A Proactive Service Model Facilitating Stream Data Fusion and Correlation

Abstract

Stream data from devices and sensors is considered a typical kind of big data. Though being promising, they have a good prospect only when we can reasonably correlate and effectively use them. Herein, services come back to the spotlight. The paper reports some of the authors' efforts in promoting service-based fusion and correlation of such stream data in a real setting – monitoring and optimized coordination of individual devices in a power plant. This paper advocates a decentralized and service-based approach to dynamically correlating the sensor data and proactively generating higher-level events between sensors and applications. A novel service model for transforming and correlating massive stream data is proposed. This service model shows potential in realizing various middle-way programmable nodes to form larger-granularity and software-defined ‘sensors' in an IoT context.

A Correlation Driven Approach with Edge Services for Predictive Industrial Maintenance

“…We further test our approach’s performance under edge computing paradigm and cloud computing paradigm [ 5 , 6 ] with different data source numbers, i.e., number of physical sensors. We use the following indicator.…”

“…Therefore, we need an abstraction of these sensors at the software layer. Our previous works [ 4 , 5 , 6 ] proposed a proactive data service model, which is the abstraction and lays foundation for this paper.…”

“…A service event correlation will be encapsulated into a service hyperlink if p ≥ δ p , where δ p is a probability threshold. Details of service event correlation encapsulation can be found in our previous works [ 5 , 6 ].…”

“…In our previous works, we proposed a service-based framework to dynamically correlating the sensor data and generating higher-level events between sensors and applications [ 4 , 5 , 6 ]. We mapped physical sensors into a software-defined abstraction deployed in the cloud, called proactive data service.…”

An Anomaly Detection Algorithm Selection Service for IoT Stream Data Based on Tsfresh Tool and Genetic Algorithm

“…For example, streaming as a service is studied by many researchers [3][4][5], which can provide the sharing and simple processing capabilities for stream data. e idea of choosing suitable service or methods can be referred to in [6][7][8]. It is proposed to provide common functions for various data sources, which enable users to conveniently reuse these functions and form more complex functions through service composition.…”