Each speaker has been asked to take some time to generate some discussion, on top of the traditional questions from the audience.
10:00 - 10:45 : Presentation
Kinda Khawam (Associate Professor, UVSQ), on the subject “ Lightweight Learning for efficient resource allocation in LoRaWAN.
Abstract: For a seamless deployment of the Internet of Things (IoT), self-managing solutions are needed to overcome the challenges of IoT, including massive data pro- cessing and resource management in terms of calculation, memory and battery. One of the most promising solutions to these challenges is the use of artificial intelligence. This will enable IoT equipment to operate autonomously in a dynamic environment by using innovative and inherently distributed learning techniques, thus freeing IoT equipment from draining their limited energy by constantly communi- cating with a centralized controller. In particular, the work is applied to a specific context of the IoT, the LoRaWAN networks where the equipment communicates with the gateway (GW) via a distributed access with ALOHA type contention (without detection) and spread spectrum technology (CSS) by resorting to the Multi-armed bandit algorithm.
11:00 - 11:45 : Presentation
Bilal Maaz (Professor, CNAM, Lebanon), on the subject "Joint User Association, Power Control and Scheduling in Multi-Cell 5G Networks".
Abstract: We propose a unified framework to study the interplay of user association, scheduling and power allocation in heterogeneous cellular networks. In the existing multi-cell networks, multiple BSs use the same radio resources in a given operating area. The ensuing Inter Cell Interference harms the radio transmissions and degrades the performances. Thus, a certain degree of coordination between the BSs is required to manage the resources and minimize the interference level.