Machine Learning and Bio-Inspired Deep Learning Approaches for Energy-Efficient and Secure Clustering and Routing in Wireless Sensor Networks:A Survey

Authors

  • S.Sumitha Pandit Author
  • Dr. A. Vijaya Author

Keywords:

wireless sensor networks; cluster-head election; energy-hole problem; hotspot mitigation; ant colony optimization; grey wolf optimizer; reinforcement learning; deep Q-network; LSTM; autoencoder; trust management; intrusion detection.

Abstract

Wireless Sensor Networks (WSNs) remain constrained by the finite battery energy of their constituent nodes, which makes energy-aware clustering and routing the central design problem of the field. Since the introduction of the Low-Energy Adaptive Clustering Hierarchy (LEACH) protocol, a large body of research has sought to improve cluster-head (CH) election and multi-hop routing along four broad lines: (1) geometry- and threshold based unequal clustering to counter the "hotspot" or energy-hole problem near the base station; (2) machine learning and metaheuristic CH election using k-means, fuzzy logic, particle swarm optimization (PSO), genetic algorithms (GA), and artificial neural networks; (3) bio-inspired swarm-intelligence routing using Ant Colony Optimization (ACO), the Grey Wolf Optimizer (GWO), and hybrid combinations of these and other nature inspired metaheuristics; and (4) reinforcement learning (RL) and deep learning approaches, including tabular Q learning, Deep Q-Networks (DQN), Long Short-Term Memory (LSTM) energy prediction, and autoencoder based anomaly detection for security. This survey reviews and synthesizes 71 peer-reviewed and preprint sources across these four lines, organizes them into a coherent taxonomy, and builds comparative tables of their clustering/routing mechanisms, evaluation scale, and reported performance gains. The review is deliberately structured to support a three-phase enhancement of an existing Energy-Efficient Machine-Learning-based Clustering and Routing (EEMLCR) protocol: a hotspot-aware adaptive CH scheduling phase, a bio-inspired ACO-GWO multi-objective routing phase, and a unified deep-learning phase combining LSTM-based proactive energy prediction, DQN-based routing, and autoencoder/trust-based security. The survey concludes by identifying three concrete gaps in the existing literature — the absence of a threshold-driven, TDMA-integrated hotspot recovery mechanism; the lack of a systematic ACO-explores/GWO-exploits routing pipeline validated at scale; and the absence of a single framework unifying proactive LSTM prediction, DQN routing, and trust cross-validated anomaly detection — that motivate the proposed enhancements.

Downloads

Download data is not yet available.

Downloads

Published

2026-09-22

How to Cite

Machine Learning and Bio-Inspired Deep Learning Approaches for Energy-Efficient and Secure Clustering and Routing in Wireless Sensor Networks:A Survey. (2026). Minimax Theory and Its Applications, 11(2s), 231-248. https://journalmta.com/index.php/jmta/article/view/411