Intelligent Routing Orchestration for Ultra-Low Latency Transport Networks

Abstract

Autonomous driving scenarios face the need for millisecond real-time response, which has led to the study of mobile networks with high speed and ultra-low latency. Software-defined networking (SDN) is recognized as a key technology for next-generation networks because it contains advanced functions such as centralized control, software-based traffic analysis, and forwarding rules for dynamic updates. In this paper, an SDN with flexible architecture is considered and a transport component is proposed. The component based on mesh topology is an example of joint route prediction and forwarding. First, different from existing transport protocols, the component can adopt a software-defined stream access control strategy that includes an extended forwarding mechanism (retransmission) to improve the shortterm response performance. Second, we evaluate the impact of route prediction on transport network performance by using offline training and prediction. The key challenge here is that a suitable model needs to be trained from a limited training sample dataset, which will dynamically update the forwarding rules based on current and historical facts (network data). By introducing a parallel neural network classifier, an intelligent route arrangement is implemented in this work. Experimental results over different traffic patterns verify the advantages of the design. Not only does it enhance the flexibility of SDN, but it also significantly reduces the signaling overhead of the transport network without reducing the network throughput.INDEX TERMS SDN, traffic control, routing, machine learning, prediction.

Review on Machine Learning for Intelligent Routing, Key Requirement and Challenges Towards 6G

“…The suggested method is highly accurate at determining the appropriate path combinations. The author in [42] analyses the effect of route prediction on the performance of the transport network. In order to effectively perform fast inference and lower the cost of control information exchange, the central controller uses a DNN classifier to predict the path sequence.…”

A service‐aware transport layer framework for SDN‐enabled cellular core networks

“…State-of-the-art activities on reducing E2E delay in cellular CNs include optimization-based approaches [19,20] and customized transport layer protocols [21,22]. Qu et al in [19] suggested a dynamic flow migration strategy in 5G CNs with constrained resources for delay-sensitive services.…”

“…Results proved that their transport protocol could achieve a lower E2E delay when compared to the conventional transport layer protocol. [22] proposed an SDN‐based architecture and a transport protocol for reducing latency. Their proposed path selection algorithm could outperform the open shortest path first (OSPF) approach.…”

“…State‐of‐the‐art activities on reducing E2E delay in cellular CNs include optimization‐based approaches [19, 20] and customized transport layer protocols [21, 22]. Qu et al.…”

Lifetime Maximization for 5G Mobile Networks using Secured and Finest Optimal Routing Protocol

“…Essentially, the part can receive a product characterized stream access control procedure that incorporates an allinclusive sending component (retransmission) to improve the transient reaction execution. At that point the effect of route forecast on transport network execution is finished by utilizing offline preparing and prediction [10]. QoS mindful organization design and multipath sending approach was acquainted all together with deal with the SDN activity empowered Open Virtual Switches (OVSs).…”