Softwarized and distributed learning for SON management systems

Abstract

Self-Organizing Networks (SON) functions have already proven to be useful for network operations. However, a higher automation level is required to make a network enabled with SON capabilities respond as a whole to the operator's objectives. For this purpose, a Policy Based SON Management (PBSM) layer has been proposed to manage the deployed SON functions. In this paper, we propose to empower the PBSM with cognition capability in order to manage efficiently SON enabled networks. We focus particularly on the implementation of such a Cognitive PBSM (C-PBSM) on a large scale network and propose a scalable approach based on distributed Reinforcement Learning (RL): RL agents are deployed on different clusters of the network. These clusters should be defined in such a way that the RL agents can learn independently. As the interaction between these clusters may evolve in time due for instance to traffic dynamics, we propose a flexible implementation of this C-PBSM framework with dynamic clustering to adapt to network's evolutions. We show how this flexible implementation is rendered possible under Software Defined Networks (SDN) framework. We also assess the performance of the proposed distributed learning approach on an LTE-A simulator.

A Survey of Networking Applications Applying the Software Defined Networking Concept Based on Machine Learning

“…Furthermore, RL with architecture changes are discussed, because of the complicated and dynamic network environment. Daher et al [43] proposed a scalable approach based on distributed RL in order to manage SON (Self-Organizing Networks) enabled networks efficiently.…”

Correlation-Based Feature Mapping of Crowdsourced LTE Data

“…Reasoning use cases considered in this thesis include the mapping of requests and SON function operations (CONTRIB1.1) and inference of LTE metric effect dependencies (CONTRIB1.2). With respect to the request-operation mapping, some previous efforts have focused on policy-based network management in SON environment [55,85,36,37,56]. Although these works share the idea of mapping human-defined objectives to SON function configurations, they neither consider semantic modelling nor logical reasoning that would facilitate the discovery and composition of SON function operations.…”

“…As a final suggestion for future work, the earlier work done in the policy-and objective-based SON management [55,53,85,36,37,56] as well as the intentbased networking concept [16] could be extended with semantic definitions of context-specific high-level goals in the networks. This research direction would also require a semantic modelling of context attributes and their relation to measurement patterns in order to define, what impacts a high-level goal in a certain situation will have.…”