Title :
Hybrid demand model for load estimation and short term load forecasting in distribution electric systems
Author :
Villalba, Salvador Añó ; Bel, Carlos Álvarez
Author_Institution :
Dept. of Electr. Eng., Univ. Politecnica de Valencia, Spain
fDate :
4/1/2000 12:00:00 AM
Abstract :
A new hybrid demand model to enhance load modeling in distribution applications is proposed in this paper. This model is specially well suited for the applications emerging from the new structure of the power sector worldwide. The modeling is performed in two steps. The first one is a state space model for load estimation at the selected points in the network. It uses information already available in the utility and also some measurements, and it suggests measurement planning for meter location and bad data detection. The second step is an artificial neural network (ANN) model for short-term load forecasting which is able to cope with the nonlinear behavior of the load. The model has been validated in simulation studies and using historical data from the distribution level
Keywords :
load forecasting; neural nets; power distribution planning; power engineering computing; power system state estimation; state-space methods; artificial neural network; bad data detection; electric utility; hybrid demand model; load estimation; measurement planning; meter location; nonlinear load behavior; power distribution systems; short-term load forecasting; state space model; Artificial neural networks; Bayesian methods; Load forecasting; Load modeling; Mathematical model; Neural networks; Power system modeling; Predictive models; State estimation; State-space methods;
Journal_Title :
Power Delivery, IEEE Transactions on