Scholarlink

Abstract <p>Wireless Sensor Networks (WSNs) are increasingly vital in a wide range of real-time applications, yet their efficiency remains constrained by energy limitations and routing inefficiencies. Energy efficiency is a complex consideration in the architecture of WSN. This study presents a Modified Rendezvous Point Selection Scheme (MRPSS) enhanced by three nature-inspired optimization algorithms–Salp Swarm Algorithm (SSA), Flower Pollination Algorithm (FPA), and African Vulture Optimization (AVO)–to address these challenges. The methods presented in this study aim to optimize energy efficiency and network latency to extend network lifetime. AVO demonstrates superior performance in terms of remaining network energy with average improvements of 16-20% as compared to other algorithms for the number of rounds and about 4% better than others with respect to node density. Additionally, the study applies Robust Linear Regression (RLR) models to accurately predict network energy, enabling efficient resource forecasting with minimal computational overhead. Simulation results validate the effectiveness of the optimization framework followed by ML approach for future energy-aware WSN deployments. This dual-pronged strategy showcases the potential of combining metaheuristic optimization with predictive modeling for intelligent WSN management.</p> Graphic Abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Energy-Efficient Routing in Wireless Sensor Networks via Nature-Inspired Algorithms and Robust Regression-Based Forecasting

  • 期刊论文

  • 发表日期：

    2026年6月30日

查看全文
  • Tigmanshu Patel,
  • Brijesh Kundaliya,
  • Hiren Mewada,
  • Upesh Patel,
  • Sarman Hadia

摘要

Abstract

Wireless Sensor Networks (WSNs) are increasingly vital in a wide range of real-time applications, yet their efficiency remains constrained by energy limitations and routing inefficiencies. Energy efficiency is a complex consideration in the architecture of WSN. This study presents a Modified Rendezvous Point Selection Scheme (MRPSS) enhanced by three nature-inspired optimization algorithms–Salp Swarm Algorithm (SSA), Flower Pollination Algorithm (FPA), and African Vulture Optimization (AVO)–to address these challenges. The methods presented in this study aim to optimize energy efficiency and network latency to extend network lifetime. AVO demonstrates superior performance in terms of remaining network energy with average improvements of 16-20% as compared to other algorithms for the number of rounds and about 4% better than others with respect to node density. Additionally, the study applies Robust Linear Regression (RLR) models to accurately predict network energy, enabling efficient resource forecasting with minimal computational overhead. Simulation results validate the effectiveness of the optimization framework followed by ML approach for future energy-aware WSN deployments. This dual-pronged strategy showcases the potential of combining metaheuristic optimization with predictive modeling for intelligent WSN management.

Graphic Abstract