A Markovian Approach to Multipath Data Transfer in Overlay Networks

Abstract

The use of multipath routing in overlay networks is a promising solution to improve performance and availability of Internet applications, without the replacement of the existing TCP/IP infrastructure. In this paper, we propose an approach to distribute data over multiple overlay paths that is able to improve Quality of Service (QoS) metrics, such as the data transfer time, loss, and throughput. By using the Imbedded Markov Chain technique, we demonstrate that the system under analysis, observed at specific instants, possesses the Markov property. We therefore cast the data distribution problem into the Markov Decision Process (MDP) framework, and design a computationally efficient algorithm named Online Policy Iteration (OPI), to solve the optimization problem on the fly. The proposed approach is applied to the problem of multipath data distribution in various wired/wireless network scenarios, with the objective of minimizing the data transfer time as well as the delay and losses. Through both intensive ns-2 simulations with data collected from real heterogeneous networks and experiments over real networks, we show the superior performance of the proposed traffic control mechanism in comparison with two classical schemes, that are Weighted Round Robin and Join the Shortest Queue.

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

“…The work closest to ours is conducted by Bui et al [2]. The authors formulate the multipath data distribution as a Markov Decision Process and propose an Online Policy Iteration (OPI) algorithm.…”

“…1. However, a single communication path is not capable of completely satisfying the stringent QoS (Quality of Service) requirements (e.g., delay, bandwidth and reliability) imposed by current and emerging real-time multimedia applications [2][3] (e.g., multi-player online gaming and live sports program). With the rise of multihomed or multinetwork clients [4] (e.g., the Mushroom products [5]), new research trends [6] [7] have moved towards simultaneously exploiting these multiple paths for enhanced transmission reliability and throughput.…”

“…Therefore, many algorithms [1] [2][10] [11] have been proposed to optimize the delay or throughput performance. However, these network-level criteria cannot properly indicate the benefits of upper-layer applications.…”

“…To effectively aggregate the available capacity of different network paths, we have to seriously consider: (1) how to guarantee the input traffic delivering within the delay constraint, and (2) how to alleviate the burst data losses 1 frequently encountered in wired/wireless packet switching networks. Motivated by addressing the above issues, we propose a Goodput-Aware Load distribuTiON model (GALTON) that includes three phases: (1) path status estimation to capture the physical characteristics of each transport link, (2) flow rate assignment to optimize the aggregate goodput of input traffic, and (3) deadline-constrained packet interleaving to alleviate consecutive losses. The detailed descriptions of the proposed solution will be presented in Section 4.…”

Multicast Utility Maximization with Load Balanc-ing in Private Cloud Environment

“…In [12], Congestion controls achieves high bandwidth utilization over networks operating multi-path routing In [13], MVNE model achieved a lower blocking ratio, higher revenue, and balanced network utilization. In [14], defined the multicast virtual network restoration problem and demonstrate its NP-complete nature in arbitrary graphs. Moreover, they demonstrated that the issue can be illuminated in polynomial-time in multi-established treelike server farm arrange topologies.…”