Current students


ZHANG BIBOCycle: XXXIV

Section: Telecommunications
Advisor: FILIPPINI ILARIO
Tutor: CESANA MATTEO

Major Research topic:
Resource Management for Millimeter-Wave Access Networks Based on Artificial Intelligence

Abstract:
;
;
Millimeter wave (mmWave) communications have been introduced in the 5G standardization process due to their attractive potential to provide a huge capacity extension to traditional sub-6 GHz technologies. However, such high-frequency communications are characterized by harsh propagation conditions, thus requiring base stations to be densely deployed. Integrated access and backhaul (IAB) network architecture proposed by 3GPP is gaining momentum as the most promising and cost-effective solution to this need of network densification. IAB networks’ available resources need to be carefully tuned in a complex setting, including directional transmissions, device heterogeneity, and intermittent links with different levels of availability that quickly change over time. It is hard for traditional optimization techniques to provide alone the best performance in these conditions. We have investigated different scenarios, considering potential dynamic factors (e.g., random link blockages, users' mobility). We believe that Artificial Intelligence (AI) techniques can implicitly capture the regularities of environment dynamics and learn the best resource allocation strategy in networks affected by varying link availabilities and mobile users. In this thesis, we first propose hybrid approaches that incorporate Column Generation (CG) and Deep Reinforcement Learning (DRL) techniques to cope with the effects of the link blockages. Thereafter, we develop a multiagent reinforcement learning (MARL) based framework to tackle the dynamic topologies originated from users' mobility. Numerical results have demonstrated the effectiveness and advantages of AI-based approaches in addressing resource management in dynamic mmWawe access networks, compared with the traditional optimization or heuristic based approaches.
;
;