2026-04-21T01:05:12Zhttps://ebiltegia.mondragon.edu/oai/request

oai:ebiltegia.mondragon.edu:20.500.11984/63792024-05-24T11:21:35Zcom_20.500.11984_1143col_20.500.11984_1148

Data-driven energy resource planning for Smart Cities Larrinaga, Felix Mulero, Sofía Hernández, José L. Vicente, Julia Sáez de Viteri, Patxi smart cities Energy efficiency Energy Planning Digital Services Machine learning Cities are growing and, therefore, the primary needs, such as the energy resources. Hence, managing them in the proper way becomes essential for a sustainable growth. This paper proposes a data-driven tool based on IoT data with the aim of reducing the gap between demand and consumption, minimizing the energy losses. Smart and efficient energy planning is the ultimate objective, where the final energy usage is fitted into the predicted demand. One day time horizon is used in order to provide energy managers, ESCOs or urban planners with an accurate forecast about the required energy. This service will be available on the urban platform of Vitoria under the context of the SmartEnCity project (GA # 691883). However, the training data has been captured from CITyFiED project (GA # 609129), which is energetically speaking similar. The city elements included in the training model have been characterized based on data from combined static and dynamic data to adapt the context through machine-learning techniques. 2024-04-25T14:00:12Z 2024-04-25T14:00:12Z 2020 http://purl.org/coar/resource_type/c_c94f 978-1-7281-6728-2 https://katalogoa.mondragon.edu/janium-bin/janium_login_opac.pl?find&ficha_no=158898 https://hdl.handle.net/20.500.11984/6379 eng © 2020 IEEE IEEE