Time series based approach for detecting Passive Intermodulation occurrences in cellular network

Ranjani, H.G.; Puthennurakel, Sleeba P; Brisebois, Arthur; Banerjee, Somnath; Umaashankar, Venkatesh

doi:10.1109/comsnets53615.2022.9668382

Cited by 3 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed solution is demonstrated on four different applications, including a time-series forecasting and anomaly detection. A similar approach is adopted by Ranjani et al in [15], where authors propose an ensemble technique consisting of time-series based ML, utilizing random forest models, and signal processing methods for automatically predicting PIM problems, for 4G and 5G networks sites in real-time. The proposed method also considers the KPis of neighbor cells while determining whether a cell suffers from PIM, to improve the accuracy of PIM detection.…”

Section: Related Workmentioning

confidence: 99%

PIM Detection in Wireless Networks as an Anomaly Detection Problem

Cantali

Deniz²,

Ozay³

et al. 2023

2023 International Balkan Conference on Communications and Networking (BalkanCom)

View full text Add to dashboard Cite

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 SG and 6G, network operators are expected to encounter more complex challenges soon. One such network issue is the Passive Intermodulation (PIM) problem that is observed in both 4G and SG 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.

show abstract

Section: Related Workmentioning

confidence: 99%