
Istraživanje se fokusira na sljedeće doprinose: • Arhitektura generičkog radnog okvira s predlošcima komponenti za napredne analitičke alate s ciljem ugradnje u SCADA-sustave vođene događajima • Metamodel za definiranje agregiranih podataka iz SCADA sustava i vanjskih izvora s ciljem opisa sučelja generičkog okvira • Prototip sustava implementiranog generičkim radnim okvirom s primjenom u području energetike Prvo, dan je pregled najboljih metoda ugradnje naprednih analitičkih modela u SCADA-sustave vođene događajima. Dan je pregled raznih načina kako se napredne analitičke metode poput strojnog učenja ili mekog računarstva koriste za proširivanje funkcionalnosti SCADA-sustava. Dizajniran je podatkovni metamodel koji spaja podatkovni model SCADA-sustava sa skupovima podataka koje koriste napredni analitički modeli. Ovo je temelj za dizajn generičkog radnog okvira za brzu izgradnju prototipova naprednih analitičkih komponenti SCADA-sustava. Dan je opis implementacije i načina korištenja generičkog okvira, a nakon toga i stvarni primjeri uporabe radnog okvira za probleme predviđanja vrijednosti mjerenja ili procjene stanja električne mreže.
The research sets out to show the following contributions: • Generic framework architecture with component templates for advanced analytics, with the goal of integration into event-driven SCADA systems. • Metamodel for the aggregated data from the SCADA system and external sources, with the goal of the description of the generic framework interfaces. • Prototype of the system applicable in the field of electric power systems. First, an overview of the different ways advanced analytics like machine learning or soft com- puting are used to enhance the functionality of SCADA systems is given. A data metamodel is constructed, connecting SCADA system data models with datasets used by advanced analytics. This serves as a basis for designing a generic framework that can be used for fast prototyping of advanced analytical SCADA components. An overview of the framework implementation and use is given, followed by realistic examples of the framework use like measurement fore- casting or state estimation. The thesis concludes by comparing the research with the anticipated contributions, confirming them.
meko računarstvo, machine learning, Computer science and technology. Computing. Data processing, TECHNICAL SCIENCES. Computing., TEHNIČKE ZNANOSTI. Računarstvo., soft computing, dizajn radnog okvira, info:eu-repo/classification/udc/004(043.3), SCADA sustavi, SCADA systems, framework design, Računalna znanost i tehnologija. Računalstvo. Obrada podataka, strojno učenje
meko računarstvo, machine learning, Computer science and technology. Computing. Data processing, TECHNICAL SCIENCES. Computing., TEHNIČKE ZNANOSTI. Računarstvo., soft computing, dizajn radnog okvira, info:eu-repo/classification/udc/004(043.3), SCADA sustavi, SCADA systems, framework design, Računalna znanost i tehnologija. Računalstvo. Obrada podataka, strojno učenje
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
