oalogo2  

AUTHOR(S): 

L. Ekonomou, C. A. Christodoulou, V. Mladenov

 

TITLE

A Short-Term Load Forecasting Method Using Artificial Neural Networks and Wavelet Analysis

pdf PDF

KEYWORDS

Artificial neural networks; Back-propagation algorithm; Denoising algorithm; Short-term load forecasting; Wavelet analysis

ABSTRACT

Load forecasting is an issue of great importance for the reliable operation of the electric power system grids. Various forecasting methodologies have been proposed in the international research bibliography, following different models and mathematical approaches. A precise electric load forecasting results in cost saving and secure operational conditions. Moreover, it can also be helpful in power supply strategy, market research and financing planning. In the current work a methodology based on artificial neural networks methods reinforced by an appropriate wavelet denoising algorithm is implemented, in order to obtain short-term load forecasting. Real recoded data obtained from the Bulgarian power system grid was used in the analysis. The extracted outcomes indicate the effectiveness of the proposed method, reducing the relative error between real and theoretical data.

Cite this paper

L. Ekonomou, C. A. Christodoulou, V. Mladenov. (2016) A Short-Term Load Forecasting Method Using Artificial Neural Networks and Wavelet Analysis. International Journal of Power Systems, 1, 64-68