Efficient routing protocols are required in opportunistic networks due to the inherent challenges of sporadic connectivity, transmission delays, and dynamic network topologies. In these networks, information is forwarded and disseminated among smart devices based on opportunistic contacts driven primarily by network dynamics and user mobility. This paper introducesLearnRouter, a dynamic reinforcement learning-based routing algorithm designed to improve the message delivery ratio while minimizing end-to-end delay in opportunistic networks. Existing routing protocols use static strategies or fixed replication schemes, leading to resource utilization and high message drop rates. LearnRouter addresses these challenges by incorporating the multi-armed bandit framework and utilizing the Upper Confidence Bound algorithm to make more intelligent and data-driven forwarding decisions. The proposed approach enables the protocol to adapt continuously to network changes while balancing the trade-off between exploration and exploitation. The simulation results show that LearnRouter surpasses end-to-end delay and message delivery ratio in comparison with Direct Delivery, Spray and Wait, CBR, SimRouter, RL-Prophet, and K-DQLR in opportunistic and dynamic environments.

With an increasing demand for IoT applications, powering these nodes has become challenging. Delivering power to IoT nodes with energy harvesting is a promising solution. Solar, among many harvesting approaches, is emerging for both indoor and outdoor applications. However, most of the published solutions with solar harvesting are single-node solutions for short and long-range communication. The primary challenge for developing scalable and self-configurable sustainable networks is the intermittent operation of the IoT nodes due to the non-availability of required power. In this paper, we demonstrate a cost-efficient solar-powered multi-hop self-configurable sensor network for future IoT applications. One of our proposed solutions can harvest 420 mW power and hence can support multiple sensors as well; however, it does not store any power. Another design is more stable with an onboard supercapacitor but can harvest a max of 80 mW. Both of these solutions are able to power nodes continuously in outdoor settings and hence develop a scalable network. We also propose a compact, cost-effective, rugged version of the solar-powered IoT sensor node.