A Unified Approach to Optimizing Performance in Networks serving Heterogeneous Flows

In this work, we study the control of communication networks in the presence of both inelastic and elastic traffic flows. The characteristics of these two types of traffic differ significantly. Hence, earlier approaches that focus on homogeneous scenarios with a single traffic type are not directly applicable. We formulate a new network optimization problem that incorporates the performance requirements of inelastic and elastic traffic flows. The solution of this problem provides us with a new queueing architecture, and distributed load balancing and congestion control algorithm with provably optimal performance. In particular, we show that our algorithm achieves the dual goal of maximizing the aggregate utility gained by the elastic flows while satisfying the demands of inelastic flows. Our base optimal algorithm is extended to provide better delay performance for both types of traffic with minimal degradation in throughput. It is also extended to the practically relevant case of dynamic arrivals and departures. Our solution allows for a controlled interaction between the performance of inelastic and elastic traffic flows. This performance can be tuned to achieve the appropriate design tradeoff. The network performance is studied both theoretically and through extensive simulations.