Real-Time Event-Driven Learning in Highly Volatile Systems: A Case for Embedded Machine Learning for SCADA Systems
Extracting key system parameters and their impact on state transition is a necessity for knowledge and data engineering. In Decision Support Systems, the quest for yet more efficient and faster methods of sensitivity analysis (SA) and feature extraction in complex and volatile systems persists. A ne...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9770808/ |
| _version_ | 1828213959127203840 |
|---|---|
| author | Manuel Goncalves Pedro Sousa Jerome Mendes Morad Danishvar Alireza Mousavi |
| author_facet | Manuel Goncalves Pedro Sousa Jerome Mendes Morad Danishvar Alireza Mousavi |
| author_sort | Manuel Goncalves |
| collection | DOAJ |
| description | Extracting key system parameters and their impact on state transition is a necessity for knowledge and data engineering. In Decision Support Systems, the quest for yet more efficient and faster methods of sensitivity analysis (SA) and feature extraction in complex and volatile systems persists. A new improved event tracking methodology, the fastTracker, for real-time SA in large scale complex systems is proposed in this paper. The main feature of fastTracker is its high-frequency analytics using meager computational cost. It is suitable for data processing and prioritization in embedded systems, Internet of Things (IoT), distributed computing (e.g. Edge computing) applications. The presented algorithm’s underpinning rationale is event driven; its objective is to correctly and succinctly quantify the sensitivity of observable changes in the system (output) with respect to the input variables. To demonstrate the performance of the proposed fastTracker methodology, fastTracker was deployed in the Supervisory control and data acquisition (SCADA) system from real cement industry. fastTracker has been verified by system experts in real industrial application. Its performance was compared with other real-time event-based SA techniques. The comparison revealed savings of 98.8% in processing time per sensitivity index and 20% in memory usage when compared with EventTracker, its closest rival. The proposed methodology is more accurate and 80.9% faster than an entropy-based method. Its application is recommended for reinforced learning and/or formulating system key performance indicators from raw data. |
| first_indexed | 2024-04-12T14:57:51Z |
| format | Article |
| id | doaj.art-447a61c9b8854c1baa77fa3d39ead579 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T14:57:51Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-447a61c9b8854c1baa77fa3d39ead5792022-12-22T03:28:11ZengIEEEIEEE Access2169-35362022-01-0110507945080610.1109/ACCESS.2022.31733769770808Real-Time Event-Driven Learning in Highly Volatile Systems: A Case for Embedded Machine Learning for SCADA SystemsManuel Goncalves0Pedro Sousa1Jerome Mendes2https://orcid.org/0000-0003-4616-3473Morad Danishvar3https://orcid.org/0000-0002-7939-9098Alireza Mousavi4https://orcid.org/0000-0003-0360-2712Department of Electrical and Computer Engineering, Institute of Systems and Robotics, University of Coimbra, Pólo II, Coimbra, PortugalOncontrol Technologies, Coimbra, PortugalDepartment of Electrical and Computer Engineering, Institute of Systems and Robotics, University of Coimbra, Pólo II, Coimbra, PortugalDepartment of Mechanical and Aerospace Engineering, College of Engineering, Design and Physical Sciences, Brunel University London, London, Uxbridge, U.K.Department of Mechanical and Aerospace Engineering, College of Engineering, Design and Physical Sciences, Brunel University London, London, Uxbridge, U.K.Extracting key system parameters and their impact on state transition is a necessity for knowledge and data engineering. In Decision Support Systems, the quest for yet more efficient and faster methods of sensitivity analysis (SA) and feature extraction in complex and volatile systems persists. A new improved event tracking methodology, the fastTracker, for real-time SA in large scale complex systems is proposed in this paper. The main feature of fastTracker is its high-frequency analytics using meager computational cost. It is suitable for data processing and prioritization in embedded systems, Internet of Things (IoT), distributed computing (e.g. Edge computing) applications. The presented algorithm’s underpinning rationale is event driven; its objective is to correctly and succinctly quantify the sensitivity of observable changes in the system (output) with respect to the input variables. To demonstrate the performance of the proposed fastTracker methodology, fastTracker was deployed in the Supervisory control and data acquisition (SCADA) system from real cement industry. fastTracker has been verified by system experts in real industrial application. Its performance was compared with other real-time event-based SA techniques. The comparison revealed savings of 98.8% in processing time per sensitivity index and 20% in memory usage when compared with EventTracker, its closest rival. The proposed methodology is more accurate and 80.9% faster than an entropy-based method. Its application is recommended for reinforced learning and/or formulating system key performance indicators from raw data.https://ieeexplore.ieee.org/document/9770808/Event Trackingsensitivity analysis (SA)discrete event systemsinput variable selectionreal-time systemsdistributed computing |
| spellingShingle | Manuel Goncalves Pedro Sousa Jerome Mendes Morad Danishvar Alireza Mousavi Real-Time Event-Driven Learning in Highly Volatile Systems: A Case for Embedded Machine Learning for SCADA Systems IEEE Access Event Tracking sensitivity analysis (SA) discrete event systems input variable selection real-time systems distributed computing |
| title | Real-Time Event-Driven Learning in Highly Volatile Systems: A Case for Embedded Machine Learning for SCADA Systems |
| title_full | Real-Time Event-Driven Learning in Highly Volatile Systems: A Case for Embedded Machine Learning for SCADA Systems |
| title_fullStr | Real-Time Event-Driven Learning in Highly Volatile Systems: A Case for Embedded Machine Learning for SCADA Systems |
| title_full_unstemmed | Real-Time Event-Driven Learning in Highly Volatile Systems: A Case for Embedded Machine Learning for SCADA Systems |
| title_short | Real-Time Event-Driven Learning in Highly Volatile Systems: A Case for Embedded Machine Learning for SCADA Systems |
| title_sort | real time event driven learning in highly volatile systems a case for embedded machine learning for scada systems |
| topic | Event Tracking sensitivity analysis (SA) discrete event systems input variable selection real-time systems distributed computing |
| url | https://ieeexplore.ieee.org/document/9770808/ |
| work_keys_str_mv | AT manuelgoncalves realtimeeventdrivenlearninginhighlyvolatilesystemsacaseforembeddedmachinelearningforscadasystems AT pedrosousa realtimeeventdrivenlearninginhighlyvolatilesystemsacaseforembeddedmachinelearningforscadasystems AT jeromemendes realtimeeventdrivenlearninginhighlyvolatilesystemsacaseforembeddedmachinelearningforscadasystems AT moraddanishvar realtimeeventdrivenlearninginhighlyvolatilesystemsacaseforembeddedmachinelearningforscadasystems AT alirezamousavi realtimeeventdrivenlearninginhighlyvolatilesystemsacaseforembeddedmachinelearningforscadasystems |