Improved wind speed forecasts can help urban

Researchers at Concordia University present a new wind speed forecasting model that they say can help urban microgrids plan and manage electricity generation. Navid Shirzadi Ph.D. used data from a Weibull probability distribution and numerical weather prediction models and fed it into a recurrent neural network. He says his model improves forecasting by over 30 percent over a 48-horizon.

Related Keywords

Montreal ,Quebec ,Canada ,Germany ,Canadian ,Pilar Monsalvete ,Anton Kaifel ,Ursula Eicker ,Ramanunni Menon ,Fuzhan Nasiri ,Recurrent Neural Networks ,Gina Cody School Of Engineering ,Centre For Solar Energy ,Department Of Building ,International Energy Agency ,Hydrogen Research In Stuttgart ,Canada Excellence Research ,Agency Institutional Program Secretariat ,Concordia University ,Method Of Research ,Generation Cities Institute ,Environmental Engineering ,Gina Cody School ,Computer Science ,Navid Shirzadi ,Long Short Term Memory ,Next Generation Cities Institute ,Net Zero Emissions ,Canada Excellence Research Chair ,Resilient Cities ,Solar Energy ,Hydrogen Research ,Tri Agency Institutional Program ,Urban Wind Power Forecasting ,Integrating Weibull Distribution ,Numerical Weather ,