Application Aware Multiple Constraint Optimal Paths for Transport Network using SDN

Santhosha Kamath, Apoorv Srivastava, Prathamesh Kamath, Sanjay Singh, M. Sathish Kumar

Research output: Contribution to journalArticlepeer-review

Abstract

The backhaul networks for the 5G networks consist of different links that handle massive heterogeneous traffic. Fulfilling the QoS requirement of users to comply with the growth and increasing revenue is a challenge for the service providers. We address QoS parameters like bandwidth and delay for the user’s transport network. We use Software-Defined Networking and solve this problem. We have added a component Flowlet based Multiple Constraint Optimal Paths (MCOP) for packet forwarding by taking input as QoS requirements and creating a logical network in backhaul transport networks when needed for the elephant traffic. Due to security reasons, the transport network cannot access L7 to identify the application type. We have added an application identification component to detect the traffic type. We use an experimental platform using mininet and OpenFlow. Our proposed algorithm has higher QoS performance than the conventional method after the primary link exhaust capacity. It takes around 20 to 30 packets to learn the traffic type up to L6 parameters. Our approach identifies 73.10% of traffic type. The multipath usage helps improve revenue growth by assuring the dynamic allocation of the resources to the customer for elephant flow with the required QoS.

Original languageEnglish
JournalIEEE Transactions on Network and Service Management
DOIs
Publication statusAccepted/In press - 2021

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Application Aware Multiple Constraint Optimal Paths for Transport Network using SDN'. Together they form a unique fingerprint.

Cite this