AWStream: Adaptive Wide-area Streaming Analytics

Abstract

The emerging class of wide-area streaming analytics faces the challenge of scarce and variable WAN bandwidth. Non-adaptive applications built with TCP or UDP suffer from increased latency or degraded accuracy. State-of-the-art approaches that adapt to network changes require developer writing sub-optimal manual policies or are limited to application-specific optimizations. We present AWStream, a stream processing system that simultaneously achieves low latency and high accuracy in the wide area, requiring minimal developer efforts. To realize this, AWStream uses three ideas: (<i>i</i>) it integrates application adaptation as a first-class programming abstraction in the stream processing model; (<i>ii</i>) with a combination of offline and online profiling, it automatically learns an accurate profile that models accuracy and bandwidth trade-off; and (<i>iii</i>) at runtime, it carefully adjusts the application data rate to match the available bandwidth while maximizing the achievable accuracy. We evaluate AWStream with three real-world applications: augmented reality, pedestrian detection, and monitoring log analysis. Our experiments show that AWStream achieves sub-second latency with only nominal accuracy drop (2-6%).