On Comparing the Performance of Dynamic Multi-Network Optimizations

With a large variety of wireless access technologies available, multi-homed devices may strongly improve the performance and reliability of communication when using multiple networks simultaneously. A key question for the practical application of multi-path strategies is the granularity at which the traffic streams should be dispersed among the available networks. This level of granularity may be expected to have a major impact on both the efficiency and complexity of practical realizations. Motivated by this, we compare two dynamic strategies that operate at different levels of granularity. The first strategy, which we call network selection, requires little operational complexity and dynamically assigns an arriving application data transfer to the network that delivers the highest expected performance. Our second strategy, which we call traffic-splitting, is of higher complexity and aims to optimally split individual data transfers among the available networks. To this end, we (1) develop quantitative models that describe the performance of both strategies, (2) determine the (near-)optimal algorithms for both strategies, and (3) validate the efficiency and practical usefulness of the algorithms via extensive network simulations and experiments in a real-life testbed environment. These experimental results show that the optimal strategies obtained from the theoretical models lead to extremely well-performing solutions in practical circumstances. Moreover, the results show that the splitting of data transfers, which is easy to embed in the network requiring no information on the number of flows in the system, leads to a much better performance compared to dynamic network selection.