Recent Advances in an Optimized Causal Dilated Convolutional Neural Networks-Based Energy-Efficient and Delay-Sensitive Routing Paths Using Mobility Prediction in Mobile WSN: A Systematic Review

Abstract

Wireless Sensor Networks (WSNs) have become a fundamental component of modern communication systems, widely used in applications such as environmental monitoring, smart cities, industrial automation, and healthcare systems. However, Mobile WSNs (MWSNs) face significant challenges due to dynamic network topology, limited battery energy, and frequent node mobility, which complicate the design of efficient routing protocols. Traditional routing techniques often struggle to maintain stable communication and adapt to rapidly changing network conditions, leading to increased packet loss, delay, and energy consumption. In recent years, Artificial Intelligence (AI), particularly deep learning approaches such as causal dilated convolutional neural networks (CD-CNNs), has emerged as a promising solution to address these limitations. This systematic review examines AI-driven routing techniques with emphasis on energy efficiency, delay minimization, and mobility prediction in MWSNs. Hybrid deep learning models combining causal and dilated convolutions are highlighted for capturing short-term and long-term temporal dependencies in traffic and mobility patterns. CNNs, temporal convolutional networks, and attention mechanisms improve spatial-temporal feature extraction, enabling smarter routing decisions and efficient resource utilization. Mobility prediction further enhances reliability by anticipating node movement and reducing link breakage. Integration of predictive intelligence with routing protocols reduces latency, energy usage, and packet loss while improving delivery ratio.