DRL-Based Offloading for Computation Delay Minimization in Wireless-Powered Multi-access Edge Computing

• Published in: IEEE transactions on communications Vol. 71; no. 3; p. 1
• Main Authors: Zheng, Kechen, Jiang, Guodong, Liu, Xiaoying, Chi, Kaikai, Yao, Xinwei, Liu, Jiajia
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.03.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; computation delay; Computation offloading; Computational modeling; deep reinforcement learning; Delay; Delays; Edge computing; Energy limitation; Integer programming; Linear programming; Machine learning; Mixed integer; Mobile computing; Multi-access edge computing; Optimization; Problem solving; Rayleigh channels; Resource management; Task analysis; Wireless communication; wireless power transfer; Wireless power transmission
• ISSN: 0090-6778; 1558-0857
• DOI: 10.1109/TCOMM.2023.3237854

Wireless power transfer (WPT) and edge computing have been validated as effective ways to solve the energy-limited problem and computation-capacity-limited problem of wireless devices (WDs), respectively. This paper studies the wireless-powered multi-access edge computing (WP-MEC) network, where WDs conduct either local computing or task offloading for their individable computation tasks. We aim to minimize total computation delay (TCD) when each WD has a computation task to execute, referred to as the total computation delay minimization (TCDM) problem, by jointly optimizing the offloading-decision, WPT duration, and transmission durations of offloading WDs. The TCDM problem is a mixed integer programming (MIP) problem that is challenging to efficiently obtain the optimal or near-optimal solution. To tackle this challenge, we decompose the TCDM problem into the sub-problem of optimizing the WPT duration and transmission durations, and the top-problem of optimizing the offloading decision. For the nonconvex sub-problem, we design a worst-WD-adjusting (WDA) algorithm to efficiently obtain its optimal solution. For the top-problem, under the time-varying channel conditions, traditional optimization methods are hard to determine the optimal or near-optimal offloading decision within the channel coherence duration. To fast obtain the near-optimal offloading decision, we propose a deep neural networks (DNN)-based deep reinforcement learning (DRL) model, which takes the sub-problem solving as one component for utility evaluation. Finally, numerical results demonstrate that the proposed online DRL-based offloading algorithm achieves the near-minimal TCD with low computational complexity, and is suitable for the fast-fading WP-MEC network.