Opportunistic traffic scheduling in cellular data networks

Cellular data networks are experiencing a serious capacity crunch in the face of exponential increase in mobile data traffic volume. New traffic management techniques are needed to improve network and user perceived performance. In this work, we consider the existence of a higher-layer, agent-based scheduling system that could potentially delay scheduling of low priority flows at peak loads. The priorities are assumed to be user or application tagged, either automatically or manually. The general goal is to potentially move the low priority flows in time and space opportunistically to reduce the overall resource needs. We develop and evaluate two scheduling schemes-one based on a straightforward greedy method that requires real-time load monitoring and the other based on model-based estimation of traffic loads and subscriber mobility based on historical data. Simulation results using a large-scale cellular network trace data collected inside a nationwide network show the potential of these approaches in reducing base station resource requirements. This indirectly demonstrates that if providers can incentivize subscribers to tag certain flows as low priority, they can potentially accommodate a significant number of additional subscribers in the same network without expending any additional resource.