CIMNE RTD Project: OMELET


Url	https://cimne.com/sgp/rtd/Project.aspx?id=1019

Acronym	OMELET
Project title	Advanced semantic knowledge graph methods for the massive integration of renewables and storage in electrical distribution networks at the district level
Reference	PID2023-152461OB-I00
Principal investigator	Jordi CIPRIANO LINDEZ - cipriano@cimne.upc.edu Stoyan Viktorov DANOV - sdanov@cimne.upc.edu
Start date	01/09/2024	End date	31/08/2027
Coordinator	CIMNE
Consortium members
Program	P.E. para Impulsar la Investigación Científico-Técnica y su Transferencia	Call	Proyectos Generación de Conocimiento 2023
Subprogram	Subprograma Estatal de Generación de Conocimiento	Category	Nacional
Funding body(ies)	MCIU	Grant	$0.00
Abstract	The OMELET project aims to revolutionize the adoption of distributed renewable energy generation systems (DER), electricity storage, and electric vehicle infrastructure in Medium Voltage (MV) and Low Voltage (LV) electricity networks. It focuses on creating a digital twin of the electricity grid using a semantic knowledge graph, employing advanced data-driven technologies. OMELET utilizes a toolbox of physicsinformed Graph-based Neural Network methodologies, including AutoRegressive with exogenous inputs (ARX), recursive least squares, and Support Vector Machines (SVM). The knowledge graph framework enables real-time prediction and control of electrical system operations at the distribution level. OMELET leverages the digitalization of the electrical grid, particularly smart metering and control systems in low voltage networks, to integrate local renewables and storage efficiently. The project envisions an interoperable software framework interconnected via web semantics and artificial intelligence knowledge, optimizing automated Demand Response (DR) and Distributed Energy Resources (DER) within low to mid-voltage electricity networks. Key objectives include increasing the capacity to integrate new electrical consumptions and grid-based services, contributing to the sustained deployment of DER generation systems, and opening new markets for prosumers and aggregators in grid services. OMELET addresses challenges associated with the high penetration of variable generation sources, developing technological solutions to control changes in power flows. The project introduces innovative data integration and modeling tools based on semantic knowledge graph techniques, structured as a multigraph. This approach facilitates a comprehensive understanding of complex data sets and urban energy systems, considering interdependencies between adjacent buildings, neighborhoods, and urban elements. OMELET proposes cutting-edge graph-based software technologies, combining Graph Neural Networks (GNNs), machine learning, and big data analytics to fill the knowledge gap in data-driven urban energy models. The project aims to collect and utilize real information from a LV electricity network managed by the DSO company PEUSA for training and validation purposes. To enhance resilience, OMELET integrates a real-time supervision system with distributed intelligence using Remote Terminal Units (RTU) and applies the "Grid Edge" processing concept. The project envisions three key performance indicators (KPIs) aligned with the European Electricity Grid Initiative guidelines, focusing on the integration capacity of DER and electric vehicles, improvements in LV and MV network operation, and increased capacity and intelligence in network planning and management. The prospective impact of the project is measured by achieving threshold values, including a 25% increase in the integration capacity of DER and EV, a 65% improvement in LV and MV network operation, and a 96% increase in capacity and intelligence in network planning and management. The validation stage involves utilizing a digital twin system for software in the loop (SIL) to work with an emulated distribution grid in real-time, followed by a final stage validation in a real scenario.