Efficient traffic splitting in parallel TCP-based wireless networks: Modelling and experimental evaluation

The concurrent use of networks provides a powerful means to boost performance in areas covered by multiple networks where only limited bandwidth is available. However, despite its enormous potential for performance improvement only little is known about how to effectively exploit the potential for performance improvement in practical deployments. This raises the need for traffic-splitting-and-reassembly algorithms that are effective, yet simple and easy-to-deploy. Motivated by this, we first propose a simple analytic flow-level model, called the Concurrent Access Network (CAN) model, that optimally splits traffic in the idealized situation where there is full state information at infinitely fine-grained time granularity, leading to zero synchronization delay during the reassembly phase. Next, we present a new splitting algorithm for TCP-based networks that uses a simple score function to make on-the-fly decisions on the routing of individual TCP segments, based on the measured per-connection RTT, transmission-buffer content and throughput. Then, we use the CAN-model as a benchmark to evaluate the effectiveness and practical usefulness of the score-function based algorithm on real TCP networks in a test-lab environment. Extensive lab experimentation demonstrates that this score-function based splitting of TCP traffic is extremely efficient, leads to close-to-optimal response-time performance and is easily deployable.