LCEMILCP: Design of a Low-complexity Energy Harvesting Model Via Incremental Learning and Continuous Power Quality Optimization Process in Wsn

Dr. (Mrs.) Jaya Dipti Lal

doi:10.36948/ijfmr.2024.v06i01.13345

LCEMILCP: Design of a Low-complexity Energy Harvesting Model Via Incremental Learning and Continuous Power Quality Optimization Process in Wsn

Author(s)	Dr. (Mrs.) Jaya Dipti Lal
Country	India
Abstract	Optimization of energy harvesting requires design of low complexity & high efficiency models that can work with maximum power gain levels. To design such models, researchers have proposed multiple techniques, that can assist in improving power quality via selection of optimum harvesting sources in multisource environments. But these models require continuous reconfiguration of static rules, which limits their efficiency when applied to large-scale network scenarios. Moreover, most of these models also showcase higher complexity due to reconfiguration, which reduces their scalability performance. To overcome this limitation, a novel Low-Complexity Energy Harvesting Model via Incremental Learning and Continuous Power Quality Optimization process is discussed in this text. The proposed model initially uses a Q-Learning based power evaluation method, that is capable of generating high-efficiency configurations of multisource harvesting devices. This is cascaded with design of a Particle Swarm Optimizer (PSO), that assists in performing continuous power quality optimizations. The combined model is capable of selecting hybrid harvesting source configurations, and incrementally tune it for optimum harvesting performance. This is achieved via modelling a reward function that incorporates power gain along with low-complexity source selection process. The selection process is further enhanced via PSO based continuous learning for improving harvesting source configurations. The proposed model was tested on a wide variety of network scenarios, and its QoS efficiency levels were compared with different state-of-the-art methods. Based on this comparison, it was observed that the proposed model is capable of improving power gain by 8.3%, while minimizing harvesting delay by 6.5%, and improving harvesting throughput by 5.9%, which makes it useful for large-scale multisource harvesting applications.
Keywords	Energy, Harvesting, Multisource, Throughput, Delay, Power, Gain, PSO, Q-Learning, Configurations
Field	Engineering
Published In	Volume 6, Issue 1, January-February 2024
Published On	2024-02-11
Cite This	LCEMILCP: Design of a Low-complexity Energy Harvesting Model Via Incremental Learning and Continuous Power Quality Optimization Process in Wsn - Dr. (Mrs.) Jaya Dipti Lal - IJFMR Volume 6, Issue 1, January-February 2024. DOI 10.36948/ijfmr.2024.v06i01.13345
DOI	https://doi.org/10.36948/ijfmr.2024.v06i01.13345
Short DOI	https://doi.org/gthqm8

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 6 Isu 6 Cover Page Vol 6 Isu 5 Cover Page Vol 6 Isu 4

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-5948-55	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

LCEMILCP: Design of a Low-complexity Energy Harvesting Model Via Incremental Learning and Continuous Power Quality Optimization Process in Wsn

Share this