TIIM: technology-independent interference mitigation for low-power wireless networks

Abstract

The rise of heterogeneity in wireless technologies operating in the unlicensed bands has been shown to adversely affect the performance of low-power wireless networks. Cross-Technology Interference (CTI) is highly uncertain and raises the need for agile methods that assess the channel conditions and apply actions maximizing communication success. In this paper, we present TIIM, a lightweight Technology-Independent Interference Mitigation solution that detects, quantifies, and reacts to CTI in realtime. TIIM employs a lightweight machine learning classifier to (i) decide whether communication is viable over the interfered link, (ii) characterize the ambient conditions and apply the best coexistence mitigation strategy. We present an in-depth experimental characterization of the effect of CTI on 802.15.4 links, which motivated and influenced the design of TIIM. Our evaluation shows that TIIM, while exposed to extensive and heterogeneous interference, can achieve a total PRR improvement of 30% with an additional transmission overhead of 5.6%.