Energy-Efficient Mobile Edge Computing Under Delay Constraints

• Published in: IEEE transactions on green communications and networking Vol. 6; no. 2; pp. 776 - 786
• Main Authors: Li, Zhidu, Zhu, Ni, Wu, Dapeng, Wang, Honggang, Wang, Ruyan
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.06.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Computation offloading; Computational modeling; Delay; Delays; Edge computing; Energy consumption; Mobile computing; Optimization; Processor scheduling; Resource allocation; Resource management; Resource scheduling; Servers; Task analysis; task delay; task processing priority; Task scheduling
• ISSN: 2473-2400; 2473-2400
• DOI: 10.1109/TGCN.2021.3138729

Green communication is one of the key goals of the beyond 5G networks. However, as more and more delay sensitive applications emerge, the contradiction between task delay requirement and energy conservation becomes more and more prominent on the device side. This paper focuses on a mobile edge computing system where local computing capability and edge computing capability are both limited, which may lead to task discarding due to delay violation. An energy consumption minimization problem is first formulated under the binary offloading and the partial offloading modes. Then a low-complexity heuristic scheme and a Lagrange dual scheme are proposed to jointly optimize the task scheduling and resource allocation under those two modes respectively. Particularly, a task processing priority model is designed to effectively reduce the number of discarded tasks and improve the service performance of the MEC server. The effectiveness of the proposed schemes is validated by extensive simulations with comparison to other baseline schemes.