Deep Q-Learning Driven Protocol for Enhanced Border Surveillance with Extended Wireless Sensor Network Lifespan

Wireless Sensor Networks (WSNs) play a critical role in automated border surveillance systems, where continuous monitoring is essential. However, limited energy resources in sensor nodes lead to frequent network failures and reduced coverage over time. To address this issue, this paper presents an innovative energy-efficient protocol based on deep Q-learning (DQN), specifically developed to prolong the operational lifespan of WSNs used in border surveillance. By harnessing the adaptive power of DQN, the proposed protocol dynamically adjusts node activity and communication patterns. This approach ensures optimal energy usage while maintaining high coverage, connectivity, and data accuracy. The proposed system is modeled with 100 sensor nodes deployed over a 1000 m 1000 m area, featuring a strategically positioned sink node. Our method outperforms traditional approaches, achieving significant enhancements in network lifetime and energy utilization. Through extensive simulations, it is observed that the network lifetime increases by 9.75%, throughput increases by 8.85% and average delay decreases by 9.45% in comparison to the similar recent protocols. It demonstrates the robustness and efficiency of our protocol in real-world scenarios, highlighting its potential to revolutionize border surveillance operations.