Article citationsMore>>

Wu, J., Zhang, W. and Li, J. (2022) DeepRL-Routing: A Deep Reinforcement Learning-Based Geographic Routing Protocol for Wireless Sensor Networks. IEEE Access, 10, 74500-74513.

has been cited by the following article:

• TITLE: Energy-Efficient Geographic Routing with Obstacle Avoidance in Wireless Sensor Networks

  AUTHORS: Ahoua Cyrille Aka, Lagasane Ouattara Kra, Akanza Konan Ricky N’dri, Abdou Khadre Diop

  KEYWORDS: Wireless Sensor Networks, Geographic Routing, Obstacle Avoidance, Energy Optimization

  JOURNAL NAME: Journal of Sensor Technology, Vol.15 No.3, November 28, 2025

  ABSTRACT: Wireless sensor networks (WSNs) are essential in environmental, industrial, and urban monitoring applications. However, in hostile environments where communication is hampered by physical obstacles, traditional geographic routing protocols suffer from significant performance degradation. This paper presents OAGF (Obstacle-Aware Greedy Forwarding), a geographic routing protocol capable of obstacle avoidance while optimizing energy consumption and latency. OAGF combines an adaptation of Greedy Forwarding with mechanisms for obstacle detection, alternative route selection, and residual energy consideration. Simulations under OMNeT++/INET 4.4 demonstrate that OAGF reduces latency by an average of 31%, total energy consumption by 38%, and improves delivery rates by 7% compared to GARL and GEAR. These results show that OAGF is a robust and efficient approach for RCSF deployments in complex environments.