Machine Learning-Based Interference Mitigation in Long-Range Networks for High-Ceiling Smart Buildings

Abstract

Long-Range networks are increasingly used in smart spaces due to their ability to provide longer communication range while consuming low energy. To facilitate communication among different Long-Range nodes, a gateway is used. For instance, in smart buildings such as airports, railway stations, indoor stadiums, and auditoriums, sensory data from multiple sites are transferred to a base station through a Long-Range gateway. However, when multiple nodes transmit data simultaneously to the gateway, it generates network interference, especially in high-ceiling smart buildings where Long-Range nodes with sensors are attached to monitor the building's health. In this paper, we present a new method for identifying interfering Long-Range Nodes (LNs) in high-ceiling smart buildings using a classification model. Our approach involves gathering and analyzing network parameters, such as signal-to-noise ratio and received signal strength indicator, from the signals to extract features that the classifier uses for interference classification. The approach categorizes interference based on the number of interfering LNs, with each class representing a distinct number of interfering LNs. We also introduce a push-based mechanism to detect and adjust the power levels of faulty LNs, reducing interference. Our method is cost-effective as it is hardware-independent, making it feasible to implement on the LG platform. Finally, we present a dataset of network interference generated by varying the number of nodes, obstacles, and other parameters. We train the model on the generated dataset and evaluate its effectiveness using a test bed. The experimental results demonstrate that the approach can successfully identify interference nodes in a complex network.