Machine Learning for Energy Systems

• Autore: Sidorov Denis N
• Pubblicazione: Basel, Switzerland, : MDPI - Multidisciplinary Digital Publishing Institute, 2020
• Descrizione fisica: 1 electronic resource (272 p.)
• Soggetto topico: History of engineering & technology
• Soggetto non controllato: vacuum tank degasser; rule extraction; extreme learning machine; classification and regression trees; wind power: wind speed: T–S fuzzy model: forecasting; linearization; machine learning; photovoltaic output power forecasting; hybrid interval forecasting; relevance vector machine; sample entropy; ensemble empirical mode decomposition; high permeability renewable energy; blockchain technology; energy router; QoS index of energy flow; MOPSO algorithm; scheduling optimization; Adaptive Neuro-Fuzzy Inference System; insulator fault forecast; wavelet packets; time series forecasting; power quality; harmonic parameter; harmonic responsibility; monitoring data without phase angle; parameter estimation; blockchain; energy internet; information security; forecasting; clustering; energy systems; classification; integrated energy system; risk assessment; component accident set; vulnerability; hybrid AC/DC power system; stochastic optimization; renewable energy source; Volterra models; wind turbine; maintenance; fatigue; power control; offshore wind farm; Interfacial tension; transformer oil parameters; harmonic impedance; traction network; harmonic impedance identification; linear regression model; data evolution mechanism; cast-resin transformers; abnormal defects; partial discharge; pattern recognition; hierarchical clustering; decision tree; industrial mathematics; inverse problems; intelligent control; artificial intelligence; energy management system; smart microgrid; optimization; Volterra equations; energy storage; load leveling; cyber-physical systems
• Persona (resp. second.): SidorovDenis N
• Sommario/riassunto: This volume deals with recent advances in and applications of computational intelligence and advanced machine learning methods in power systems, heating and cooling systems, and gas transportation systems. The optimal coordinated dispatch of the multi-energy microgrids with renewable generation and storage control using advanced numerical methods is discussed. Forecasting models are designed for electrical insulator faults, the health of the battery, electrical insulator faults, wind speed and power, PV output power and transformer oil test parameters. The loads balance algorithm for an offshore wind farm is proposed. The information security problems in the energy internet are analyzed and attacked using information transmission contemporary models, based on blockchain technology. This book will be of interest, not only to electrical engineers, but also to applied mathematicians who are looking for novel challenging problems to focus on.
• Titolo autorizzato: Machine Learning for Energy Systems
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910557678803321
• Lo trovi qui: Univ. Federico II