Decentralized Stratified Sampling for Low-Latency Approximate Geospatial Data Stream Processing in Edge-Cloud Architectures

2026-05-03

AI Summary

This study addresses the limitations of traditional cloud-centric processing of geospatial data streams, which suffers from excessive bandwidth consumption and high latency, hindering real-time analytics. To overcome these challenges, the authors propose EdgeApproxGeo, an edge-cloud collaborative architecture featuring EdgeSOS—a novel decentralized, geography-aware stratified sampling algorithm. EdgeSOS enables online sampling at the edge using geohashing without requiring node synchronization, and integrates spatially aware data distribution with Kafka topic routing to support low-latency approximate queries. A prototype built on Apache Kafka and Spark is evaluated on real-world mobility and air quality datasets, demonstrating significant speedup over cloud-only approaches. At an 80% sampling rate, the system achieves a mean absolute percentage error (MAPE) below 10%, with Geohash-5 reducing error by approximately 30% compared to Geohash-6, highlighting a tunable trade-off between spatial granularity and the accuracy-efficiency balance.

Abstract

The exponential growth of geospatial data streams flowing from IoT devices challenges conventional cloud-based analytics, which typically suffer from network bandwidth waste and latency, basically attributed to the data being managed completely by Cloud, such as centralized sampling. To address this gap, we propose EdgeApproxGeo, a novel edge-cloud architecture that performs spatial-stratified online sampling at network edge devices near data sources. Our system introduces a novel sampling method called EdgeSOS, which is a unique decentralized, geohash-based stratified sampling algorithm designed to operate independently at resource-constrained edge nodes without cross-node synchronization, coupled with spatial-aware data distribution and topic routing in Apache Kafka data stream ingestion, aiming at optimizing downstream data stream processing analytics. We evaluated our system on two real-world geo-referenced datasets, mobility and air quality, and EdgeApproxGeo achieves a significant speedup over cloud-only baselines while maintaining errors in check (e.g., MAPE < 10% error rate at 80% sampling rate). We further demonstrate that coarser geohash granularity (e.g., Geohash-5) can reduce error figures by 30% as compared to finer counterparts (i.e., Geohash-6), thus revealing a tunable accuracy-efficiency trade-off. Our standard-compliant prototype, built atop Apache Kafka and Apache Spark, further validates the utility of edge-deployed approximate query processing for real-time big geospatial data analytics.

Problem

• geospatial data streams
• edge-cloud architecture
• low-latency processing
• approximate sampling
• decentralized sampling

Innovation

• decentralized stratified sampling
• edge-cloud architecture
• geohash-based sampling
• approximate stream processing
• spatial-aware routing