Wind profile prediction using linear Markov chains: A linear algebra approach

To predict the future wind speed and wind direction is of relevance to the wind industry to maximize the power generation. In this regards, this article describes a methodology for the construction of predictive models based on linear Markov chains under linear algebra point of view. The model analy...

Descripción completa

Detalles Bibliográficos
Autores: García Planas, María Isabel|||0000-0001-7418-7208, Gongadze, Tornike
Tipo de recurso: artículo
Fecha de publicación:2018
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/115139
Acceso en línea:https://hdl.handle.net/2117/115139
https://dx.doi.org/10.1109/TLA.2018.8327410
Access Level:acceso abierto
Palabra clave:Eigenvectors
Markov processes
MATLAB
Markov Chains
eigenvectors
eigenvalues
stationary distribution
Espais vectorials
Markov, Processos de
Àrees temàtiques de la UPC::Matemàtiques i estadística
Descripción
Sumario:To predict the future wind speed and wind direction is of relevance to the wind industry to maximize the power generation. In this regards, this article describes a methodology for the construction of predictive models based on linear Markov chains under linear algebra point of view. The model analyzes the direction and speed of the wind obtained from a meteorological station. This Model allows making a precise study of wind direction and speeding data; figure out the stability, the most common direction or speed, its behaviour depending on the hours or seasons.