Revisiting available bandwidth estimation tools in contemporary hybrid networks: Gigabit ethernet with last-hop 802.11n Wi-Fi

Abstract

High-speed and wireless network environments pose substantial challenges to the accuracy and reliability of available-bandwidth (avail-bw) estimation, particularly in hybrid access networks integrating high-capacity wired cores with variable wireless edges. A common deployment combines a Gigabit Ethernet (GigE) backbone with a last-hop IEEE 802.11n Wi-Fi link, providing high nominal capacity while exhibiting significant temporal variability caused by contention, stochastic channel behavior, and non-stationary traffic dynamics. This configuration reflects real-world networks where stable wired infrastructure coexists with wireless technologies subject to variable channel conditions and competing traffic. Despite newer wireless standards, IEEE 802.11n remains widely deployed in end-user devices and continues to support last-hop connectivity. This mixed wired–wireless environment provides a realistic setting for evaluating classical avail-bw estimation tools. Accordingly, this study experimentally evaluates established end-to-end avail-bw estimation tools under realistic mixed-technology conditions. DietTOPP, PTR, and Pathwave are assessed on a real-world testbed integrating GigE with a last-hop 802.11n Wi-Fi link. Using the D-ITG cross-traffic generator, diverse traffic patterns and controlled crossing and contending traffic scenarios are emulated. Results reveal significant accuracy degradation under non-stationary and concurrent loads, highlighting the limitations of existing tools and the need for wireless-aware, traffic-adaptive avail-bw estimation techniques for modern hybrid networks.