Joint computing and communication resource allocation for satellite communication networks with edge computing

• Published in: China communications Vol. 18; no. 7; pp. 236 - 252
• Main Authors: Zhang, Shanghong, Cui, Gaofeng, Long, Yating, Wang, Weidong
• Format: Journal Article
• Language: English
• Published: China Institute of Communications 01.07.2021; School of Electronic Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China; Key Laboratory of Universal Wireless Communications (Beijing University of Posts and Telecommunications),Beijing 100876,China; Key Laboratory of Universal Wireless Communications (Beijing University of Posts and Telecommunications),Beijing 100876,China%School of Electronic Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China; Science and Technology on Information Transmission and Dissemination in Communication Networks Laboratory,Hebei 050000,China
• Subjects: Edge computing; Logic gates; matching theory; resource allocation; Resource management; Satellite broadcasting; satellite communication networks; Satellites; Servers; Task analysis; satellite communication networks; resource allocation; matching theory; edge computing
• ISSN: 1673-5447
• DOI: 10.23919/JCC.2021.07.019

Benefit from the enhanced onboard processing capacities and high-speed satellite-terrestrial links, satellite edge computing has been regarded as a promising technique to facilitate the execution of the computation-intensive applications for satellite communication networks (SCNs). By deploying edge computing servers in satellite and gateway stations, SCNs can achieve significant performance gains of the computing capacities at the expense of extending the dimensions and complexity of resource management. Therefore, in this paper, we investigate the joint computing and communication resource management problem for SCNs to minimize the execution latency of the computation-intensive applications, while two different satellite edge computing scenarios and local execution are considered. Furthermore, the joint computing and communication resource allocation problem for the computation-intensive services is formulated as a mixed-integer programming problem. A game-theoretic and many-to-one matching theory-based scheme (JCCRA-GM) is proposed to achieve an approximate optimal solution. Numerical results show that the proposed method with low complexity can achieve almost the same weight-sum latency as the Brute-force method.