2020/07/08 by Metin Öztürk, Ozturk, Metin, Attai Ibrahim Abubakar +9 · 2 citations
Engineering · #Advanced MIMO Systems Optimization #Advanced Wireless Communication Technologies #Advanced Wireless Network Optimization #FOS: Computer and information sciences #FOS: Electrical engineering #Networking and Internet Architecture (cs.NI) #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2007.04133
openalex publication_date 2020/07/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Ultra-dense deployments in 5G, the next generation of cellular networks, are\nan alternative to provide ultra-high throughput by bringing the users closer to\nthe base stations. On the other hand, 5G deployments must not incur a large\nincrease in energy consumption in order to keep them cost-effective and most\nimportantly to reduce the carbon footprint of cellular networks. We propose a\nreinforcement learning cell switching algorithm, to minimize the energy\nconsumption in ultra-dense deployments without compromising the quality of\nservice (QoS) experienced by the users. In this regard, the proposed algorithm\ncan intelligently learn which small cells (SCs) to turn off at any given time\nbased on the traffic load of the SCs and the macro cell. To validate the idea,\nwe used the open call detail record (CDR) data set from the city of Milan,\nItaly, and tested our algorithm against typical operational benchmark\nsolutions. With the obtained results, we demonstrate exactly when and how the\nproposed algorithm can provide energy savings, and moreover how this happens\nwithout reducing QoS of users. Most importantly, we show that our solution has\na very similar performance to the exhaustive search, with the advantage of\nbeing scalable and less complex.\n