%0 Journal Article
	%A Tomohiro Hachino and  Hitoshi Takata and  Seiji Fukushima and  Yasutaka Igarashi
	%D 2014
	%J International Journal of Electrical and Computer Engineering
	%B World Academy of Science, Engineering and Technology
	%I Open Science Index 86, 2014
	%T Short-Term Electric Load Forecasting Using Multiple Gaussian Process Models
	%U https://publications.waset.org/pdf/9998341
	%V 86
	%X This paper presents a Gaussian process model-based
short-term electric load forecasting. The Gaussian process model is
a nonparametric model and the output of the model has Gaussian
distribution with mean and variance. The multiple Gaussian process
models as every hour ahead predictors are used to forecast future
electric load demands up to 24 hours ahead in accordance with the
direct forecasting approach. The separable least-squares approach that
combines the linear least-squares method and genetic algorithm is
applied to train these Gaussian process models. Simulation results
are shown to demonstrate the effectiveness of the proposed electric
load forecasting.

	%P 447 - 452