[Paper Review] Design and implementation of a differentiated service based qos model for real-time interactive traffic on constrained bandwidth ip networks

Sruti Gan Chaudhuri|arXiv (Cornell University)|May 15, 2012

Network Traffic and Congestion Control6 references3 citations

TL;DR

This paper proposes a DiffServ-based QoS model for real-time interactive traffic in bandwidth-constrained IP networks, using dynamic, adaptive queuing with priority-based scheduling and weighted service rates to ensure low delay and packet loss without overprovisioning. Experimental results demonstrate effective QoS provisioning for video conferencing and surveillance traffic, with improved fairness and resource utilization in both lab and real network tests.

ABSTRACT

In this thesis work, a QoS model for real-time interactive traffic on a real network with constrained bandwidth and real-time traffic has been proposed. The model supports tight guarantees of QoS to real-time interactive traffic without over provisioning of bandwidth. A dynamic scheduling model which is adaptive to input data rate of traffic has been proposed. In this model, A Differentiated Service (DiffServ) based approach is proposed for QoS provisioning. The packets are classified and distributed among finite number of queues with limited buffer based on different priorities and total available bandwidth. The model proposes a mechanism to derive the weighted service rates and queue length distribution so as to meet the requirement of low packet loss and delay for real time interactive traffic in the QoS engineered network. An adaptive queuing strategy is proposed so that minimum bandwidth in used for real time traffic. This ensures maximizing availability to best effort traffic. The model assumes constrained bandwidth without having to over provision the network resources and thus keeping the cost low. A modified version suitable for testing on a real network is also presented. Experimental verification of these in a test bed network in a laboratory as well as on a real network has been carried out. The results of the QoS provisioning model for different sources of real-time traffic such as video conferencing equipment, robotic surveillance camera has also been shown. The thesis also introduces a real-time Variable Bit Rate (VBR) traffic tuning parameter for controlling the service of VBR traffic to give better and fair performance to rest of the traffic.

Motivation & Objective

• To design a QoS model that guarantees low delay and packet loss for real-time interactive traffic in bandwidth-constrained IP networks.
• To avoid network overprovisioning while maintaining high-quality service for real-time applications.
• To develop an adaptive queuing strategy that dynamically adjusts to input data rates and optimizes bandwidth usage.
• To ensure fair resource allocation between real-time and best-effort traffic under limited bandwidth.
• To validate the model experimentally in both lab testbed and real network environments.

Proposed method

• The model uses a Differentiated Services (DiffServ) framework to classify packets into priority-based queues with limited buffer space.
• It implements a dynamic scheduling mechanism that adapts to the input data rate of real-time traffic.
• Weighted service rates and queue length distributions are derived mathematically to meet QoS requirements for delay and loss.
• An adaptive queuing strategy minimizes bandwidth usage for real-time traffic, maximizing availability for best-effort traffic.
• A real-time Variable Bit Rate (VBR) traffic tuning parameter is introduced to balance performance across traffic types.
• A modified version of the model is implemented for real-world testing on physical network infrastructure.

Experimental results

Research questions

• RQ1 How can QoS guarantees for real-time interactive traffic be achieved in a bandwidth-constrained IP network without overprovisioning?
• RQ2 What dynamic scheduling mechanism ensures low delay and packet loss under variable traffic input rates?
• RQ3 How can weighted service rates and queue length distributions be optimized to meet real-time QoS requirements?
• RQ4 What impact does the VBR tuning parameter have on fairness and performance across mixed traffic types?
• RQ5 How does the proposed model perform in real-world network conditions compared to theoretical expectations?

Key findings

• The model successfully achieves low packet loss and delay for real-time traffic, such as video conferencing and robotic surveillance, in both lab and real network environments.
• Experimental results confirm that the adaptive queuing strategy minimizes bandwidth usage for real-time traffic while preserving capacity for best-effort traffic.
• The VBR tuning parameter enables fairer performance distribution, improving overall network efficiency.
• The model maintains QoS guarantees without requiring network overprovisioning, thus reducing operational costs.
• The implementation on a real testbed network validates the model’s feasibility and effectiveness under practical conditions.
• The proposed mechanism for deriving weighted service rates and queue length distributions effectively supports low-latency, low-loss operation.