Journal
2022 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC)
Volume -, Issue -, Pages 292-297Publisher
IEEE
DOI: 10.1109/WCNC51071.2022.9771874
Keywords
Mobile edge computing; small cell; energy efficiency; cooperative task offloading
Categories
Funding
- CSC Scholarship [CSC202006960079]
- NSF China [61901319, 61971327]
- NRF of Korea - Korean Government (MSIT) [NRF-2020R1A2B5B02002478]
Ask authors/readers for more resources
In this paper, an adaptive cooperative task offloading algorithm is proposed to maximize the time-averaged energy efficiency for small cell MEC networks enabled by millimeter-wave backhauls. The algorithm makes a good tradeoff between cooperation utility and total energy consumption, and ensures network stability and task admission rate fulfillment.
Cooperative task offloading has emerged as a compelling computing paradigm for balancing spatially uneven task workloads and computational resources in distributed mobile edge computing (MEC) systems. However, enabling cooperation among multiple MEC nodes inevitably requires extra communication and computational energy overheads which might counteract the cooperation gain without energy-efficient offloading mechanisms. This paper presents an adaptive cooperative task offloading algorithm aiming at maximizing the time-averaged energy efficiency for small cell MEC networks enabled by millimeter-wave backhauls. With the considered network dynamics, the proposed algorithm makes a good tradeoff between the harvested cooperation utility and the total energy consumption in the long term. In addition, our algorithm ensures the network stability and fulfills the task admission rate requirement of each individual user equipment, by making slot-based decisions over time without requiring a-priori knowledge of the network dynamics. Simulation results verify the outstanding performance of the proposed algorithm by comparing with the static cooperative and adaptive non-cooperative schemes.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available