Traffic-aware QoS provisioning in P4-based Software Defined Networks

نوع: Type: Thesis

مقطع: Segment: masters

عنوان: Title: Traffic-aware QoS provisioning in P4-based Software Defined Networks

ارائه دهنده: Provider: Vahid Shekarpour Jahani

اساتید راهنما: Supervisors: Dr.Reza Mohammadi

اساتید مشاور: Advisory Professors:

اساتید ممتحن یا داور: Examining professors or referees: Dr.Hatam Abdoli,Dr.mehdi abbasi

زمان و تاریخ ارائه: Time and date of presentation: 2025

مکان ارائه: Place of presentation: سمینار کامپیوتر

چکیده: Abstract: With the rapid growth of data and the increasing demand for fast and stable communications, efficient traffic management has become one of the key challenges in modern networks. In this context, Software-Defined Networking (SDN), by separating the control plane from the data plane and enabling centralized programmability, provides a new foundation for intelligent network management. Meanwhile, the P4 programming language and its programmable switches enable flexible and precise packet processing at the data-plane level. In this research, a hybrid architecture based on SDN and P4 switches is designed and implemented with the aim of improving Quality of Service (QoS) and enhancing traffic management efficiency. In the proposed structure, P4 switches classify packets according to their traffic type and characteristics and place them into appropriate queues. The central controller (ONOS) periodically collects statistical information from network paths—such as delay, bandwidth utilization, and path cost—and determines the optimal route for each traffic flow. The decision-making process in the controller is performed using the TOPSIS algorithm as a multi-criteria decision-making model, enabling the selection of the most suitable path based on the defined metrics. The results demonstrate that combining SDN’s centralized control capabilities with the flexible packet processing of P4 switches significantly improves resource allocation, reduces latency, and enhances overall service quality. Furthermore, employing the TOPSIS algorithm allows the controller to make intelligent and adaptive routing decisions according to the dynamic state of the network.