Dynamic Traffic Steering Research Articles

Smart Service Function Chain System for Dynamic Traffic Steering using Reinforcement Learning (CHRL)

Smart Service Function Chain System for Dynamic Traffic Steering using Reinforcement Learning (CHRL)

Design and Experiment of Satellite-Terrestrial Integrated Gateway with Dynamic Traffic Steering Capabilities for Maritime Communication.

This study presents the architectural design and implementation of a multi-RAT gateway (MRGW) supporting dual satellite and terrestrial connectivity that enables moving maritime vessels, such as autonomous surface ships, to be connected to multiple radio access networks in the maritime communication environment. We developed an MRGW combining LTE and very-small-aperture terminal (VSAT) access networks to realize access traffic steering, switching, and splitting functionalities between them. In addition, we developed communication interfaces between the MRGW and end-devices connecting to their corresponding radio access networks, as well as between the MRGW and the digital bridge system of an autonomous surface ship, enabling the MRGW to collect wireless channel information from each RAT end-device and provide the collected data to the digital bridge system to determine the optimal navigation route for the autonomous surface ship. Experiments on the MRGW with LTE and VSAT end-devices are conducted at sea near Ulsan city and the Kumsan satellite service center in Korea. Through validation experiments on a real maritime communication testbed, we demonstrate the feasibility of future maritime communication technologies capable of providing the minimum performance necessary for autonomous surface ships or digitized aids to navigation (A to N) systems.

5G-Enabled MEC: A Distributed Traffic Steering for Seamless Service Migration of Internet of Vehicles

Multiaccess edge computing (MEC) is considered as a backbone for the 5G network. The successive MEC network combines the networking and computation at the edge of the network to achieve the Quality of Services (QoS) with ultralow latency. The devices with mobility feature, whether hand-held devices or vehicles move from one edge server (ES) location to another ES, creates a nonoptimal environment in the long run. To maintain QoS and avoid service disruptions, existing network topologies do not fulfill the requirement. Hence, a unique traffic steering with dynamic path selection is required for live service migration of time-sensitive applications. In this article, we are the first to introduce a distributed traffic steering through the differentiation of two different types of network elements (i.e., ESs and routers), in a large MEC system. Using this concept, we, for the first time, resolve the scalability problem of a large MEC network into a partitioned MEC network. The proposed framework bounds the path-finding procedure with a filter strategy based on the network distance to eliminate the excess of nonrelated network elements. With a decentralized framework for MEC, we propose matrix-based dynamic shortest path selection and matrix-based dynamic multipath searching algorithms for dynamic path selection under the proposed autonomous network boundary discovery and must connect node block benchmarks. Our proposed dynamic traffic steering system works under two most important metric measurements (time delay and available bandwidth). Experimental results validate the effectiveness of dynamic and adaptive path searching in a partitioned controlled MEC network that significantly outperforms the centralized approaches with 35%–70% efficiency in QoS.

Capacity-constrained Wardrop equilibria and application to multi-connectivity in 5G networks

In this paper, a distributed, non-cooperative and dynamic load-balancing algorithm is proposed in the context of multi-commodity adversarial network equilibria with constrained providers’ capacities. The algorithm is proven to converge to a generalised Wardrop user-equilibrium, referred to as Beckmann equilibrium in the literature, in which, for each commodity, the latencies of the unsaturated providers are equalized. The algorithm is then used as a Multi-connectivity algorithm in the context of 5G heterogeneous networks, in which the user equipments are able to use different access networks simultaneously to increase the transmission capacity and/or to improve the transmission reliability. The proposed controller provides a solution for dynamic traffic steering by distributing the traffic load over the available heterogeneous access points, considered as capacity providers. Simulation results validate the approach. The developed network simulator is available as an open-source environment De Santis et al. (2020).

A scatter search algorithm to configure service function chaining

Network functions virtualisation (NFV) emerges to deal with the challenges of reducing both the capital expenses (CAPEX) and operational expenses (OPEX) of cloud providers. The NFV is done by implementing network functions and providing them as software commodities. Network services are provided by chaining a set of network functions together. The key problem will be how and where network functions should be placed in the network and how traffic is routed through them. This is the well-known service function chaining problem and it is known to be NP-hard so exhaustive search algorithms have no significant benefit in large-scale context. This paper proposes a scatter search-based solution to configure service function chain. The aim is to produce the optimal number and placement of the required virtual network functions with the dynamic traffic steering over them. This is done while respecting computing and network resources constraints.

A scatter search algorithm to configure service function chaining

Network functions virtualisation (NFV) emerges to deal with the challenges of reducing both the capital expenses (CAPEX) and operational expenses (OPEX) of cloud providers. The NFV is done by implementing network functions and providing them as software commodities. Network services are provided by chaining a set of network functions together. The key problem will be how and where network functions should be placed in the network and how traffic is routed through them. This is the well-known service function chaining problem and it is known to be NP-hard so exhaustive search algorithms have no significant benefit in large-scale context. This paper proposes a scatter search-based solution to configure service function chain. The aim is to produce the optimal number and placement of the required virtual network functions with the dynamic traffic steering over them. This is done while respecting computing and network resources constraints.

Dynamic traffic steering based on fuzzy Q-Learning approach in a multi-RAT multi-layer wireless network

The infrastructure of current cellular networks must evolve to cope with the increasing demand for mobile-broadband services. Heterogeneous networks are an attractive solution for operators to expand network capacity, based on deploying different Radio Access Technologies, cell sizes and carrier frequencies in the same environment. As a result, operators gain flexibility to distribute traffic across the different networks (or layers) in order to make a more efficient use of resources and enhance network performance. In this work, a dynamic traffic steering technique in multi-RAT multi-layer wireless networks is proposed. In particular, a fuzzy rule-based reinforcement learning algorithm modifies handover parameters according to a specific policy set by the operator, which typically searches for a trade-off between key performance indicators. Results show that the proposed optimization algorithm provides good flexibility to support different policies by simply adjusting some weighting factors. In addition, the Q-Learning algorithm is shown as an effective solution to adapt the network to context variations, such as those produced in the user spatial distribution.