Responsive multipath TCP in SDN-based datacenters

Duan, Jingpu; Zhi, Wang; Wu, Chuan

doi:10.1109/icc.2015.7249165

Cited by 30 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Faster download speed and improved QoE is reported in [10], where SDN is used to add or remove MPTCP paths in order to reduce large number of out-of-order packets which may cause poor performance and degrade the end-users' QoE. A responsive MPTCP approach that employs a centralized SDN controller for calculating the forwarding paths of subflows is presented in [11].…”

Section: Related Workmentioning

confidence: 99%

A Novel QoE-Centric SDN-Based Multipath Routing Approach for Multimedia Services over 5G Networks

Barakabitze

Sun

Mkwawa

et al. 2018

2018 IEEE International Conference on Communications (ICC)

View full text Add to dashboard Cite

The explosion of enhanced applications such as live video streaming, video gaming and Virtual Reality calls for efforts to optimize transport protocols to manage the increasing amount of data traffic on future 5G networks. Through bandwidth aggregation over multiple paths, the Multi-Path Transmission Control Protocol (MPTCP) can enhance the performance of network applications. MPTCP can split a large multimedia flow into subflows and apply a congestion control mechanism on each subflow. Segment Routing (SR), a promising source routing approach, has emerged to provide advanced packet forwarding over 5G networks. In this paper, we explore the utilization of MPTCP and SR in SDN-based networks to improve network resources utilization and end-user's QoE for delivering multimedia services over 5G networks. We propose a novel QoE-aware, SDN-based MPTCP/SR approach for service delivery. In order to demonstrate the feasibility of our approach, we implemented an intelligent QoE-centric Multipath Routing Algorithm (QoMRA) on an SDN source routing platform using Mininet and POX controller. We carried out experiments on Dynamic Adaptive video Steaming over HTTP (DASH) applications over various network conditions. The preliminary results show that, our QoEaware SDN-based MPTCP/SR scheme performs better compared to the conventional TCP approach in terms of throughput, link utilization and the end-user's QoE.

show abstract

Section: Related Workmentioning

confidence: 99%

A Novel QoE-Centric SDN-Based Multipath Routing Approach for Multimedia Services over 5G Networks

Barakabitze

Sun

Mkwawa

et al. 2018

2018 IEEE International Conference on Communications (ICC)

View full text Add to dashboard Cite

show abstract

“…The authors adjust the number of MPTCP paths based on the available link capacity to reduce a large number of outof-order packets which may cause poor performance and degrade the end-user's QoE. Jingpu et al [32] employ a centralized controller for intelligent subflow route calculation for each MPTCP session in SDN-based data centers. To enable load balancing, Kalpana et al [33] propose a SubFlow Optimizer (SFO) that establishes new subflows and assigns them to the best paths in SDN.…”

Section: Related Work a Mptcp Sdn/nfv-based Approaches For Videomentioning

confidence: 99%

QoEMultiSDN: Management of Multimedia Services using MPTCP/SR in Softwarized and Virtualized Networks

et al. 2024

View full text Add to dashboard Cite

5G networks are set to empower new user experiences for multimedia streaming services by offering high data rates and low latency. The rapid growth of multimedia services, such as video streaming services over future softwarized 5G networks, poses great challenges for both service providers and network operators regarding service provisioning with high Quality of Experience (QoE). Network evolution towards Software Defined Networking (SDN) and Network Function Virtualization (NFV) provides new opportunities to develop innovative ways to address the challenges. In this paper, we present a novel QoE-aware management scheme based on SDN/NFV by utilizing Multi-Path-TCP/Segment-Routing (MPTCP/SR) techniques and exploring information from both the network and client. The new scheme, entitled QoEMultiSDN, provides an optimized end-to-end QoE for multimedia service delivery. QoEMultiSDN employs two novel strategies to achieve this: (a) QoE-based multisource routing and QoE optimization, and (b) multipath protection and dynamic link-failure-free mechanisms. We implemented the proposed scheme over SDN through Dynamic Adaptive Streaming over HTTP (DASH) experiments using Mininet, POX and OpenDaylight controllers, and compared its performance with MPTCP and regular TCP. Experimental results indicate that the QoEMultiSDN outperforms others in terms of system throughput, failure recovery time and the QoE of the end-user.

show abstract

“…This idea is also applied in [26], but they only consider the overlapping between subflows and neglect the capacity of links, though there won't form a bottleneck on links with sufficient bandwidth. Further, algorithms starts to consider the traffic on subflows, the author of [28] prefers paths with slighter traffic and assigns them to the route of subflows. And in [14] it chooses subflows with high bandwidth and small differences for data transmission.…”

Section: B Cross Layer Optimization For Mptcpmentioning

confidence: 99%

GCLR: GNN-Based Cross Layer Optimization for Multipath TCP by Routing

Zhu

Chen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Multipath TCP has attracted increasing attention as a promising technology for 5G networks. To fully utilize network interfaces on multi-homed terminals and the whole network resources, MPTCP is proposed as an extension of TCP to transfer packets concurrently over multiple paths. Cross layer optimization techniques have been applied for MPTCP such as routing and path management. However, existing multipath routing algorithms and network modeling techniques are facing the challenges of subflow asymmetry due to network heterogeneity, thus cannot handle routing optimization problems comprehensively. To address these problems, in this paper, firstly, a novel Graph Neural Network (GNN) based multipath routing model is proposed to explore the complications among links, paths, subflows and the MPTCP connection on various topologies. Leveraging the GNN model, expected throughput can be predicted with given network topology and multipath routes, which can further be the guidance for optimzing the multipath routing. Then, GCLR, a GNN based cross layer optimization system for MPTCP by routing, is proposed with the help of SDN (Software Defined Networking). According to simulation results, our off-line learned GNN model can predict the expected throughput of specific MPTCP connections with very low error. Besides, it's validated that the model has high generalization ability in terms of connection arbitrary and topology arbitrary, it can maintain MSE (mean squared error) at a low level when the situations are not seen during training, which is sufficient for throughput prediction in multipath routing decisions. Finally, the online routing optimization system is realized using SDN, experimental results show that our proposed routing optimization system can achieve significant throughput enhancement compared with traditional multipath routing algorithms. INDEX TERMS Routing, multipath TCP, graph neural network, cross layer optimization, software defined networking.

show abstract

Responsive multipath TCP in SDN-based datacenters

Cited by 30 publications

References 8 publications

A Novel QoE-Centric SDN-Based Multipath Routing Approach for Multimedia Services over 5G Networks

A Novel QoE-Centric SDN-Based Multipath Routing Approach for Multimedia Services over 5G Networks

QoEMultiSDN: Management of Multimedia Services using MPTCP/SR in Softwarized and Virtualized Networks

GCLR: GNN-Based Cross Layer Optimization for Multipath TCP by Routing

Contact Info

Product

Resources

About