This study presents an innovative machine learning-based approach to estimate node voltages in Medium Voltage distribution networks. It combines a Graph Convolutional Network with a Gradient-Boosted Decision Tree, achieving low estimation errors while significantly reducing computational time, therefore offering fast solutions for complex scenarios like extended and multi-energy networks.<\/p>\n","protected":false},"author":93,"featured_media":0,"comment_status":"open","ping_status":"closed","template":"","meta":{"_acf_changed":false,"footnotes":""},"tags":[652,1325,1315],"targets":[1317],"pubblicazioni_tipologie":[778],"class_list":["post-203801","pubblicazioni","type-pubblicazioni","status-publish","hentry","tag-active-networks","tag-electrical-system","tag-smart-grids-en","targets-research","pubblicazioni_tipologie-paper-en"],"acf":{"dont_show_hompage":true,"projects":{"ID":188404,"post_author":"464","post_date":"2024-06-13 15:10:10","post_date_gmt":"2024-06-13 13:10:10","post_content":"","post_title":"Digitalization of the integrated energy system","post_excerpt":"The project studies the possibilities of using emerging technologies in computing, telecommunications and artificial intelligence and develops methods, tools, algorithms, demonstration platforms and experiments for the digitalization and integration of energy systems.","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"digitalization-of-the-integrated-energy-system","to_ping":"","pinged":"","post_modified":"2024-09-05 13:18:31","post_modified_gmt":"2024-09-05 11:18:31","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.rse-web.it\/progetti\/digitalization-of-the-integrated-energy-system\/","menu_order":0,"post_type":"progetti","post_mime_type":"","comment_count":"0","filter":"raw"},"order_posts":"","dont_show_search":false,"related_posts":false,"show_on_slider":false,"single_post_data":{"titolo_spot":"","post_content":"
Smart grids represent an evolution of traditional electrical systems, integrating new technologies to enhance the monitoring and control of electrical system operations. In this context, machine learning techniques, particularly deep learning algorithms or ensemble methods, offer valuable tools for extracting information from the vast amount of data collected by smart grid components.<\/p>\n
<\/p>\n
Additionally, the use of ontologies capable of representing the topology of energy networks enables the application of processing techniques and artificial intelligence algorithms specific to graph structures. In this study, we introduce a novel machine learning-based approach for estimating node voltages in Medium Voltage distribution networks, typically derived from power flow computations.<\/p>\n
<\/p>\n
Our solution employs a hybrid strategy characterized by stacking a Graph Convolutional Network model and a Gradient-Boosted Decision Tree model. This method achieves an estimation error that adheres to constraints, thus mitigating the need for penalties imposed by the power supplier, while also substantially reducing computational time compared to conventional solutions.<\/p>\n
<\/p>\n
Our approach could be more relevant for obtaining fast responses in scenarios not easily solvable through numerical techniques, such as in the case of extended and multi-energy networks.<\/p>\n","scarica_file":false,"link_estreno":[{"link_text":"Download Publication","link":"https:\/\/ieeexplore.ieee.org\/document\/10761306"}],"button":{"text":"","link":""},"referente_group":false,"data_emissione":"2024-09-20","autori":"L. Gori, A. Verosimile, A. Damiani, M. D. Santambrogio (Politecnico di Milano), F. Soldan, E. Bionda, C. Tornelli (RSE S.p.A.)","destinazione":"IEEE 8th Forum on Research and Technologies for Society and Industry Innovation (RTSI), Lecco 18-20 Settembre 2024","rif_rse":"24004678"},"satellite_post_url":""},"yoast_head":"\n