Project description
Deep learning for next-generation intelligent wireless solutions
On the eve of 5G and the beyond-5G wireless networks, there are several problems that must be resolved. There is a need for ultra-high data rates to serve a huge number of devices. Ultra-reliable, low-latency communications and energy efficiency are also necessary. The EU-funded IUCCF project aims to design intelligent cellular wireless data networks by engaging a deep learning approach. The researcher will upgrade the traditional massive MIMO concept (sending and receiving multi-data signal over a radio channel with a multipath propagation) with antennas in the form of a simple access point (AP) as well as unmanned aerial vehicles (UAVs). The project will adopt machine learning tools, distributed optimisation and statistical signal processing.
Objective
IUCCF is a 24-months research project focusing on the intelligent design of future cellular wireless data networks. The project leverages on the concepts of ultra-dense network deployments, cloud-based implementations of radio access networks, and of cell-free, user-centric architecture. The aim is to be able to cope with the difficult challenges of future 5G and beyond-5G wireless networks, which will be required to provide ultra-high data-rates, to support a very large number of devices, to provide ultra-reliable and low-latency communications to specific applications, and to operate with the highest levels of energy efficiency. The project will explore the potentialities of the user-centric cell-free massive MIMO concept, where the antennas are distributed, in the form of simple access points (APs), in the service area instead of being collocated at a cell-center. In addition to the use of fixed APs (FAPs), as in traditional cell-free massive MIMO system, the project will introduce also moving APs in the form of unmanned aerial vehicles (UAVs). This scenario poses many issues related to network management and resource allocation schemes that should be considered.
During the project, the ER will learn and adopt tools from machine learning, distributed optimization and statistical signal processing to optimize and add intelligence at both network core and edge in order to tackle the challenges of such a distributed autonomous system.
The project will be carried out by the ER at the University of Cassino and Lazio Meridionale (Italy), under the supervision of Prof. Stefano Buzzi. Furthermore, Nokia Bell-Labs Research Center in Dublin (Ireland) will host the ER for a six-months secondment. The applying ER is Dr. Mohamed Elwekeil, currently a post-doctoral researcher at the college of information engineering, Shenzhen University, China.
Fields of science
- engineering and technologyelectrical engineering, electronic engineering, information engineeringinformation engineeringtelecommunicationstelecommunications networksmobile network5G
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringsignal processing
- engineering and technologyelectrical engineering, electronic engineering, information engineeringinformation engineeringtelecommunicationstelecommunications networksdata networks
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringroboticsautonomous robotsdrones
- natural sciencescomputer and information sciencesartificial intelligencemachine learningdeep learning
Keywords
Programme(s)
Funding Scheme
MSCA-IF - Marie Skłodowska-Curie Individual Fellowships (IF)Coordinator
03043 Cassino
Italy