DQN-based resource allocation for NOMA-MEC-aided multi-source data stream

Abstract This paper investigates a non-orthogonal multiple access (NOMA)-aided mobile edge computing (MEC) network with sources and one point (CAP), in which NOMA technology is applied to transmit multi-source data streams CAP for computing. To measure the performance of considered NOMA-aided MEC network, we first design system cost as linear weighting function energy consumption delay under network. Moreover, propose deep Q (DQN)-based offloading strategy minimize by jointly optimizing ratio transmission power allocation. Finally, experiments demonstrate effectiveness proposed strategy. Specifically, designed can decrease about 15% compared local when number 5.