Meintanis, I.I.MeintanisMonios, N.N.MoniosLivieris, I.E.I.E.LivierisKampourakis, M.M.KampourakisFourakis, S.S.FourakisKyriakoulis, N.N.KyriakoulisKokkorikos, S.S.KokkorikosChondronasios, A.A.Chondronasios2021-01-152021-01-152020-11-26Technologie- und Klimawandel: Energie-Gebäude-Umwelt, 465-471978-3-7011-0460-4http://hdl.handle.net/20.500.11790/1395Science.Research.Pannonia. 22Forecasting the building energy consumption constitutes a significant factor for a wide variety of applications including planning, management and optimization. Nowadays, research is focused towards the development of more efficient and sustainable energy management systems which focus on minimising energy waste. These systems are based on intelligent models, which provide accurate predictions of future energy demand/load, both at aggregate and individual site level. In this work, we present a holistic integrated solution for the buildings’ energy management systems using deep learning methods. The proposed solution is based on efficient deep-learning forecasting models for short-term local weather parameters and energy load consumption. The developed forecasting models are integrated into the smart energy management system of the building for taking the proper decisions to ensure efficient utilization of energy resources.eninfo:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-nd/4.0/Konferenzbeitrag