must be selected accordingly. The route may not be the shortest in number, but the best in terms of the actual time a packet requires to reach the target. The key objective of this research work is to design such an adaptive routing algorithm, while minimizing the delivery time and preventing the network from congestion. The rationale for this research work is to optimize adaptive routing protocol based on reinforcement learning, which efficiently delivers packets in the WMN. The experimental evaluation demonstrates that the obtained results significantly improve the system performance compared to the benchmark routing protocols. The Quality of Service (QoS) parameters such as packet delivery ratio (PDR), delay, and throughput metrics are used to assess the performance of the proposed technique using the NS‐3 simulator.Keywords
This publication has 36 references indexed in Scilit:
- Dynamic dual-reinforcement-learning routing strategies for quality of experience-aware wireless mesh networkingComputer Networks, 2015
- Clonal-Selection-Based Minimum-Interference Channel Assignment Algorithms for Multiradio Wireless Mesh Networks2015
- QGrid: Q-learning based routing protocol for vehicular ad hoc networks2014
- QoS-aware distributed adaptive cooperative routing in wireless sensor networksAd Hoc Networks, 2014
- Performance evaluation and comparison of AODV and DSR routing protocols in MANETs under wormhole attack2013
- Reinforcement Learning Algorithms forMDPs2011
- Performance comparison of routing protocols for ad hoc networks2004
- Mobilized ad-hoc networks: a reinforcement learning approach2004
- A performance comparison of multi-hop wireless ad hoc network routing protocols1998
- No free lunch theorems for optimizationIEEE Transactions on Evolutionary Computation, 1997