[PVLDB] Edge Computing for Spatiotemporal Quantile Monitoring

We have a research paper “Efficient and Error-Bounded Spatiotemporal Quantile Monitoring in Edge Computing Environments” accepted by PVLDB vol. 15. The abstract is as follows.

Underlying many types of data analytics, a spatiotemporal quantile monitoring (SQM) query continuously returns the quantiles of a data set observed in a spatiotemporal range. In this paper, we study SQM in an IoT-based edge computing environment, where concurrent SQM queries share the same infrastructure asynchronously. Our goal is to minimize query latency while providing result accuracy guarantees. To this end, we design a processing framework that virtualizes edge-resident data sketches for quantile computing. Within the framework, a coordinator edge node manages edge sketches and synchronizes the edge sketch processing and query executions. The coordinator also controls the processed data fractions of edge sketches, which helps to achieve the optimal latency with error-bounded results for each single query. To support concurrent queries, we employ a grid to decompose queries into subqueries and process them efficiently using shared edge sketches. We also devise a relaxing algorithm to converge to optimal latencies for those subqueries whose result errors are still bounded. We evaluate our proposals extensively using two high-speed streaming datasets in a simulated IoT setting with edge nodes. The results show that our proposals achieve efficient, scalable, and error-bounded SQM.

This is a work collaborated with collogues from SUSTECH and RUC. We look forward to presenting this work in VLDB 2022.