Compact Representations for Efficient Storage of Semantic Sensor Data

TL;DR

This paper introduces a compact, factorized representation for semantic sensor data that reduces storage size and significantly improves query processing efficiency, especially in large datasets using Big Data technologies.

Contribution

The paper presents a novel factorized representation for semantic sensor data that minimizes redundancy and enhances storage and query performance over RDF systems.

Findings

Up to 100x reduction in query execution time.

Effective storage optimization for large-scale sensor data.

Improved query processing across diverse RDF implementations.

Abstract

Nowadays, there is a rapid increase in the number of sensor data generated by a wide variety of sensors and devices. Data semantics facilitate information exchange, adaptability, and interoperability among several sensors and devices. Sensor data and their meaning can be described using ontologies, e.g., the Semantic Sensor Network (SSN) Ontology. Notwithstanding, semantically enriched, the size of semantic sensor data is substantially larger than raw sensor data. Moreover, some measurement values can be observed by sensors several times, and a huge number of repeated facts about sensor data can be produced. We propose a compact or factorized representation of semantic sensor data, where repeated measurement values are described only once. Furthermore, these compact representations are able to enhance the storage and processing of semantic sensor data. To scale up to large datasets, factorization based, tabular representations are exploited to store and manage factorized semantic sensor data using Big Data technologies. We empirically study the effectiveness of a semantic sensor's proposed compact representations and their impact on query processing. Additionally, we evaluate the effects of storing the proposed representations on diverse RDF implementations. Results suggest that the proposed compact representations empower the storage and query processing of sensor data over diverse RDF implementations, and up to two orders of magnitude can reduce query execution time.