Kyeong-Eun Han

Priority-based grant-aware scheduling for low-latency switching

This paper introduces new scheduling algorithms supporting low-latency switching. The proposed grant-aware (GA) algorithm improves the average delay performance by using the grant information of previous iteration. The simulation result shows that the average delay of GA algorithm is about one-tenth of the existing algorithm in high-load condition. We also introduce two priority-based scheduling algorithms grant-aware and priority-aware (GAPA) algorithm and cyclic scheduling with the longest-queue-first (C-LQF) algorithm. In the priority-based scheduling, the scheduling priority of VoQ is determined based on its queue size. GAPA and C-LQF consider the priority only after the first iteration to prevent the starvation problem. The simulation result shows that GAPA and C-LQF scheduling achieves better performance than GA in terms of average delay, maximum delay, and hotspot throughput.

Scheduling with machine-learning-based flow detection for packet-switched optical data center networks

A scalable, low-latency, high-speed, and energy- efficient data center network is a key element in the deployment of future large-scale data centers, and photonic switching has recently been recognized as a promising solution to fulfill these goals. In this study, we present a packet-switched optical network (PSON) architecture with centralized control for intra-data-center connectivity. For efficient PSON operation, intelligent yet low-complexity bandwidth-scheduling algorithms are critical. To align with realistic traffic flows in a data center, we consider “mice flow,” which occurs frequently but carries a small number of bytes, and “elephant flow,” which occurs occasionally but has a huge number of bytes. To classify traffic flows with different characteristics, we investigate various machine-learning (classification) techniques, such as C4.5 and Naïve Bayes Discretization, and compare their performance in terms of accuracy and classification speed. We also develop a priority-aware scheduling algorithm for packet switching, which is optimized for PSON, and is adaptive to flow classification under a dynamic traffic scenario. Numerical simulations show that our proposed scheduling algorithm assisted by flow-classification techniques can outperform a benchmark algorithm in terms of average delay and packet-loss ratio.

Inter-layer path control with FA-LSP cognitive capability in multi-layer networks

We propose a novel inter-layer path control mechanism in a PCE-VNTM cooperative multi-layer networks (MLN). For this, we define a novel FA-LSP aware PCE which only reports and manages a forwarding adjacency-label switched path (FA-LSP) state. In our scheme, the FA-LSP can be distinguished from the pure higher-layer TE link more and accurately controlled with a network policy. We worked out the methodology and conducted a simulation in terms of the setup delay and the control message overhead under various conditions. Our results indicate that, compared with other representative models, it provides the lowest setup delay of about 300 ms with a 50% reduction in the overhead.