Machine Learning and Data Mining Applications in Power Systems

• Autore: Leonowicz Zbigniew
• Pubblicazione: Basel, : MDPI - Multidisciplinary Digital Publishing Institute, 2022
• Descrizione fisica: 1 online resource (314 p.)
• Soggetto topico: Energy industries and utilities; History of engineering and technology; Technology: general issues
• Soggetto non controllato: 2-150 kHz; agglomerative; ANFIS; battery energy storage systems (BESS); binary-coded genetic algorithms; cluster analysis; cluster analysis (CA); clustering; conducted disturbances; COVID-19; critical infrastructure; Data Injection Attack; data mining; demand response; demand-side management; demographic characteristic; dictionary impulsion; different batteries; discrete cosine transform; discrete Haar transform; discrete wavelet transform; distributed energy resources; distributed energy resources (DER); energy management; energy storage systems; energy storage systems (ESS); frequency estimation; fuzzy logic; global index; harmonics, cancellation, and attenuation of harmonics; Hidden Markov Model; home energy management; household energy consumption; induction generator; integrated renewable energy system; intentional emission; K-means; load profile; long-term assessment; low-voltage networks; machine learning; mains signalling; MPPT; n/a; neural network; non-intentional emission; nonlinear loads; off-grid microgrid; optimal power scheduling; optimization techniques; Power Line Communications (PLC); power network disturbances; power quality; power quality (PQ); power system; power systems; renewable energy; short term conditions; short-term forecast; singular value decomposition; smart grid; smart grids; social distancing; sparse signal decomposition; spectrum interpolation; supervised dictionary learning; supraharmonics; THDi; time series; time-varying reproduction number; transient stability assessment; variable speed WECS; virtual power plant; virtual power plant (VPP); water treatment plant; waveform distortion; wind energy; wind energy conversion system
• Persona (resp. second.): JasińskiMichał; LeonowiczZbigniew
• Sommario/riassunto: This Special Issue was intended as a forum to advance research and apply machine-learning and data-mining methods to facilitate the development of modern electric power systems, grids and devices, and smart grids and protection devices, as well as to develop tools for more accurate and efficient power system analysis. Conventional signal processing is no longer adequate to extract all the relevant information from distorted signals through filtering, estimation, and detection to facilitate decision-making and control actions. Machine learning algorithms, optimization techniques and efficient numerical algorithms, distributed signal processing, machine learning, data-mining statistical signal detection, and estimation may help to solve contemporary challenges in modern power systems. The increased use of digital information and control technology can improve the grid's reliability, security, and efficiency; the dynamic optimization of grid operations; demand response; the incorporation of demand-side resources and integration of energy-efficient resources; distribution automation; and the integration of smart appliances and consumer devices. Signal processing offers the tools needed to convert measurement data to information, and to transform information into actionable intelligence. This Special Issue includes fifteen articles, authored by international research teams from several countries.
• Titolo autorizzato: Machine Learning and Data Mining Applications in Power Systems
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910576877503321
• Lo trovi qui: Univ. Federico II