Paper Info
Title
Network And Cloudlet Selection For Computation Offloading On A Software-Defined Edge Architecture
Abstract
Edge computing is an emerging paradigm that brings the benefits of the cloud processing closer to the user, thus reducing delays in computational offloading. However, mobile user experience can still be affected due to signal degradation, reduced network throughput, as well as limited edge processing capabilities. To mitigate this problem, this paper proposes a framework to select computational and network resources for offloading operations in a mobile cloudlet environment. The proposed strategy considers the quality of service (QoS) requirements of the application as input to a fuzzy system in order to perform network selection. The selection of computational resources is carried out by a weighted cost function with metrics set by the analytic hierarchy process (AHP) method. A Software Defined Networking (SDN) approach is devised in order to reroute offloading data. Face recognition application were evaluated and achieved gains in terms of reduced processing times of up to 58,58%.
Year
DOI
Venue
2019
10.1007/978-3-030-19223-5_11
GREEN, PERVASIVE, AND CLOUD COMPUTING, GPC 2019
Keywords
Field
DocType
Edge computing, Computational offloading, Software Defined Networks, Fuzzy logic
Edge computing,User experience design,Cloudlet,Computer science,Quality of service,Computer network,Computation offloading,Throughput,Software-defined networking,Cloud computing,Distributed computing
Conference
Volume
ISSN
Citations 
11484
0302-9743
0
PageRank 
References 
Authors
0.34
0
3
Name
Order
Citations
PageRank
Bruno Silva112416.86
Warley Junior200.34
Kelvin Dias3269.61