TY - JOUR
T1 - AI Driven Heterogeneous MEC System with UAV Assistance for Dynamic Environment - Challenges and Solutions
AU - Jiang, Feibo
AU - Wang, Kezhi
AU - Dong, Li
AU - Pan, Cunhua
AU - Xu, Wei
AU - Yang, Kun
N1 - The work of K. Yang was supported in part by the National Natural Science Foundation of China (NSFC) (61620106011) and EU H2020 Project COSAFE (GA-824019); the work of F. Jiang was supported in part by NSFC (41604117 and 61701179), the Scientific Research Fund of Hunan Provincial Education Department in China (18A031) and the Hunan Provincial Natural Science Foundation of China (2020JJ4428) and Hunan Provincial Science Technology Project Foundation (2018TP1018 and 2018RS3065); the work of L. Dong was supported in part by NSFC (41904127) and the Hunan Provincial Natural Science Foundation of China under Grant (2020JJ5105); the work of W. Xu was supported in part by NSFC (62022026 and 61871109).
PY - 2021/1
Y1 - 2021/1
N2 - By taking full advantage of Computing, Communication and Caching (3C) resources at the network edge, Mobile Edge Computing (MEC) is envisioned as one of the key enablers for the next generation networks. However, current fixed-location MEC architecture may not be able to make realtime decision in dynamic environment, especially in large-scale scenarios. To address this issue, in this paper, a Heterogeneous MEC (H-MEC) architecture is proposed, which is composed of fixed unit, i.e., Ground Stations (GSs) as well as moving nodes, i.e., Ground Vehicles (GVs) and Unmanned Aerial Vehicles (UAVs), all with 3C resource enabled. The key challenges in H-MEC, i.e., mobile edge node management, real-time decision making, user association and resource allocation along with the possible Artificial Intelligence (AI)-based solutions are discussed. In addition, the AI-based joint Resource schEduling (ARE) framework with two different AI-based mechanisms, i.e., Deep neural network (DNN)-based and deep reinforcement learning (DRL)-based architectures are proposed. DNN based solution with online incremental learning applies the global optimizer and therefore has better performance than the DRL-based architecture with online policy updating, but requires longer training time. The simulation results are given to verify the efficiency of our proposed ARE framework.
AB - By taking full advantage of Computing, Communication and Caching (3C) resources at the network edge, Mobile Edge Computing (MEC) is envisioned as one of the key enablers for the next generation networks. However, current fixed-location MEC architecture may not be able to make realtime decision in dynamic environment, especially in large-scale scenarios. To address this issue, in this paper, a Heterogeneous MEC (H-MEC) architecture is proposed, which is composed of fixed unit, i.e., Ground Stations (GSs) as well as moving nodes, i.e., Ground Vehicles (GVs) and Unmanned Aerial Vehicles (UAVs), all with 3C resource enabled. The key challenges in H-MEC, i.e., mobile edge node management, real-time decision making, user association and resource allocation along with the possible Artificial Intelligence (AI)-based solutions are discussed. In addition, the AI-based joint Resource schEduling (ARE) framework with two different AI-based mechanisms, i.e., Deep neural network (DNN)-based and deep reinforcement learning (DRL)-based architectures are proposed. DNN based solution with online incremental learning applies the global optimizer and therefore has better performance than the DRL-based architecture with online policy updating, but requires longer training time. The simulation results are given to verify the efficiency of our proposed ARE framework.
KW - Heterogeneous mobile edge computing
KW - , artificial intelligence
KW - deep neural network
KW - deep reinforcement learning
KW - dynamic environment
U2 - 10.1109/mnet.011.2000440
DO - 10.1109/mnet.011.2000440
M3 - Article
SN - 0890-8044
VL - 35
SP - 400
EP - 408
JO - IEEE Network
JF - IEEE Network
IS - 1
ER -