MINANI Frodouard - 21DOCS Test Area

MINANI Frodouard

PhD Student

Frodouard Minani received his Bachelor’s degree in Computer Science and Master’s degree from the School of Information and Communication Technology, College of Science and Technology, University of Rwanda, Kigali, Rwanda in 2014, and 2017 respectively. He is currently the Lecturer at University of Rwanda, College of Science and Technology. He is currently working toward his PhD degree at Osaka University, Graduate School of Information Science and Technology (DC2). In line with this, he received the award of Best Paper in 2023 14th International Conference on Mobile Computing and Ubiquitous Networking. He has supervised more than 10 projects of undergraduate students in the area of Computer networking, Software engineering and data communication. He has been working as intern in SI/IT GoR department in Korea Company named Africa Olleh Service (Aos Ltd) from 2014 to 2015. He has received the award as the best performer in the graduands of the University of Rwanda, College of Science and Technology in academic year 2014. His research interests include resource allocation for Non-Terrestrial Networks (NTNs), Machine Learning applied to NTNs, Deep Learning and Semantic Communications applied to wireless communication and NTNs.

Japan

Public Documents 1

QoSem-based Resource Allocation for Semantic Communication in NTN Downlinks

Frodouard Minani

and 5 more

February 27, 2025

Non-terrestrial networks (NTNs) are crucial for 6G communications but face challenges like classical communication bottlenecks. Semantic communication (SemCom) offers a solution, but efficient resource allocation remains unresolved. This paper proposes a joint approach for resource allocation and semantic information selection in low-earth orbit (LEO) satellitebased image transmission. A novel metric, Quality of Semantic (QoSem), is introduced to measure the SemCom performance. An optimization problem is formulated to maximize QoSem by allocating computing, power, and bandwidth resources and selecting optimal semantic information. Furthermore, we propose a novel deep reinforcement learning (DRL) algorithm, namely Mixed-Action Decision Intelligent Semantic-aware Soft-Actor Critic (MADIS-SAC), to handle the problem's nonconvexity and NP-hard complexity. Results show 82.5% of QoSem improvement compared to baselines under resource constraints.