Scalable On-Demand Network Management Module for Software Defined Telecommunication Networks

Abstract

The design of telecommunication networks and its provisioning is a challenging and complex task, which is constantly influenced by various factors. The disciplines of Traffic Engineering (TE) and Network Management (NM) have addressed these domains with static, semi-automatic and pure self-organizational approaches. Most of the existing approaches usually either relax the problem by taking strong assumptions on the problem instances or by only taking a small portion of the solution space into consideration, thus losing the chance of proving any global optimality gaps. The emerging cloud hosted flexible telecommunication system addressed by the industry nowadays puts new requirements on TE and ND. Current, telecommunication networks are often statically deployed and over-provisioned to cover pre-defined peak data rates, but are inflexible to adapt to dynamic network load situations. This paper presents novel dynamic Traffic Engineering (TE) and adaptive Network Management (NM) approaches for software defined telecommunication networks, which reduce Operational - and Capital Expenditures (OPEX/CAPEX), but also enhance the level of flexibility and elasticity at the same time.