Mobile Satellite Service (MSS) can provide users reliable communication abilities wherever they are on earth surface, even in a high-speed motion status, which can either be stand-alone or a complementary service to the terrestrial communication systems. In the recent past, diverse MSS applications have been emerging rapidly. Some introduce unprecedentedly heavy traffic transmission pressure, and some others require real-time response, both of which cannot be satisfied by legacy mobile satellite communication networks anymore. This paper proposes an enhanced strategy to enable edge computing ability on the existing satellite networks. More precisely, this paper re-architects a GEO satellite node to become a cloudlet which possesses a set of computation, storage and networking resources, and can accomplish a certain amount of computing jobs which are typically happened on centralised cloud centre on the ground. A test-bed containing the emulated cloudlet-enabled GEO satellite has been built on a single PC. Functional test and performance evaluation are conducted for FTP file transmission and HTTP web browsing services. Experimental results show that the enhanced edge computing ability can effectively and efficiently decrease bandwidth consumption and lower the response latency in mobile satellite networks.
[1]
Brandon Lucia,et al.
Orbital Edge Computing: Machine Inference in Space
,
2019,
IEEE Computer Architecture Letters.
[2]
Wenyu Zhang,et al.
Satellite Mobile Edge Computing: Improving QoS of High-Speed Satellite-Terrestrial Networks Using Edge Computing Techniques
,
2019,
IEEE Network.
[3]
Larry L. Peterson,et al.
Central office re-architected as a data center
,
2016,
IEEE Communications Magazine.
[4]
Xing Zhang,et al.
A Computation Offloading Strategy in Satellite Terrestrial Networks with Double Edge Computing
,
2018,
2018 IEEE International Conference on Communication Systems (ICCS).
[5]
Nikolay N. Mirenkov,et al.
Satellite Cloud Computing
,
2011,
2011 IEEE Workshops of International Conference on Advanced Information Networking and Applications.