Towards Proactive Context-Aware Self-Healing for 5G Networks

Abstract

In this paper, we suggest a new research direction and a future vision for Self-Healing (SH) in Self-Organizing Networks (SONs). The problem we wish to solve is that traditional SH solutions may not be sufficient for the future needs of cellular network management because of their reactive nature, i.e., they start recovering after detecting already occurred faults instead of preparing for possible future faults in a pre-emptive manner. The detection delays are especially problematic with regard to the zero latency requirements of 5G networks. To address this problem, existing SONs need to be upgraded from reactive to proactive response. One of the dimensions in SH research is to employ more holistic context information that includes, e.g., user location and mobility information, in addition to traditional context information mostly gathered from sources inside the network. Such extra information has already been found useful in SH. In this paper, we suggest how user context information can not only be incorporated in SH but also how future context could be predicted based on currently available information. We present a user mobility case study as an example to illustrate our idea.