Titre: Joint Scheduling-Offloading policies in NOMA-based Mobile Edge Computing Systems

Abstract: We consider the problem of jointly optimizing scheduling and offloading, in a NOMA-based wireless network where the users are connected to a Base Station equipped with a Mobile Edge Computing (MEC) server. The users have the choice to execute their buffered data (stored under strict delay constraints) either locally or by offloading them to the MEC server and retrieve the results. To minimize the number of dropped packets, we model the problem as a Markov Decision Process, and solve it using both model-based and model-free methods (e.g. deep q-learning).