A scalable and error-tolerant solution for traffic matrix assessment in hybrid IP/SDN networks
The advent of the Software Defined Networking (SDN) paradigm represents a great opportunity for the definition of new network management solutions. In this work, we focus on the definition and implementation of a novel technique to solve the Traffic Matrix Assessment (TMA) problem from the perspective of an Internet Service Provider. Since the migration from legacy IP networks to fully-deployed SDN ones needs to be incremental due to budget and technical constraints, this paper proposes a mixed measurement and estimation scalable solution for hybrid IP/SDN networks to accurately solve the TMA problem by exploiting the availability of flow rule counters in SDN switches. The performance evaluation shows that our error-Tolerant solution is able to assess the TM with a negligible estimation error by only measuring a small percentage of traffic flows, overcoming other state-of-The-Art algorithms proposed in the literature. Moreover, the performance analysis of the proposed implementation using the OpenDaylight controller over an emulated network environment, shows that a trade-off between the quality of the assessed TM and its impact on the network in terms of control messages can be found by properly tuning the number of measured flows.