RT info:eu-repo/semantics/article
T1 Improved short-term load forecasting based on two-stage predictions with artificial neural networks in a microgrid environment
A1 Hernández Callejo, Luis
A1 Baladrón García, Carlos
A1 Aguiar Pérez, Javier Manuel
A1 Calavia, Lorena
A1 Carro Martínez, Belén
A1 Sánchez Esguevillas, Antonio Javier
A1 Sanjuán, Javier
A1 González, Álvaro
A1 Lloret, Jaime
K1 Artificial Neural Networks (ANN)
K1 Short-term load forecasting
K1 Microgrids
K1 Multilayer perceptron
K1 33 Ciencias Tecnológicas
AB Short-Term Load Forecasting plays a significant role in energy generationplanning, and is specially gaining momentum in the emerging Smart Grids environment,which usually presents highly disaggregated scenarios where detailed real-time informationis available thanks to Communications and Information Technologies, as it happens forexample in the case of microgrids. This paper presents a two stage prediction model basedon an Artificial Neural Network in order to allow Short-Term Load Forecasting of thefollowing day in microgrid environment, which first estimates peak and valley values of thedemand curve of the day to be forecasted. Those, together with other variables, will make thesecond stage, forecast of the entire demand curve, more precise than a direct, single-stageforecast. The whole architecture of the model will be presented and the results comparedwith recent work on the same set of data, and on the same location, obtaining a MeanAbsolute Percentage Error of 1.62% against the original 2.47% of the single stage model.
PB MDPI
SN 1999-4907
YR 2013
FD 2013
LK https://uvadoc.uva.es/handle/10324/57639
UL https://uvadoc.uva.es/handle/10324/57639
LA eng
NO Energies, 2013, vol. 6, n. 9, p. 4489-4507
NO Producción Científica
DS UVaDOC
RD 08-ago-2024