Cognitive Network Management and Control With Significantly Reduced State Sensing

Future networks have to accommodate an increase of 3 and 4 orders of magnitude in data rates with heterogeneous session sizes and potentially stricter time deadline requirements. The dynamic nature of scheduling of large transactions and the need for rapid actions by the network management and control (NMC) system, require timely collection of network state information. Rough estimates of the size of detailed network states suggest a huge burden for network transport and computation resources. Thus, judicious sampling of network states is necessary for a cost-effective network management system. In this paper, we consider an NMC system where sensing and routing decisions are made with cognitive understanding of network states and short-term behavior of exogenous offered traffic. We study a small but realistic example of adaptive monitoring based on significant sampling techniques. This technique balances the need for updated state information against the updating cost and provides an algorithm that yields near optimum performance with significantly reduced burden of sampling, transport, and computation. We show that our adaptive monitoring system can reduce the NMC overhead by a factor of 100 in one example. The spirit of cognitive NMC is to collect network states ONLY when they can improve the network performance.