Energy Efficient Edge Computing and Data Compression Collaboration Scheme for UAV-Assisted Network
Kaijun Cheng, Xuming Fang, Xianbin Wang
Abstract
Edge computing is a promising technique that can assist wireless devices (WDs) in processing computation tasks by offloading them to nearby base stations for reducing processing latency and energy consumption. However, in situations where terrestrial wireless infrastructure is unavailable, unmanned aerial vehicle (UAV)-assisted communication becomes an alternative solution that can be flexibly deployed over the WDs to provide communication and edge computing services. In this paper, we study a data compression scheme in the multi-user UAV-enabled edge computing process to reduce energy consumption of WDs. The offloading of compressed tasks is further investigated for the overall improved computing performance. Specifically, we formulate a problem to minimize the sum energy consumption of WDs by optimizing WD power control, task compression ratio, communication resource allocation, and UAV trajectory, under the constraints of computation task deadline, communication resource budget, WD transmission power budget, UAV onboard energy budget, and trajectory limitations. Numerical results are shown to evaluate the performance of this edge computing and data compression collaboration scheme, which validates the feasibility of the proposed energy efficient edge computing and data compression algorithm and presents that our proposed scheme can save at least 28.2% energy consumption compared with other baseline schemes when the raw task size is 4 Mbits.