eduzhai > Applied Sciences > Engineering >

Energy Optimization in Ultra-Dense Radio Access Networks via Traffic-Aware Cell Switching

  • king
  • (0) Download
  • 20210505
  • Save

... pages left unread,continue reading

Document pages: 30 pages

Abstract: Ultra-dense deployments in 5G, the next generation of cellular networks, arean alternative to provide ultra-high throughput by bringing the users closer tothe base stations. On the other hand, 5G deployments must not incur a largeincrease in energy consumption in order to keep them cost-effective and mostimportantly to reduce the carbon footprint of cellular networks. We propose areinforcement learning cell switching algorithm, to minimize the energyconsumption in ultra-dense deployments without compromising the quality ofservice (QoS) experienced by the users. In this regard, the proposed algorithmcan intelligently learn which small cells (SCs) to turn off at any given timebased on the traffic load of the SCs and the macro cell. To validate the idea,we used the open call detail record (CDR) data set from the city of Milan,Italy, and tested our algorithm against typical operational benchmarksolutions. With the obtained results, we demonstrate exactly when and how theproposed algorithm can provide energy savings, and moreover how this happenswithout reducing QoS of users. Most importantly, we show that our solution hasa very similar performance to the exhaustive search, with the advantage ofbeing scalable and less complex.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...