Daily electrical power curves: Classification and forecasting using a Kohonen map

Cottrell, Marie; Girard, B.; Girard, Y.; Muller, Corinne; Rousset, Patrick

doi:10.1007/3-540-59497-3_291

Cited by 13 publications

(11 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Actually, neural network based predictors are regarded as best. Supervised learning (Afkhami-Rohani and Maratukulam, 1998;Kiartzis et al, 1997;Fidalgo and Pecas Lopez, 2005;Osowski and Siwek, 2002) as well as competitive self-organizing (Cottrell et al, 1995;Osowski and Siwek, 1999) networks are most widely known. In our work we have used three neural prediction methods.…”

Section: Individual Neural Predictorsmentioning

confidence: 99%

“…The second type of predictor makes use of selforganization of the learning data (Cottrell et al, 1995;Osowski and Siwek, 1999). The main task of the selforganizing network is to learn the characteristics of the daily loads of the system.…”

Section: 2mentioning

confidence: 99%

“…To make the prediction independent of the general trend, changing from year to year, we transform the input data by cutting out the mean value and dividing the result by the standard deviation of the data for this day. In this way the so-called profile p (d, h) for the d-th day and the h-th hour is defined (Cottrell et al, 1995;Nikias and Petropulu, 1993),…”

Section: 2mentioning

confidence: 99%

“…The most common are linear methods based on autoregressive models of time series, such as AutoRegressive with eXogenous input (ARX), AutoRegressive Moving Average with eXogenous input (ARMAX) or AutoRegressive Integrated Moving Average (ARIMA) (Gonzalez-Romera et al, 2006;Hippert et al, 2001;Ljung, 1999). More advanced approaches apply nonlinear models based mainly on artificial neural networks, such as the MultiLayer Perceptron (MLP), Radial Basis Function (RBF) networks, the Support Vector Machine (SVM) or self-organizing neural networks of the Kohonen type (Cottrell et al, 1995;Fidalgo and Pecas Lopez, 2005;Kandil et al, 2006;Lendasse et al, 2002;Osowski and Siwek, 2002;Yalcinoz and Eminoglu, 2005). Neural networks are nonlinear structures, capable of taking into account more complex relations existing among the analyzed data.…”

Section: Introductionmentioning

confidence: 99%

“…For example, the application of a Kohonen network exploits the concept of the clusterization of similar data points (Cottrell et al, 1995;Osowski and Siwek, 1999), while the MLP, RBF and the SVM take into account the universal approximation ability of these networks (Osowski, 2006;Yalci-304 K. Siwek et al noz and Eminoglu, 2005). On the other hand, the MLP network performs global approximation, while the RBF network is a typical local approximation tool.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Ensemble Neural Network Approach for Accurate Load Forecasting in a Power System

Siwek¹,

Osowski²,

Szupiluk³

2009

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

The paper presents an improved method for 1-24 hours load forecasting in the power system, integrating and combining different neural forecasting results by an ensemble system. We will integrate the results of partial predictions made by three solutions, out of which one relies on a multilayer perceptron and two others on self-organizing networks of the competitive type. As the expert system we will apply different integration methods: simple averaging, SVD based weighted averaging, principal component analysis and blind source separation. The results of numerical experiments, concerning forecasting the hourly load for the next 24 hours of the Polish power system, will be presented and discussed. We will compare the performance of different ensemble methods on the basis of the mean absolute percentage error, mean squared error and maximum percentage error. They show a significant improvement of the proposed ensemble method in comparison to the individual results of prediction. The comparison of our work with the results of other papers for the same data proves the superiority of our approach.

show abstract

Section: Individual Neural Predictorsmentioning

confidence: 99%

Section: 2mentioning

confidence: 99%

Section: 2mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Ensemble Neural Network Approach for Accurate Load Forecasting in a Power System

Siwek¹,

Osowski²,

Szupiluk³

2009

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

show abstract

Forecasting of curves using a Kohonen classification

1998

Self Cite

View full text Add to dashboard Cite

This paper addresses an extensively studied problem, which is a particular case of long‐term forecasting. In many practical situations, one has to predict a complete curve, i.e. the set of the 24 hourly values for the next day, of all the daily values for the next month or for the next year. For example, it is the case if the matter is to forecast the daily half‐hour electricity consumption. Many methods have been developed, standard linear methods (e.g. ARIMA) as well as neural ones. In this paper we present a very simple method that we call the K‐method. We assume the forecasting problem can be split up into three subproblems: the forecast of the mean (level of the values), of the standard deviation (scattering) and of the normalized profile (which essentially represents the shape). The profiles are classified using a Kohonen map with the neighbourhood preservation property and the mean and variance are fitted using any convenient short‐term forecasting method. Then, for some future curve, a strategy is defined in order to compute its expected normalized profile, the mean and the variance are forecast and the expected curve is computed. This method is low computation time consuming and is easy to develop. Two applications are presented: an example using artificial data and the prediction of the daily half‐hour electrical power curves in France. Copyright © 1998 John Wiley & Sons, Ltd.

show abstract

Classifying hedge funds with Kohonen maps: A first attempt

Maillet

Rousset

2003

Connectionist Approaches in Economics and Management Sciences

View full text Add to dashboard Cite

Daily electrical power curves: Classification and forecasting using a Kohonen map

Cited by 13 publications

References 3 publications

Ensemble Neural Network Approach for Accurate Load Forecasting in a Power System

Ensemble Neural Network Approach for Accurate Load Forecasting in a Power System

Forecasting of curves using a Kohonen classification

Classifying hedge funds with Kohonen maps: A first attempt

Contact Info

Product

Resources

About