A machine learning based algorithm for joint improvement of power control, link adaptation, and capacity in beyond 5G communication systems

Wireless sensor networks (WSNs) require optimized energy consumption and an improved packet delivery ratio (PDR) for optimal performance. Clustering and routing strategies are frequently used to reduce energy usage, while multiradio (MR) multichannel (MC) systems improve PDR levels. Transmission power control (TPC) features in both energy consumption reduction and PDR improvement. While the mentioned techniques are used in previous studies, they were investigated separately and without a holistic approach. This study discusses the challenge of obtaining high‐PDR, energy‐efficient, and cost‐effective clustering and routing in WSNs. As a means of reducing deployment costs, a heterogeneous setting with energy‐constraint normal sensors for environmental monitoring as well as some high‐energy, TPC‐enabled, MR super nodes is assumed. The super nodes are considered as CHs and are responsible for collecting the sensed data from the normal sensors. Installing additional radios on super nodes enables static channel assignment (CA), which yields high PDR with low imposed overhead on the network. The mentioned TPC‐based MC heterogeneous setting, which yields cost‐effectiveness, high PDR, and energy efficiency, was not investigated in previous studies. The considered problem is decoupled into two phases of configuring the super nodes and normal sensors, which are solved using the grey wolf optimization (GWO) algorithm. The performed simulations show an average improvement of our proposed algorithm in PDR, energy consumption, consumed energy per delivered bit, and network lifetime by 9%, 30%, 65%, and 44%, respectively.

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

A machine learning based algorithm for joint improvement of power control, link adaptation, and capacity in beyond 5G communication systems

Cited by 2 publications

References 67 publications

Deep Reinforcement Learning Based Link Adaptation Technique for LTE/NR Systems

Deep Reinforcement Learning Based Link Adaptation Technique for LTE/NR Systems

Cost‐Efficient Network Design in Multichannel WSNs With Power Control: A Grey Wolf Optimization Approach to Routing and Clustering

Contact Info

Product

Resources

About