An Enhanced Available Bandwidth Estimation Technique for an End-to-End Network Path

This paper presents a unique probing scheme, a rate adjustment algorithm, and a modified excursion detection algorithm (EDA) for estimating the available bandwidth (ABW) of an end-to-end network path more accurately and less intrusively. The proposed algorithm is based on the well-known concept of self-induced congestion and it features a unique probing train structure in which there is a region where packets are sampled more frequently than in other regions. This high-density region enables our algorithm to find the turning point more accurately. When the dynamic ABW is outside of this region, we readjust the lower rate and upper rate of the packet stream to fit the dynamic ABW into that region. We appropriately adjust the range between the lower rate and the upper rate using spread factors, which enables us to keep the number of packets low, and we are thus able to measure the ABW less intrusively. Finally, to detect the ABW from the one-way queuing delay, we present a modified EDA from PathChirps' original EDA to better deal with sudden increase and decrease in queuing delays due to cross traffic burstiness. For the experiments, an Android OS-based device was used to measure the ABW over a commercial 4G/LTE mobile network of a Japanese mobile operator, as well, as real testbed measurements were conducted over fixed and WLAN network. Simulations and experimental results show that our algorithm can achieve ABW estimations in real time and outperforms other stat-of-the-art measurement algorithms in terms of accuracy, intrusiveness, and convergence time.