Efficient and error-bounded spatiotemporal quantile monitoring in edge computing environments

Abstract

Underlying many types of data analytics, a spatiotemporal quantile monitoring (SQM) query continuously returns the quantiles of a dataset observed in a spatiotemporal range. In this paper, we study SQM in an Internet of Things (IoT) based edge computing environment, where concurrent SQM queries share the same infrastructure asynchronously. To minimize query latency while providing result accuracy guarantees, we design a processing framework that virtualizes edge-resident data sketches for quantile computing. In the framework, a coordinator edge node manages edge sketches and synchronizes edge sketch processing and query executions. The co-ordinator 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 relaxation algorithm to converge to optimal latencies for those subqueries whose result errors are still bounded. We evaluate our proposals 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.

Spatial data analysis for intelligent buildings: Awareness of context and data uncertainty

“…To make appropriate task decomposition and task assignment among IoT devices, new techniques for profiling IoT devices, modeling tasks' objectives (e.g., processing latency, accuracy, and transmitted data volume), and efficient coordination are required. Recent efforts (Ma et al, 2019;Li et al, 2022) have been made to manage and analyze spatial and spatiotemporal data in the IoT edge computing environments. • Privacy-preserving SDAIB.…”

“…On the one hand, compared to current manually designed models, automated means such as semantic parsing and extraction (Teng et al, 2018 ; Guo et al, 2021 ) can be developed to extract contexts from the physical world; on the other hand, data structures with more powerful expression capabilities such as heterogeneous graphs and hypergraphs (Zhou et al, 2006 ) can be introduced to the modeling framework. In terms of data uncertainty modeling , the framework should support the decentralized data setting (Li et al, 2022 ), i.e., heterogeneous computing nodes generate and consume data with different mechanisms. In this case, the framework should be able to model and analyze the spatial data uncertainty of heterogeneous data nodes, and the merging of such spatial data in different degrees or types of uncertainty.…”