Graph Reinforcement Learning-based CNN Inference Offloading in Dynamic Edge Computing

Nan Li*, Alexandros Iosifidis, Qi Zhang

*Corresponding author af dette arbejde

Publikation: Bidrag til bog/antologi/rapport/proceedingKonferencebidrag i proceedingsForskningpeer review


This paper studies the computational offloading of CNN inference in dynamic multi-access edge computing (MEC) networks. To address the uncertainties in communication time and Edge servers' available capacity, we use early-exit mechanism to terminate the computation earlier to meet the deadline of inference tasks. We design a reward function to trade off the communication, computation and inference accuracy, and formu-late the offloading problem of CNN inference as a maximization problem with the goal of maximizing the average inference accuracy and throughput in long term. To solve the maxi-mization problem, we propose a graph reinforcement learning-based early-exit mechanism (GRLE), which outperforms the state-of-the-art work, deep reinforcement learning-based online offloading (DROO) and its enhanced method, DROO with early-exit mechanism (DROOE), under different dynamic scenarios. The experimental results show that G RLE achieves the average accuracy up to 3.41 x over graph reinforcement learning (GRL) and 1.45x over DROOE, which shows the advantages of GRLE for offloading decision-making in dynamic MEC.

Titel2022 IEEE Global Communications Conference, GLOBECOM 2022 - Proceedings
Antal sider6
ISBN (Elektronisk)978-1-6654-3540-6
StatusUdgivet - 2022
BegivenhedIEEE Global Communications Conference 2022: Hybrid: In-Person and Virtual Conference Accelerating the Digital Transformation through Smart Communications - Rio de Janeiro, Brasilien
Varighed: 4 dec. 20228 dec. 2022


KonferenceIEEE Global Communications Conference 2022
ByRio de Janeiro


Dyk ned i forskningsemnerne om 'Graph Reinforcement Learning-based CNN Inference Offloading in Dynamic Edge Computing'. Sammen danner de et unikt fingeraftryk.