Deep Learning for Hybrid 5G Services in Mobile Edge Computing Systems: Learn From a Digital Twin

• Published in: IEEE transactions on wireless communications Vol. 18; no. 10; pp. 4692 - 4707
• Main Authors: Dong, Rui, She, Changyang, Hardjawana, Wibowo, Li, Yonghui, Vucetic, Branka
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.10.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Computer simulation; Deep learning; deep learning (DL); Delays; digital twin; Digital twins; Edge computing; Energy conservation; Energy consumption; Machine learning; Machine learning algorithms; Mobile computing; mobile edge computing (MEC); Mobility management; Optimization; Reliability; Resource allocation; Resource management; Servers; Task analysis; Ultra-reliable and low-latency communications (URLLC); user association
• ISSN: 1536-1276; 1558-2248
• DOI: 10.1109/TWC.2019.2927312

In this paper, we consider a mobile edge computing system with both ultra-reliable and low-latency communications services and delay tolerant services. We aim to minimize the normalized energy consumption, defined as the energy consumption per bit, by optimizing user association, resource allocation, and offloading probabilities subject to the quality-of-service requirements. The user association is managed by the mobility management entity (MME), while resource allocation and offloading probabilities are determined by each access point (AP). We propose a deep learning (DL) architecture, where a digital twin of the real network environment is used to train the DL algorithm off-line at a central server. From the pre-trained deep neural network (DNN), the MME can obtain user association scheme in a real-time manner. Considering that the real networks are not static, the digital twin monitors the variation of real networks and updates the DNN accordingly. For a given user association scheme, we propose an optimization algorithm to find the optimal resource allocation and offloading probabilities at each AP. The simulation results show that our method can achieve lower normalized energy consumption with less computation complexity compared with an existing method and approach to the performance of the global optimal solution.