Deep Learning and Optimization Approaches in Optimized Causal Dilated Convolutional Neural Networks-Based Energy-Efficient and Delay-Sensitive Routing Paths Using Mobility Prediction in Mobile WSN: A Review

Abstract

Wireless Sensor Networks (WSNs), particularly mobile WSNs, are integral components of modern Internet of Things (IoT) applications such as smart cities, healthcare, and environmental monitoring. However, energy efficiency and delay-sensitive routing remain major challenges due to dynamic topology, limited battery power, and frequent node mobility. Recent advances in deep learning, especially Causal Dilated Convolutional Neural Networks (CDCNNs), have shown promising capabilities in capturing temporal dependencies and improving routing decisions through mobility prediction. This review explores deep learning and optimization approaches applied to energy-efficient and delay-sensitive routing in mobile WSNs. It focuses on the integration of CDCNN, reinforcement learning, and hybrid optimization techniques to enhance routing performance. Additionally, it discusses how mobility prediction improves network lifetime, reduces latency, and ensures reliable communication. The study synthesizes recent works, highlighting their methodologies, advantages, and limitations. The review also identifies key research gaps, including scalability, real-time adaptability, and computational overhead. Finally, it outlines future research directions such as lightweight deep learning models and cross-layer optimization strategies. This paper provides a comprehensive foundation for researchers working on intelligent routing in mobile WSN environments.