Surrogate Model-Based Energy-Efficient Scheduling for LPWA-Based Environmental Monitoring Systems

The rapid development of the Internet of Things (IoTs) with newly proposed wireless communication technology has compactly generated connections between humans and the physical world. Beginning with research on wireless sensor networks, environmental monitoring research has currently developed into wider applications aiming to detect the world with multitudinous IoT technologies. Recently, low power wide area technologies have provided such benefits as longer communication range, larger network capacity, and low unit-price, providing more choices for managers to set up more detailed monitoring. However, the operational lives of battery-powered end-devices still hinder long-term monitoring. In this paper, we propose a decentralized framework for energy-efficient environmental monitoring considering both the operation cost and current computational capabilities of the end-devices. The core function is a low-complexity scheduling approach that can balance the monitoring performance and energy consumption for different environmental states. Driven by the prediction accuracy of the surrogate model, monitoring nodes are selected. Meanwhile, the energy consumption of the other nodes is saved. Simulation results demonstrate that the proposed monitoring system has high energy efficiency with acceptable performance. The battery life of the whole system can be prolonged by up to 136.22%.