Continuous fractional-order grey model and electricity prediction research based on the observation error feedback

摘要

As superiority to conventional statistical models, the grey model based on the fractional calculus becomes a hot topic and show great potentials with excellent performance. In this paper, the generalized fractional-order forms for grey models are given, which could have more freedom and better modeling by the fractional derivatives. The case of per capita output of electricity prediction is discussed by the modified optimized fractional grey model using the error feedback. The performance is evaluated and greatly improved in modeling and prediction compared with some traditional grey methods. Due to the fractional derivatives, the novel model could provide the fitting, prediction with more freedom and enrich the content, scope and application of grey theory. (C) 2016 Elsevier Ltd. All rights reserved.