Cooperative Resource Allocation for Computation-Intensive IIoT Applications in Aerial Computing





Citation of Original Publication

J. Liu, G. Li, Q. Huang, M. Bilal, X. Xu and H. Song, "Cooperative Resource Allocation for Computation-Intensive IIoT Applications in Aerial Computing," in IEEE Internet of Things Journal, 2022, doi: 10.1109/JIOT.2022.3222340.


© 2022 IEEE.  Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.



Unmanned aerial vehicles (UAVs) will be a vital part of the massive Industrial Internet of Things (IIoT) in the 5G and 6G paradigms. The UAVs are required to collaborate with each other to deal with some computation-intensive IIoT applications in an autonomous UAV system. However, due to the limited processing capacity of UAVs, they are occasionally unable to handle certain tasks adequately (e.g., crowd sensing). Therefore, it is an important issue to realize efficient offloading of these computation-intensive IIoT applications. In this paper, we first partition the computation-intensive IIoT application into a directed acyclic graph with multiple collaborative tasks. Then, we establish a joint optimization problem based on the models of the processor resources and energy consumption for the task offloading scheme. Thirdly, we propose a cooperative resource allocation approach to optimize the joint optimization problem under the constraints of resource and communication latency, and then can migrate more computation-intensive tasks to the edge clouds. Finally, we build an aerial computing simulation system, and make a comparative evaluation and analysis of our proposed cooperative resource allocation approach in terms of effectiveness and performance. The experimental results show that our proposed approach performs better than other related approaches.