The demand for wireless services and ubiquitous access is increasing exponentially. The fifth generation~(5G) cellular network is introduced and successfully implemented to support the increased data demand. To that end, 5G considered a massive deployment of small cells as a key technique. Hence, the future network is expected to be a highly dense heterogeneous network. However, an ultra-dense deployment of small cells brings great challenges to network operation and management. With an increased number of low-power small-cell base stations, the network structure becomes increasingly complex, and energy consumption will increase dramatically. Studies have shown that wireless networks have a contribution of approximately 2\% to the total amount of CO2 emissions. In particular, 70-80\% of the total energy in wireless networks is consumed for the sake of base station~(BS) operation and management. Therefore, a flexible small cell operation strategy is required for the enhancement of energy efficiency in ultra-dense cellular networks. In this project, we are working to develop a dynamic small cell sleep mode switching algorithm for ultra-dense cellular networks. to improve the energy efficiency of the networks. We will follow a data driven approach considering machine learning techniques. For simulation of network scenarios, we will consider ns3 and MATLAB.
Partnerships
