Abstract: In wireless networks, edge nodes are the base stations who are directly connected to users. In the recent years, the statistics have revealed the cause of backhaul and fronthaul congestion is due to the users’ repetitive demands of the popular (e.g. multimedia) content. Moreover, the data limits provided by the network operators are not enough for sustainable data and its rates required for a multimedia content. Therefore, next generation networks are being evolved based on edge caching, where popular contents are placed in edge nodes for scalable and quick access to a large number of users, and the cache storage is updated regularly.
Further, since popularity of different contents changes over time, a dynamic caching scheme based on assessing future and present popularities are preferable. In this context, the machine learning approaches are investigated. However, due to huge number of contents over the internet, we present scalable online learning solutions, which includes reinforcement learning and its function approximated learning approaches as well.
Duration: 3 hours
Names of the Presenters: Navneet Garg and Tharmalingam Ratnarajah.
Designation and Affiliation: Post-doctoral research associate (PDRA) and Professor, 1.14, Alexander Graham Bell building, Institute of Digital Communications, School of Engineering, The University of Edinburgh, Edinburgh, EH9 3FG, UK.
Navneet Garg received the B.Tech. degree in electronics and communication engineering from College of Science & Engineering, Jhansi, India, in 2010, and the M.Tech. degree in digital communications from ABV-Indian Institute of Information Technology and Management, Gwalior, in 2012. He has completed the Ph.D. degree in June 2018 from the department of electrical engineering at the Indian Institute of Technology Kanpur, India. From July 2018-Jan 2019, he visited The University of Edinburgh, UK. From February 2019-2020, he is employed as a research associate in Heriot-Watt university, Edinburgh, UK. Since February 2020, he is working as a research associate in The University of Edinburgh, UK. His main research interests include wireless communications, signal processing, optimization, and machine learning.
Tharmalingam Ratnarajah is currently with the Institute for Digital Communications, the University of Edinburgh, Edinburgh, UK, as a Professor in Digital Communications and Signal Processing. He was a Head of the Institute for Digital Communications during 2016-2018. His research interests include signal processing and information theoretic aspects of beyond 5G wireless networks, full-duplex radio, mmWave communications, random matrices theory, interference alignment, statistical and array signal processing and quantum information theory. He has published over 400 publications in these areas and holds four U.S. patents. He has supervised 16 PhD students and 21 post-doctoral research fellows and raised $11+ million USD of research funding. He was the coordinator of the EU projects ADEL (3.7M €) in the area of licensed shared access for 5G wireless networks, HARP (4.6M €) in the area of highly distributed MIMO, as well as EU Future and Emerging Technologies projects HIATUS (3.6M €) in the area of interference alignment and CROWN (3.4M €) in the area of cognitive radio networks. Dr Ratnarajah was an associate editor IEEE Transactions on Signal Processing, 2015-2017 and Technical co-chair, The 17th IEEE International workshop on Signal Processing advances in Wireless Communications, Edinburgh, UK, 3-6, July 2016. Dr Ratnarajah is a Fellow of Higher Education Academy (FHEA).