04293nam a22006015i 4500 978-3-031-47909-0 DE-He213 20251030111403.0 cr nn 008mamaa 240127s2024 sz | s |||| 0|eng d 9783031479090 978-3-031-47909-0 10.1007/978-3-031-47909-0 doi Q342 UYQ bicssc COM004000 bisacsh UYQ thema Machine Learning Applications for Intelligent Energy Management [electronic resource] : Invited Chapters from Experts on the Energy Field / edited by Haris Doukas, Vangelis Marinakis, Elissaios Sarmas. 1st ed. 2024. Cham : Springer Nature Switzerland : Imprint: Springer, 2024. XIV, 226 p. 110 illus., 107 illus. in color. online resource. text txt rdacontent computer c rdamedia online resource cr rdacarrier text file PDF rda Learning and Analytics in Intelligent Systems, 2662-3455 ; 35 AI-Powered Transformation and Decentralization of the Energy Ecosystem -- An Explainable AI-based Framework for Supporting Decisions in Energy Management -- The big data value chain for the provision of AI-enabled energy analytics services -- MODULAR BIG DATA APPLICATIONS FOR ENERGY SERVICES IN BUILDINGS AND DISTRICTS: DIGITAL TWINS, TECHNICAL BUILDING MANAGEMENT SYSTEMS AND ENERGY SAVINGS CALCULATIONS -- Neural network based approaches for fault diagnosis of photovoltaic systems -- Clustering of building stock -- BIG DATA SUPPORTED ANALYTICS FOR NEXT GENERATION ENERGY PERFORMANCE CERTIFICATES -- Synthetic data on buildings. As carbon dioxide (CO2) emissions and other greenhouse gases constantly rise and constitute the main contributor to climate change, temperature rise and global warming, artificial intelligence, big data, Internet of things, and blockchain technologies are enlisted to help enforce energy transition and transform the entire energy sector. The book at hand presents state-of-the-art developments in artificial intelligence-empowered analytics of energy data and artificial intelligence-empowered application development. Topics covered include a presentation of the various stakeholders in the energy sector and their corresponding required analytic services, such as state-of-the-art machine learning, artificial intelligence, and optimization models and algorithms tailored for a series of demanding energy problems and aiming at providing optimal solutions under specific constraints. Professors, researchers, scientists, engineers, and students inenergy sector-related disciplines are expected to be inspired and benefit from this book, along with readers from other disciplines wishing to learn more about this exciting new field of research. Computational intelligence. 64052 Electrical engineering. 65586 Artificial intelligence. 58441 Energy policy. 61992 Energy and state. 66460 Computational Intelligence. 64052 Electrical and Electronic Engineering. 65588 Artificial Intelligence. 58441 Energy Policy, Economics and Management. 66461 Doukas, Haris. editor. edt http://id.loc.gov/vocabulary/relators/edt 69952 Marinakis, Vangelis. editor. edt http://id.loc.gov/vocabulary/relators/edt 69953 Sarmas, Elissaios. editor. edt http://id.loc.gov/vocabulary/relators/edt 69954 SpringerLink (Online service) Springer Nature eBook Printed edition: 9783031479083 Printed edition: 9783031479106 Printed edition: 9783031479113 Learning and Analytics in Intelligent Systems, 2662-3455 ; 35 69955 https://doi.org/10.1007/978-3-031-47909-0 ZDB-2-INR ZDB-2-SXIT 57320 57320