Year: 2021
Type: report
Abstract: This deliverable gives the results of the ARIADNE project's Task 4.2: Machine Learning based network intelligence. It presents the work conducted on various aspects of network management to deliver system level, qualitative solutions that leverage diverse machine learning techniques. The different chapters present system level, simulation and algorithmic models based on multi-agent reinforcement learning, deep reinforcement learning, learning automata for complex event forecasting, system level model for proactive handovers and resource allocation, model-driven deep learning-based channel estimation and feedbacks as well as strategies for deployment of machine learning based solutions. In short, the D4.2 provides results on promising AI and ML based methods along with their limitations and potentials that have been investigated in the ARIADNE project.\n\n
Authors: Di Renzo, Marco, Qian, Xuewen, Hrasnica, Halid, Katzouris, Nikos, Manganaris, Kyriakos, Selimis, Dimitris, Lazarakis, Fotis, Sanguanpuak, Tachporn, Halmetoja, Heikki, Ibrahim, Moamen, Yaqub, Edwin, Desai, Rachana, Klinkenberg, Ralf, Kokkoniemi, Joonas, Boulogeorgos, Alexandros-Apostolos A., Sotiris, Droulias, Alexiou, Angeliki
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: European Commission
OpenAlex ID: W4286853496