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

Abstract

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.

Graph-based Deep Learning for Communication Networks: A Survey

“…Computer Networks [13,14] Electronics [15] IEEE Access [16,17] IEEE Communications Letters [18,19,20,21] IEEE Internet of Things Journal [22] IEEE Journal on Selected Areas in Communications [23,24,25,26] IEEE Systems Journal [27] IEEE Transactions on Industrial Informatics [28] IEEE Transactions on Information Forensics and Security [29] IEEE Transactions on Mobile Computing [30,31] IEEE Transactions on Network Science and Engineering [32] IEEE Transactions on Network and Service Management [33] IEEE Transactions on Signal Processing [34] IEEE Transactions on Vehicular Technology [35] IEEE Transactions on Wireless Communications [36,37] International Journal of Network Management [38] Performance Evaluation [39] Sensors [40] Transactions on Emerging Telecommunications Technologies [41] conducting a thorough literature search on the graph-based models. For now, we would give a short introduction for the GNNs used in the surveyed studies.…”

Graph Neural Networks for Communication Networks: Context, Use Cases and Opportunities

“…Multipath TCP [10], network calculus [11], or power control in wireless networks [12], [13]. In order to illustrate the potential of GNNs, we present two representative examples of custom GNN-based architectures respectively applied to two use cases of wired and wireless networks: RouteNet [1], and WCGCN [12].…”

“…GNNs can be virtually applied to a plethora of networkrelated domains as long as they can be formulated as graphs. Indeed, these models have been recently validated for several representative use cases, showing outstanding applications in different communication paradigms (wired, wireless, SDN/NFV, IoT) [1], [9], [10], [11], [12], [13]; while there is still an ocean of opportunities to apply these novel methods to different use cases (e.g., optimization, troubleshooting, planning, what-if analysis) and expand their horizon towards other types of communication networks barely explored (e.g., satellite communications). However, this will not be a straightforward task, as standard GNN models are not directly applicable to many networking use cases, but a thorough designing process is often required to come up with custom GNN architectures well suited to the target networking problem.…”

Fieldable Cross-Layer Optimized Embedded Software Defined Radio is Finally Here!

“…Cross-layer approaches have been explored as a novel solution to address a wide range of problems in wireless communication due to its perceived benefits in sustaining communications in a dynamic and constrained environment [6], [7]. This includes RF domain for tactical network [8]- [10], commercial network [11]- [14], acoustic underwater networks, and even in the upcoming visible light communication networks [15]- [18]. These solutions are designed for various objectives such as optimizing throughput and/or latency [19]- [22], fairness [8], energy consumption [12], [13], [15], resource management [14], [17], efficient multi-path TCP [11].…”

“…This includes RF domain for tactical network [8]- [10], commercial network [11]- [14], acoustic underwater networks, and even in the upcoming visible light communication networks [15]- [18]. These solutions are designed for various objectives such as optimizing throughput and/or latency [19]- [22], fairness [8], energy consumption [12], [13], [15], resource management [14], [17], efficient multi-path TCP [11]. In this work, we focus on reviewing the maturity of these state-of-the-art crosslayer solutions to expose the absence of deployable embedded SDR based solutions.…”