The combination of the edge computing paradigm with Mobile CrowdSensing (MCS) is a promising approach. However, the selection of the proper edge nodes is a crucial aspect that greatly affects the performance of the extended architecture. This work studies the performance of an edge-based MCS architecture with ParticipAct, a real-word experimental dataset. We present a community-based edge selection strategy and we measure two key-metrics, namely latency and the number of requests satisfied. We show how they vary by adopting three evolutionary community detection algorithms, TILES, Infomap and iLCD configured by changing several configuration settings. We also study the two metrics, by varying the number of edge nodes selected so that to show its benefit.
Impact of Evolutionary Community Detection Algorithms for Edge Selection Strategies
Chessa S.;Belli D.;
2020-01-01
Abstract
The combination of the edge computing paradigm with Mobile CrowdSensing (MCS) is a promising approach. However, the selection of the proper edge nodes is a crucial aspect that greatly affects the performance of the extended architecture. This work studies the performance of an edge-based MCS architecture with ParticipAct, a real-word experimental dataset. We present a community-based edge selection strategy and we measure two key-metrics, namely latency and the number of requests satisfied. We show how they vary by adopting three evolutionary community detection algorithms, TILES, Infomap and iLCD configured by changing several configuration settings. We also study the two metrics, by varying the number of edge nodes selected so that to show its benefit.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
