Energy-Efficient and QoS-Aware Data Transfer in Q-Learning-Based Small-World LPWANs

The widespread use of the Internet of Things (IoT) necessitates large-scale communication among smart IoT devices (IoDs) across a wide geographical area. However, due to the limited radio range and scalability issues of traditional wireless sensor networks, wide-area communication among IoDs is not feasible. As a solution, a low-power wide-area network (LPWAN) is emerging as one of the techniques that can provide long-range communication with minimal power consumption. Nevertheless, the direct data transmission approach will no longer be viable due to its short network lifetime. As such, multihop data routing strategies for LPWANs are proposed in the literature. However, multihop data transmission has several challenges, including increased data latency, energy imbalance, poor bandwidth utilization, and low data throughput. To address these challenges, we propose a novel method that uses the machine learning technique for an energy-efficient and Quality-of-Service (QoS)-aware data transfer based on a recent breakthrough in social networks known as small-world characteristics (SWC). The network having SWC (i.e., low average path length and high average clustering coefficient) uses long-range links to reduce the number of intermediate hops for data transmission. In particular, a Q-learning framework is utilized for introducing optimal long-range links between the selected IoDs, resulting in the development of a small-world LPWAN (SW-LPWAN). Furthermore, the performance of the proposed method is computed in terms of energy efficiency and QoS. Moreover, the results are compared with existing data routing techniques, such as low-energy adaptive clustering hierarchy (LEACH), modified LEACH, conventional multihop, and direct data transmission. Specifically, the proposed method maintains 29% more alive nodes, 18% higher residual energy, and 22% higher data throughput compared to the second-best-performing method. As such, the obtained experimental results validate that the proposed method outperforms other existing methods in the context of energy consumption and QoS.