Short-Term Load Forecasting Using Radial Basis Function Networks

Gontar, Zbigniew; Sideratos, G.; Hatziargyriou, Nikos D.

doi:10.1007/978-3-540-24674-9_45

Search citation statements

Order By: Relevance

Paper Sections

Select...

E Combination Module1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2005

2018

Publication Types

Select...

Other3

Article2

Book1

Relationship

Self Cite0

Independent6

Authors

Journals

Cited by 9 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5 shows the mean absolute error in MW. It is important to mention that the performance is very satisfactory comparing with other methods that have been implemented for the same case study [22,23]. More specifically, the MAPE criterion is always less than 5% except the last time step, while the Std APE is at very low levels less than 4.5%.…”

Section: E Combination Modulementioning

confidence: 96%

A load forecasting hybrid method for an isolated power system

Sideratos

Vitellas

Hatziargyriou

2011

2011 16th International Conference on Intelligent System Applications to Power Systems

View full text Add to dashboard Cite

This paper presents a load forecasting hybrid model designed for isolated power systems. The proposed model consists of four modules that estimate initially the future load demand and a combination module. Radial basis function neural networks (RBFNNs) are applied to make the initial predictions and multilayer perceptrons (MLPs) are used to combine them. Emphasis is given to the RBFNNs generalization ability developing a self-learning procedure with the Particle Swarm Optimization (PSO) algorithm. Satisfactory results are obtained after the evaluation in the Crete case study.

show abstract

Section: E Combination Modulementioning

confidence: 96%