Learning-Based Resource Management for Low-Power and Lossy IoT Networks

Abstract

Internet of Things (IoT) networks are key to the realization of modern industries and societies. A key application of IoT is in smart-grid communications. Smart-grid networks are resource constrained in terms of computing power and energy capacity. Similarly, the wireless links between devices are typically associated with high packet-loss rates, low throughput, and instability. To provide a sustainable communication mechanism, an IoT network stack is proposed for these devices. However, each network stack layer has its own constraints. For example, to facilitate the operation of these low-power and lossy network (LLN) devices, the international engineering task force (IETF) standardized a network-layer protocol called a routing protocol for low-power and lossy networks (RPLs). RPL often creates an inefficient network in densely deployed and varying traffic load conditions. Future dense IoT-based networks are expected to automatically optimize the reliability and efficiency of communication by inferring the diverse features of both the environments and actions of the devices. Machine learning (ML) provides a promising framework for such a dense network environment. In this study, we examine the underlying perspective of ML for such systems. We utilize the multiarmed bandit (MAB)-based expected energy count (BEEX) technique, which provides nodes the ability to effectively optimize their operation. Using the proposed mechanism, nodes can intelligently adapt their network-layer behavior. The performance of the proposed (BEEX) algorithm is evaluated through a Contiki 3.0 Cooja simulation. The proposed method improves the energy consumption and packet delivery ratio and produces a lower control overhead than other state-of-the-art mechanisms.