RT Journal Article
T1 Clustering and Flow Conservation Monitoring Tool for Software Defined Networks
A1 Puente Fernández, Jesús Antonio
A1 García Villalba, Luis Javier
A1 Kim, Tai-Hoon
AB Prediction systems present some challenges on two fronts: the relation between video quality and observed session features and on the other hand, dynamics changes on the video quality. Software Defined Networks (SDN) is a new concept of network architecture that provides the separation of control plane (controller) and data plane (switches) in network devices. Due to the existence of the southbound interface, it is possible to deploy monitoring tools to obtain the network status and retrieve a statistics collection. Therefore, achieving the most accurate statistics depends on a strategy of monitoring and information requests of network devices. In this paper, we propose an enhanced algorithm for requesting statistics to measure the traffic flow in SDN networks. Such an algorithm is based on grouping network switches in clusters focusing on their number of ports to apply different monitoring techniques. Such grouping occurs by avoiding monitoring queries in network switches with common characteristics and then, by omitting redundant information. In this way, the present proposal decreases the number of monitoring queries to switches, improving the network traffic and preventing the switching overload. We have tested our optimization in a video streaming simulation using different types of videos. The experiments and comparison with traditional monitoring techniques demonstrate the feasibility of our proposal maintaining similar values decreasing the number of queries to the switches.
PB MDPI
SN 1424-8220
YR 2018
FD 2018-04-03
LK https://hdl.handle.net/20.500.14352/12695
UL https://hdl.handle.net/20.500.14352/12695
LA eng
NO Unión Europea. Horizonte 2020
DS Docta Complutense
RD 25 abr 2025