CS Other Presentations
Besides Colloquiums, the Department of Computer Science at the University of Cyprus also holds Other Presentations (Research Seminars, PhD Defenses, Short Term Courses, Demonstrations, etc.). These presentations are given by scientists who aim to present preliminary results of their research work and/or other technical material. Other Presentations serve as a forum for educating Computer Science students and related announcements are disseminated to the Department of Computer Science (i.e., the csall list):RSS Directions
Presentations Coordinator: Demetris Zeinalipour
PhD Defense: A novel Distributed Artificial Intelligence framework with Machine Learning for 5G/6G communication, Mr. Iacovos Ioannou (University of Cyprus, Cyprus), Thursday, July 22, 2021, 10.00-11.00 EET.
The Department of Computer Science at the University of Cyprus cordially invites you to the PhD Defense entitled:
A novel Distributed Artificial Intelligence framework with Machine Learning for 5G/6G communication
Speaker: Mr. Iacovos Ioannou
New generation mobile networks, such as 5G and forthcoming 6G, face many technical challenges in reaching the very ambitious standards set forth by the research and industry community. In this thesis, aspired by the expected benefits of adopting Artificial Intelligence (AI) and Machine Learning (ML) approaches in 5G and 6G networks, we propose and implement a novel AI/ML-based Distributed AI (DAI) framework able to facilitate in achieving the ambitious goals set forth. The proposed DAI framework utilises Belief Desire Intention (BDI) agents extended with ML capabilities to better understand the surrounding environment to the agent and the ability to prioritise the order of execution of the Desires. We refer to these as BDIx agents. To illustrate the potential of the DAI framework, we focus on the aspect of Device to Device (D2D) communication in 5G and beyond networks. The main advantage of D2D communication is that it is not constrained by the licensed frequency bands and also it is transparent to the cellular network. By enabling this, improved spectral efficiency, energy efficiency, data rates, throughput, delay, interference and fairness can be achieved. Furthermore, through the specific example of Mode Selection in D2D 5G, we design and develop a detailed DAI framework plan (DAIS), discuss implementation complexities and technical aspects, and then implement the DAIS algorithm/Plan, executed by the BDIx agents. Extensive simulative evaluations, using metrics are carried out. Additionally, a comparative evaluation is performed against Distributed Sum Rate with global knowledge, as well as potentially competing techniques, such as Fuzzy ART, DBSCAN, G-MEANS and MEC, customised to the needs of D2D Communication. Overall, we demonstrate that the DAI framework can offer fast network control with less messaging exchange and reduced signalling overhead, fast decision making. Also, it can support self-healing mechanisms and collaboratively can act as a self-organising network. Furthrmore, it can capitalise on existing implementations (e.g., Artificial Neural Networks for tackling any other D2D Challenges or any other 5G and 6G challenges. Moreover, it can support mMTC and eMBB. Finally, it can be parametrised at any time by the telecom operator.
Iacovos Ioannou is a Ph.D. candidate at the Computer Science Department under the supervision of Dr. Andreas Pitsillides and Dr. Vasos Vassiliou. He has completed his undergraduate studies (B.Sc. in Computer Science) at the University of Cyprus (2006). He has also completed his postgraduate studies (M.Sc. in Computer Science) at the Open University of Cyprus (2017) with honors and distinction as top of his class. His research interests include mobile and wireless communications, next generation networks (5G/6G) and Device-to-Device (D2D) communications, using Artificial intelligence and Machine Learning techniques.
Due to the current covid-19 situation, the defence will be on-line only. For zoom link see above.
|Other Presentations Web: https://www.cs.ucy.ac.cy/colloquium/presentations.php
|Colloquia Web: https://www.cs.ucy.ac.cy/colloquium/