Joint UAV Position Optimization and Resource Scheduling in Space-Air-Ground Integrated Networks With Mixed Cloud-Edge Computing

• Published in: IEEE systems journal Vol. 15; no. 3; pp. 3992 - 4002
• Main Authors: Mao, Sun, He, Shunfan, Wu, Jinsong
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.09.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Cloud computing; Computation offloading; Computational modeling; Delay; Delays; Edge computing; Forest fires; Internet of Things; Internet of Things (IoT); Optimization; Processor scheduling; Resource scheduling; space-air-ground integrated networks (SAGIN); Task analysis; Task scheduling; Ubiquitous computing; Unmanned aerial vehicles; unmanned aerial vehicles (UAVs)
• ISSN: 1932-8184; 1937-9234
• DOI: 10.1109/JSYST.2020.3041706

Space-aerial-assisted computation offloading has been recognized as a promising technique to provide ubiquitous computing services for remote Internet of Things (IoT) applications, such as forest fire monitoring and disaster rescue. This article considers a space-aerial-assisted mixed cloud-edge computing framework, where the flying unmanned aerial vehicles (UAVs) provide IoT devices with low-delay edge computing service and satellites provide ubiquitous access to cloud computing. We aim to minimize the maximum computation delay among IoT devices with the joint scheduling for association control, computation task allocation, transmission power and bandwidth allocation, UAV computation resource, and deployment position optimization. Through exploiting block coordinate descent and successive convex approximation, we develop an alternating optimization algorithm with guaranteed convergence, to solve the formulated problem. Extensive simulation results are provided to demonstrate the remarkable delay reduction of the proposed scheme than existing benchmark methods.