Experimental validation of autonomic traffic engineering

Abstract

Traffic engineering (TE) is dealing with the issue of performance evaluation and optimization of networks. TE mechanisms have been widely exploited in the past and current networks, however their corresponding TE solutions are unfavorable for the next generation networking paradigms. To overcome the ever-increasing size and complexity of network management, Autonomic Network Management (ANM) and Software Define Networking (SDN) have been recognized as emerging solutions. On the one hand, autonomicity and self-adaptation are key factors for taking fast, online and reliable TE decisions. On the other hand, TE mechanisms in SDN can be much more efficiently and intelligently implemented as a centralized TE system. Therefore, we designed a framework that integrates ANM and SDN in order to provide a realistic solution to the complexity of network management. In this context, we designed an autonomic TE mechanism that addresses the problem of policy-based TE in core networks. In this work, we validate the performance of this mechanism, using the framework that integrates ANM / SDN and performing experiments over the OpenFlow testbed of GEANT.