Efficient routing remains the linchpin for achieving sustainable performance in Wireless Sensor Networks (WSNs) within the Internet of Things (IoT). However, traditional routing mechanisms increasingly struggle to cope with the growing complexity of network architectures, frequent changes in topology, and the dynamic behavior of mobile nodes. These issues contribute to data congestion, uneven energy consumption, and potential communication breakdowns, underscoring the urgency for optimized routing strategies. In this paper, we present a comprehensive review of over 100 studies of spanning conventional and AI-enhanced energy-efficient routing techniques. It covers diverse approaches, including metaheuristics, machine learning, reinforcement learning, and AI-based cross-layer methods aimed at improving the performance of WSN-IoT systems. The key limitations of existing solutions are discussed along with performance metrics such as scalability, energy efficiency, throughput, and packet delivery. We also highlight various research challenges and provide research directions for future exploration. By synthesizing current trends and gaps, we provide researchers and practitioners with a structured foundation for advancing intelligent, energy-conscious routing in next-generation IoT-enabled WSNs.
Thakur et al. (2025) studied this question.