Goodput-Aware Load Distribution for Real-Time Traffic over Multipath Networks

Abstract

Load distribution is a key research issue in deploying the limited network resources available to support traffic transmissions. Developing an effective solution is critical for enhancing traffic performance and network utilization. In this paper, we investigate the problem of load distribution for real-time traffic over multipath networks. Due to the path diversity and unreliability in heterogeneous overlay networks, large end-to-end delay and consecutive packet losses can significantly degrade the traffic flow's goodput, whereas existing studies mainly focus on the delay or throughput performance. To address the challenging problems, we propose a GoodputAware Load distribuTiON (GALTON) model that includes three phases: (1) path status estimation to accurately sense the quality of each transport link, (2) flow rate assignment to optimize the aggregate goodput of input traffic, and (3) deadline-constrained packet interleaving to mitigate consecutive losses. We present a mathematical formulation for multipath load distribution and derive the solution based on utility theory. The performance of the proposed model is evaluated through semi-physical emulations in Exata involving both real Internet traffic traces and H.264 video streaming. Experimental results show that GALTON outperforms existing traffic distribution models in terms of goodput, video PSNR (Peak Signal-to-Noise Ratio), end-to-end delay, and aggregate loss rate.

TCP-Oriented Raptor Coding for High-Frame-Rate Video Transmission Over Wireless Networks

“…The results' pattern is similar to the PSNR values presented in Figure 8a. It is also in accordance with the existing studies [27] that goodput performance is the key parameter in guaranteeing the QoS of real-time multimedia traffic. On one hand, ROCHET adapts the code rate to be an appropriate level to respect the delay constraint.…”

“…We employ the improved pathChirp algorithm in [27] for the channel status estimation in the system framework of ROCHET. This algorithm takes in the raw data (TCP trace if available) of status information and outputs the processed data in each probing cycle.…”

“…Recent measurement studies reveal that the video traffic pattern follows the Markov-modulated process [38]. Therefore, we model the queueing delay with the M/G/1 model and the overdue loss probability of packets over the communication network is expressed as [27]…”

“…The estimation method for video distortion is summarized in Algorithm 1 and Proposition 1 concludes the time complexity. Smooth the values of feedback network status {RT T, μ, πB, ξB} with 95% confidence interval [27];…”

“…This metric is estimated with the latest historical values of path status information and video traffic rate[27][35][37] …”