The rapid proliferation of wireless networks poses a great challenge to effective coexistence management amongst a plethora of wireless communication protocol users that are co-located and contending for the ever-scarce spectrum available. In particular, low-powered ad-hoc networks such as WSNs which are an integral part of the Internet of Things (IoT) and Industrial Internet of Things (IIoT) landscape, will be highly susceptible to cross-technology interference. This jeopardizes the envisaged performance and reliability of IoT and IIoT applications comprising many safety and mission-critical applications. For effective spectrum utilization and optimum performance of existing wireless networks and the realization of new wireless networks, coexistence management of the wireless spectrum is the key to ensuring the optimal performance of multiple wireless networks operating in close proximity.
We propose a two-step approach to attaining coexistence starting with wireless interference identification as spectrum awareness would be of keen importance in identifying concurrent transmission and subsequently applying suitable interference mitigation techniques to ensure coexistence and prevent communication blackout.
Our work uses deep learning to identify the presence of WSN, WiFi and Bluetooth single-label signals. Furthermore, we aim to identify multi-label concurrent signal transmissions that are significant in the context of interference management.
Moreover, a wireless coexistence management framework for WSNs is proposed which is an interference-aware and coexistence-friendly modification inspired by the WSN LEACH architecture that uses the proposed wireless interference identification for detection of the type of interference and the affected nodes. Depending upon the interference type, the coexistence framework assigns specific countermeasures that best counter the interference with good throughput and optimal energy consumption. In this work, we have proposed a coping mechanism against WiFi interference using an adaptive backoff time period and an in-depth study of the node interference levels