Deep Learning Based Link Failure Mitigation

Abstract

Link failure is a cause of a major concern for network operators in enhancing user experience in present system and upcoming 5G systems as well. There are many factors which can cause link failures, for example Handover (HO) failures, poor coverage and congested cells. Network operators are constantly improving their coverage qualities to overcome these issues. However reducing the link failures needs further improvements for the present and next generation (5G) systems. In this paper, we study applicability of Machine Learning (ML) algorithms to reduce link failure at handover. In the method proposed, Signal conditions (RSRP/RSRQ) are continuously observed and tracked using Deep Neural Networks such as Recurrent Neural Network (RNN) or Long Short Term Memory network (LSTM) and thus behavior of these signal conditions are taken as inputs to another neural network which acts as a classifier classifying event in either HO fail or success in advance. This advance in decision allows UE to take action to mitigate the possible link failure. Algorithms and model proposed in this paper are first of its kind connecting the link between past signal conditions and future HO result. We show the performance of the proposed algorithms for both system simulated and field log data. Given the need for more proactive role of UE in most of the link level decision in 5G systems, algorithms proposed in this paper are more relevant.