Enhanced recurrent attention-deep Q learning with optimal node constrains and effective penalty based model for data transmission scheduling on wireless sensor networks

Abstract

Effective scheduling of data transmission is critical to maximizing network performance and resource usage in the context of wireless sensor networks (WSNs). In order to improve the effectiveness of data transmission scheduling in wireless sensor networks (WSNs), this paper proposes a unique method called Recurrent Attention-Deep Q Learning with Optimal Node Constraints and Effective Penalty based WSN Scheduling (RA-DQL-ONC&EP). This technique performs dynamic scheduling of data transmission tasks considering energy consumption and network interference by combining a penalty-based model, optimal node limitations, and recurrent attention techniques. Simulation results show that the proposed approach performs remarkably well. With a 91.21% success rate, it also guarantees dependable data transport throughout the network. Additionally, the delay rate is reduced to 1.99%, demonstrating effective data transfer with low latency. It is an effective model, yet it uses 70% less energy than other models since it is energy-efficient. The algorithm’s performance is further demonstrated by throughput analysis, which shows a 72% throughput over 1,000 time steps. Based on enhanced reliability, efficiency, and energy conservation in network operations, our results highlight the potential of RA-DQL-ONC&EP as a promising approach for improving data transmission scheduling in WSNs. This optimized scheduling enhances network reliability, ensuring timely and accurate data delivery, which can support various applications such as environmental monitoring, healthcare systems, and smart city infrastructure, ultimately fostering societal well-being and progress. Additionally, the algorithm’s efficiency contributes to cost savings and resource conservation, making it a socially responsible choice for managing wireless sensor networks.