Journal
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
Volume 201, Issue -, Pages -Publisher
ACADEMIC PRESS LTD- ELSEVIER SCIENCE LTD
DOI: 10.1016/j.jnca.2022.103341
Keywords
Computation offloading; Convex optimization; Deep reinforcement learning; Mobile edge computing; Unmanned aerial vehicle
Categories
Funding
- National Research Foundation of Korea (NRF) - Korean government (MSIT) [2019R1F1A1060501]
Ask authors/readers for more resources
With the increasing growth of IoT devices, effective computation performance has become critical. Mobile edge computing (MEC) and unmanned aerial vehicles (UAVs) can address this issue. However, communication overhead and delays are major challenges. This study reviews UAV-enabled MEC solutions focusing on offloading and compares algorithms for their features and performance. Additionally, open issues and research challenges in design and implementation are discussed.
With the increasing growth of internet-of-things (IoT) devices, effective computation performance has become a critical issue. Many services provided by IoT devices (e.g., augmented reality, location-tracking, traffic systems, and autonomous driving) require intensive real-time data processing, which demands powerful computational resources. Mobile edge computing (MEC) has been introduced to effectively handle this problem reliably over the internet. The inclusion of a MEC server allows computationally intensive tasks to be offloaded from IoT devices. However, communication overhead and delays are major drawbacks. With the advantages of high mobility and low cost, unmanned aerial vehicles (UAVs) can mitigate this issue by acting as MEC servers. The offloading decisions for such scenarios involve service latency, energy/power consumption, and execution delays. For this reason, this study reviews UAV-enabled MEC solutions in which offloading was the focus of research. We compare the algorithms qualitatively to assess features and performance. Finally, we discuss open issues and research challenges in terms of design and implementation.
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