An Intelligent RL-Enable Energy Aware Routing for Wireless Sensor Networks

View at publisher Summarise with VIRAT
Authors: Sunandita Debnath, Kumar Vishant, Shashank Shekhar
Cited by: 0
References: 12

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Wireless sensor networks face significant challenges due to limited battery power, which restricts network lifetime. Traditional protocols such as LEACH and PEGASIS extend lifetime to some extent but lack adaptability under dynamic network conditions. Heuristic methods such as EER-RL offer improvements, yet they still strive to capture optimal long-term strategies. This research work proposes an EER-DQN, an energy-efficient routing protocol that formulates cluster head selection as a deep reinforcement learning problem to maximize network lifetime in energy-constrained network environments. The DQN model uses real-time network states (energy, distance, hop count) and employs experience replay with a fixed target network to ensure stable learning. Simulation results show that EER-DQN significantly outperforms existing protocols, extending the time to first node failure by approximately 275% compared to LEACH, 25% compared to PEGASIS, and 15% compared to EER-RL. Notably, by round 1000, while LEACH has consumed more than 75% of total network energy and PEGASIS around 25%, EER-DQN maintains a controlled consumption rate comparable to EER-RL, demonstrating that the DQN learns more effective load-balancing and node-preservation strategies to maximize overall network lifetime.

Fields of Study & Subjects

Energy Efficient Wireless Sensor Networks Security in Wireless Sensor Networks Mobile Ad Hoc Networks

Publication details

Journal / source
International Conference on Consumer Electronics
Pages
1–5
Publication date
3 February 2026
Language
EN