Reprint

AI Applications to Power Systems

Edited by
March 2022
156 pages
  • ISBN978-3-0365-3653-8 (Hardback)
  • ISBN978-3-0365-3654-5 (PDF)

This is a Reprint of the Special Issue AI Applications to Power Systems that was published in

Chemistry & Materials Science
Engineering
Environmental & Earth Sciences
Physical Sciences
Summary

Today, the flow of electricity is bidirectional, and not all electricity is centrally produced in large power plants. With the growing emergence of prosumers and microgrids, the amount of electricity produced by sources other than large, traditional power plants is ever-increasing. These alternative sources include photovoltaic (PV), wind turbine (WT), geothermal, and biomass renewable generation plants. Some renewable energy resources (solar PV and wind turbine generation) are highly dependent on natural processes and parameters (wind speed, wind direction, temperature, solar irradiation, humidity, etc.). Thus, the outputs are so stochastic in nature. New data-science-inspired real-time solutions are needed in order to co-develop digital twins of large intermittent renewable plants whose services can be globally delivered.

Format
  • Hardback
License and Copyright
© 2022 by the authors; CC BY-NC-ND license
Keywords
self-healing grid; machine-learning; feature extraction; event detection; optimization techniques; manta ray foraging optimization algorithm; multi-objective function; radial networks; optimal power flow; automatic P2P energy trading; Markov decision process; deep reinforcement learning; deep Q-network; long short-term delayed reward; inter-area oscillations; modal analysis; reduced order modeling; dynamic mode decomposition; machine learning; artificial neural networks; steady-state security assessment; situation awareness; cellular computational networks; load flow prediction; contingency; fuzzy system; change detection; data analytics; data mining; filtering; machine learning; optimization; power quality; signal processing; total variation smoothing; n/a