Geospatial complex event processing in smart city applications

• Published in: Simulation modelling practice and theory 2023-01, Vol.122, p.102675, Article 102675
• Main Authors: Khazael, Behnam, Vahidi Asl, Mojtaba, Tabatabaee Malazi, Hadi
• Format: Article
• Language: English
• Subjects: Complex event processing; Edge computing; Smart city; Spatio-temporal stream processing; T-Rex engine; TESLA language
• ISSN: 1569-190X; 1878-1462
• DOI: 10.1016/j.simpat.2022.102675

The extensive deployment of the Internet of things (IoT) devices in urban areas enables smart city systems (e.g., urban traffic detection and air pollution monitoring) to use these devices to discover the affected regions by various events, particularly complex ones. A complex event is inferred from patterns of different individual primitive events according to their spatio-temporal information. Complex event processing (CEP) systems facilitate applications to define their reasoning rules based on event processing languages (EPL), similar to SQL. However, current languages and CEP engines do not efficiently support spatial data characteristics. Geospatial CEP is challenging since applications have diverse definitions for complex events (e.g., air quality index), IoT devices have heterogeneous specifications/capabilities, and complex events may happen concurrently. This paper proposes the Geo-Tesla language that enables smart city applications to define spatial attributes in complex event definitions and reasoning rules. Then, we devise the GeoT-Rex CEP engine that implements geospatial operations that compiles Geo-Tesla language and processes the spatial data. The integration of Geo-Tesla and GeoT-Rex enables applications to process complex events with spatial characteristics in their reasoning rules and identify boundaries of the detected complex event (event footprint). The evaluation results from the proof of concept implementation show that our proposed solution outperforms in identifying the footprint of complex events up to 44% in the largest network size. They also show that the detection percentage in the concurrent appearance of complex events is 40% more on average than a close state-of-the-art baseline. •Devise the GeoT-Rex complex event (CE) detection engine to support spatial attributes.•Propose Geo-Tesla CE process language to identify complex event footprints.•Publicly available proof of concept implementation, combining GeoT-Rex and Geo-Tesla.•Evaluate the proposed system regarding detected CEs, detected CE areas, and processing delays.