PIM detection in wireless networks as an anomaly detection problem

As the number of base stations keeps increasing due to ever-growing wireless services and pervasive connectivity, the cost of operation for network service providers rises proportionally. In addition, with the evolution of wireless technology and development of next generation networks such as 5G and 6G, network operators are expected to encounter more complex challenges soon. One such network issue is the Passive Inter-modulation (PIM) problem that is observed in both 4G and 5G networks. Although there is a significant body of work regarding PIM detection and cancellation methods, majority of such studies depend on hardware solutions and manual investigation by network engineers, which is costly in terms of time and labor. In this paper, we propose a time-series based anomaly detection method, for identifying PIM problems in network sites. The proposed solution utilizes a set of Key Performance Indicator (KPI) data of base stations, obtained from network management systems for a significantly long time interval, and detects possible PIM problems in a site without the need for a human-in-the-loop. We measure the performance of our solution, with the guidance of experienced network engineers, on our collected dataset.