A Real-Time Approach for Smart Building Operations Prediction Using Rule-Based Complex Event Processing and SPARQL Query

TL;DR

This paper presents a real-time, rule-based system combining complex event processing and SPARQL queries to monitor and predict smart building operations, enhancing occupant comfort and safety.

Contribution

It introduces a novel integrated approach using Siddhi, RDF, Kafka, and GraphDB for dynamic, real-time monitoring of smart building IoT data with risk alert capabilities.

Findings

Efficient real-time processing of IoT data streams.

Effective generation of alerts for critical building operations.

Successful visualization of building operation status.

Abstract

Due to intelligent, adaptive nature towards various operations and their ability to provide maximum comfort to the occupants residing in them, smart buildings are becoming a pioneering area of research. Since these architectures leverage the Internet of Things (IoT), there is a need for monitoring different operations (Occupancy, Humidity, Temperature, CO2, etc.) to provide sustainable comfort to the occupants. This paper proposes a novel approach for intelligent building operations monitoring using rule-based complex event processing and query-based approaches for dynamically monitoring the different operations. Siddhi is a complex event processing engine designed for handling multiple sources of event data in real time and processing it according to predefined rules using a decision tree. Since streaming data is dynamic in nature, to keep track of different operations, we have converted the IoT data into an RDF dataset. The RDF dataset is ingested to Apache Kafka for streaming purposes and for stored data we have used the GraphDB tool that extracts information with the help of SPARQL query. Consequently, the proposed approach is also evaluated by deploying the large number of events through the Siddhi CEP engine and how efficiently they are processed in terms of time. Apart from that, a risk estimation scenario is also designed to generate alerts for end users in case any of the smart building operations need immediate attention. The output is visualized and monitored for the end user through a tableau dashboard.