no code implementations • 26 Dec 2023 • Xin Yuan, Ning li, Tuo Zhang, Muqing Li, YuWen Chen, Jose Fernan Martinez Ortega, Song Guo
Specifically, when the mobile user has a large model inference task needed to be calculated in the NOMA-based MEC, it will take the energy consumption of both device and edge server and the inference latency into account to find the optimal model split strategy, subchannel allocation strategy (uplink and downlink), and transmission power allocation strategy (uplink and downlink).