2020/11/30 by Jessica Moysen, Furqan Ahmed, Moysen, Jessica +5 · 1 citation
Computer Science · Engineering · #Advanced MIMO Systems Optimization #FOS: Computer and information sciences #Networking and Internet Architecture (cs.NI) #Telecommunications and Broadcasting Technologies #Wireless Communication Networks Research
paper · pdf · doi:10.48550/arxiv.2011.14968
openalex publication_date 2020/11/30 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
The massive amount of data available in operational mobile networks offers an\ninvaluable opportunity for operators to detect and analyze possible anomalies\nand predict network performance. In particular, application of advanced machine\nlearning (ML) techniques on data aggregated from multiple sources can lead to\nimportant insights, not only for the detection of anomalous behavior but also\nfor performance forecasting, thereby complementing classic network operation\nand maintenance solutions with intelligent monitoring tools. In this paper, we\npropose a novel framework that aggregates diverse data sets (e.g.\nconfiguration, performance, inventory, locations, user speeds) from an\noperational LTE network and applies ML algorithms to diagnose network issues\nand analyze their impact on key performance indicators. To this end, pattern\nidentification and time-series forecasting algorithms are used on the ingested\ndata. Results show that proposed framework can indeed be leveraged to automate\nthe identification of anomalous behaviors associated with the spatial-temporal\ncharacteristics, and predict customer impact in an accurate manner.\n