Optimizing energy efficiency in 5G ultra-dense networks using distributed and cooperative learning model

Wireless traffic demands are on the rise and are expected to increase exponentially. Ultra-dense small cell network is a crucial design architecture for increasing network capacity, deliver high-speed and pervasive wireless services to billions of devices in 5G networks. Ultra-dense networks involve deploying a large number of small cells (femtocells) within the macrocells. The small cells are characterised by low power, short-range, and low cost resulting in numerous overlapping zones. This problem due to interference becomes significant in such an ultra-dense network. Furthermore, due to the high-density traditional centralised approach are inefficient. As the world pushes toward greener technology and minimises energy waste, energy efficiency in the wireless network has become of significant importance.

To overcome such challenges, cooperative and autonomous operation are required in 5G networks. Several solutions proposed in the literature are limited to addressing the cooperation problem for a centralised and homogenous cellular network. There have been limited studies on techniques for handling the density, sustainability, and dynamics of ultra-dense networks in a distributed manner as highlighted in our published paper [1]. Therefore, the objective is to propose a well-designed distributed cooperative mode that can realise the numerous gains offered by ultra-dense networks.

This research aims to address the issue using innovative resource management by combining Machine learning and Game
Theory. The outcome will be a novel framework for enabling self-organising energy-efficient ultra-dense networks. The proposed framework will be evaluated and benchmarked using numerical analysis and simulation. Enhancing the energy efficiency of the wireless network through proposed techniques will help reduce the carbon footprint.