Towards automatic troubleshooting for user-level performance degradation in cellular services

Abstract

Troubleshooting cellular service issues at the per-UE (User Equipment) level is an essential task for cellular providers. However, diagnosing service issues at per-UE level is costly because it requires advanced expertise and in-depth inspection of massive network log data. This paper presents NeTExp, a generic and comprehensive data-driven approach to automatically troubleshoot cellular service issues reported by customers. NeTExp determines whether the root cause of a user-reported service issue is from the network side or the device side through deep neural networks, which extract complex spatial-Temporal feature profiles from massive network log data. The system is trained and validated using an extensive period of network and customer care data from a major cellular service provider in United States. We also present a case study on an external event that caused cellular service issues in 2020 to demonstrate the effectiveness of NeTExp on detecting network issues and identifying network-issue-related root causes at per-UE level.