Solar radiation prediction using classical and evolutionary techniques

• Author(s): Coelho, J.P. ; Cunha, José Boaventura ; Oliveira, Paulo
• Date: 2001
• Persistent ID: http://hdl.handle.net/10198/2769
• Origin: Biblioteca Digital do IPB
• Subject(s): Greenhouse; System identification; Evolutionary algorithms; Regressive methods
• Document Type: Article
• Language: English

Description

Modern greenhouse climate controllers are based on models to simulate and predict greenhouse environment behavior. These models must be able to describe indoor climate process dynamics, which is a function of both the control actions taken and outside climate. Moreover, if predictive or feedforward control techniques are to be applied, it is necessary to employ models to describe and predict the weather (solar radiation, air temperature, etc.). In this paper, classical and evolutionary techniques are applied to solar radiation time-series prediction within a greenhouse located in the UTAD campuus. Experimental results are provided and compared for the two tipes of methods.