Traffic Valuation using Routing Segmentation for Neural Network Approach

Abstract

Network operators anticipate the offering of an increasing variety of cloud-based services with stringent Service Level Agreements. Technologies currently supporting IP networks however lack the edibility and scalability properties to realize such evolution. In this article, we present Segment Routing (SR), anew network architecture aimed at sling this gap, driven by use cases denied by network operators. SR implements the source routing and tunneling paradigms, letting nodes steer packets over paths using a sequence of instructions (segments) placed in the packet header. As such, SR allows the implementation of routing policies without entries at intermediate routers. This paper introduces the SR architecture, describes its related ongoing standardization efforts, and reviews the main use-cases envisioned by network operators. The criteria for protecting ad hoc networks encompass both physical entity security and data security (authentication, integrity, confidentiality, non-repudiation). Availability is another very significant concern. For example, a robust network should not lose connectivity when a small number of nodes leave the network or become unresponsive. Access control must also be considered to prevent unauthorized access.