PROJECT TITLE :
Cognitive Cellular Networks: A Q-Learning Framework for Self-Organizing Networks
Self-organizing networks (SON) aim at simplifying network management (NM) and optimizing network capital and operational expenditure through automation. Most SON functions (SFs) are rule-primarily based management structures, that evaluate metrics and judge actions primarily based on a collection of rules. These rigid structures are, but, terribly advanced to style since rules should be derived for every SF in every possible situation. In observe, rules only support generic behavior, which cannot reply to the precise scenarios in each network or cell. Moreover, SON coordination becomes very difficult with such varied management structures. In this paper, we have a tendency to propose to advance SON toward cognitive cellular networks (CCN) by adding cognition that allows the SFs to independently learn the specified optimal configurations. We propose a generalized Q-learning framework for the CCN functions and show how the framework fits to a general SF management loop. We tend to then apply this framework to 2 functions on mobility robustness optimization (MRO) and mobility load balancing (MLB). Our results show that the MRO operate learns to optimize handover performance while the MLB perform learns to distribute instantaneous load among cells.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here