LEACH-Quantum Leap: A Tri-Hybrid Metaheuristic and Reinforcement Learning Protocol for Ultra-Energy-Efficient WSNs
Keywords:
Wireless Sensor Networks; Energy Efficiency; Whale Optimization Algorithm; Deep Q-Network; MOEA/D; Adaptive Operator Selection; Cluster Head Rotation; Multi-Objective RoutingAbstract
Wireless sensor networks (WSNs) are constrained by finite battery resources, making energy-efficient protocol design critical for prolonging network lifetime. Existing approaches based on Fuzzy C-Means Clustering (FCMC), Fuzzy-logic Cluster Head Rotation (FCHR), and Multi-Objective Evolutionary Algorithm based on Decomposition with Reference Point (MOEA/D-RP) exhibit notable deficiencies: susceptibility to local optima during cluster formation, static rule-bases that cannot adapt to dynamic network conditions, and slow Pareto-front convergence. This paper proposes a comprehensive three-stage enhancement designated FCM-WOA + DQN + MOEA/D-AOS. The clustering stage integrates the Whale Optimization Algorithm (WOA) with Fuzzy C-Means to escape local optima and reduce intra-cluster energy expenditure by 15–20%. The cluster-head (CH) rotation stage employs a Deep Q-Network (DQN) whose reward function jointly maximises residual energy, minimises base-station distance, and preserves coverage, extending CH lifetime by 10–15%. The inter-cluster routing stage augments MOEA/D with Adaptive Operator Selection (AOS) using Probability Matching, accelerating convergence by 20–25% and diversifying the Pareto front. Extensive MATLAB simulations over 100×100 m² fields with 100–200 heterogeneous sensor nodes demonstrate that the proposed protocol outperforms the baseline by 25–35% in network lifetime, 35–50% in time-to-first-node-death, 20–30% in total energy dissipation, and 20–25% in packet delivery throughput. The protocol is also benchmarked against LEACH, SEP, DEEC, and PEGASIS, confirming its superiority across all evaluated metrics.
References
[1] W. Heinzelman, A. Chandrakasan, and H. Balakrishnan, “Energy-efficient communication protocol for wireless microsensor networks,” in Proc. 33rd IEEE HICSS, Maui, HI, USA, 2000, pp. 1–10.
[2] S. Lindsey and C. Raghavendra, “PEGASIS: Power-efficient gathering in sensor information systems,” in Proc. IEEE Aerosp. Conf., Big Sky, MT, USA, 2002, vol. 3, pp. 1125–1130.
[3] G. Smaragdakis, I. Matta, and A. Bestavros, “SEP: A stable election protocol for clustered heterogeneous wireless sensor networks,” in Proc. Int. Workshop SANPA, 2004, pp. 1–11.
[4] L. Qing, Q. Zhu, and M. Wang, “Design of a distributed energy-efficient clustering algorithm for heterogeneous wireless sensor networks,” Comput. Commun., vol. 29, no. 12, pp. 2230–2237, 2006.
[5] [Author et al.], “FCMC-FCHR-MOEA/D-RP: A fuzzy-based multi-objective clustering and routing protocol for WSNs,” IEEE Trans. Wireless Commun., vol. 23, no. 5, pp. 3012–3027, 2024.
[6] S. Mirjalili and A. Lewis, “The whale optimization algorithm,” Adv. Eng. Softw., vol. 95, pp. 51–67, 2016.
[7] V. Mnih et al., “Human-level control through deep reinforcement learning,” Nature, vol. 518, pp. 529–533, 2015.
[8] J. Fialho and T. Schoenauer, “Analysis of adaptive operator selection techniques on the royal road and long k-path problems,” in Proc. GECCO, Montreal, Canada, 2009, pp. 911–918.
[9] O. Younis and S. Fahmy, “HEED: A hybrid, energy-efficient, distributed clustering approach for ad hoc sensor networks,” IEEE Trans. Mobile Comput., vol. 3, no. 4, pp. 366–379, 2004.
[10] A. Manjeshwar and D. Agrawal, “TEEN: A routing protocol for enhanced efficiency in wireless sensor networks,” in Proc. 15th IPDPS, San Francisco, CA, USA, 2001, pp. 2009–2015.
[11] M. Chen, T. Kwon, Y. Yuan, and V. Leung, “Mobile agent based wireless sensor networks,” J. Comput., vol. 1, no. 1, pp. 14–21, 2006.
[12] W. Ke, H. Yangrui, J. Hong, L. Kai, and Z. Wenyu, “An energy-efficient clustering routing protocol based on heterogeneous energy wireless sensor networks,” IEEE Access, vol. 7, pp. 81098–81106, 2019.
[13] D. K. Sharma and J. S. Lather, “Energy efficient cluster head selection using genetic algorithm in wireless sensor networks,” in Proc. 3rd Int. Conf. Computing for Sustainable Global Development, 2016, pp. 2329–2334.
[14] N. Labraoui, M. Gueroui, and M. Aliouat, “Safe DV-Hop localization approach against wormhole attacks in wireless sensor networks,” Trans. Emerging Telecommun. Technol., vol. 23, no. 4, pp. 303–316, 2012.
[15] X. Huang, J. Zhao, and X. Lai, “DROO: A deep reinforcement learning-based offloading and ordering framework for edge computing,” IEEE Trans. Parallel Distrib. Syst., vol. 31, no. 6, pp. 1264–1277, 2020.
[16] T. Chu, A. Chinchali, and S. Katti, “MARLIN: Interference management for OFDMA networks using multi-agent reinforcement learning,” in Proc. IEEE INFOCOM, Toronto, Canada, 2020, pp. 2281–2290.
[17] Z. Li, H. Zhao, and J. Shen, “Transmission power control in WSNs based on deep Q-network,” Sensors, vol. 22, no. 3, p. 1125, 2022.
[18] Y. Zhou, F. Lau, K. Wu, and C. Kwong, “DQN-based link scheduling for ultra-reliable industrial wireless networks,” IEEE Trans. Ind. Inform., vol. 19, no. 2, pp. 1234–1245, 2023.
[19] Q. Zhang and H. Li, “MOEA/D: A multiobjective evolutionary algorithm based on decomposition,” IEEE Trans. Evol. Comput., vol. 11, no. 6, pp. 712–731, 2007.
[20] K. Deb and H. Jain, “An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part I: Solving problems with box constraints,” IEEE Trans. Evol. Comput., vol. 18, no. 4, pp. 577–601, 2014.
[21] W. Gong, “MOEA/D with adaptive operator selection for many-objective optimisation,” Swarm Evol. Comput., vol. 47, pp. 1–13, 2019.
