Low latency and efficient packet scheduling for streaming applications

Abstract

Adequate bandwidth allocations and strict delay requirements are required for real time flows, such as streaming audio and video data. Most of commonly known packet scheduling algorithms like Weighted Fair Queueing (WFQ) and Start-Time Fair Queueing (SFQ) were mainly designed to ensure the bandwidth reservation function. They only guarantee the queueing delay under a certain threshold. It may cause unsteady packet latencies and introduces extra handling overheads for streaming applications. A few packet scheduling algorithms were proposed in recent years to address this problem like Low Latency Queueing (LLQ) which may suffer from low priority traffic starvation problem. In this paper, we will show the unsteady queueing delay problem, ‘The buffer underrun problem’ for most well known packet scheduling algorithms. We propose a novel packet scheduling algorithm with history support, LLEPS, to ensure low latency and efficient packet scheduling for streaming applications via monitoring the behavior of queues and traffics.