Extended forecast methods for day-ahead electricity spot prices applying artificial neural networks

Keles, Dogan; Scelle, Jonathan; Paraschiv, Florentina; Fïchtner, Wolf

doi:10.1016/j.apenergy.2015.09.087

Cited by 238 publications

(122 citation statements)

References 44 publications

Supporting

Mentioning

122

Contrasting

Order By: Relevance

“…As has been noted in a number of studies, be it statistical or computational intelligence, a key point in EPF is the appropriate choice of explanatory variables [1,[4][5][6][7][8][9][10][11]. The typical approach has been to select predictors in an ad hoc fashion, sometimes using expert knowledge, seldom based on some formal validation procedures.…”

Section: Introductionmentioning

confidence: 99%

“…Amjady and Keynia [4] proposed a feature selection algorithm that utilized the mutual information technique. (for later applications, see, e.g., [11,14,15]). In an econometric setup, Gianfreda and Grossi [5] computed p-values of the coefficients of a regression model with autoregressive fractionally integrated moving average disturbances (Reg-ARFIMA) and in one step eliminated all statistically-insignificant variables.…”

Section: Introductionmentioning

confidence: 99%

“…Ludwig et al [7] used both random forests and the least absolute shrinkage and selection operator (i.e., lasso or LASSO) as a feature selection algorithm to choose the relevant out of the 77 available weather stations. In a recent neural network study, Keles et al [11] combined the k-nearest-neighbor algorithm with backward elimination to select the most appropriate input variables out of more than 50 fundamental parameters or lagged versions of these parameters. Finally, Ziel et al [9,18] used the lasso to sparsify very large sets of model parameters (well over 100).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated Variable Selection and Shrinkage for Day-Ahead Electricity Price Forecasting

2016

View full text Add to dashboard Cite

Abstract:In day-ahead electricity price forecasting (EPF) variable selection is a crucial issue. Conducting an empirical study involving state-of-the-art parsimonious expert models as benchmarks, datasets from three major power markets and five classes of automated selection and shrinkage procedures (single-step elimination, stepwise regression, ridge regression, lasso and elastic nets), we show that using the latter two classes can bring significant accuracy gains compared to commonly-used EPF models. In particular, one of the elastic nets, a class that has not been considered in EPF before, stands out as the best performing model overall.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Variable Selection and Shrinkage for Day-Ahead Electricity Price Forecasting

2016

View full text Add to dashboard Cite

show abstract

“…By 'putting big data analytics to work'-as they referred to it-Ludwig et al [10] used random forests and the least absolute shrinkage and selection operator (LASSO or Lasso) as a feature selection algorithm to choose which of the 77 available weather stations were relevant. In parallel, in the machine learning literature, González et al [11] utilized random forests, while Keles et al [7] combined the k-Nearest-Neighbor algorithm with backward elimination to select the most appropriate inputs out of more than 50 fundamental parameters or lagged versions of these parameters.…”

Section: Introductionmentioning

confidence: 99%

“…In the machine learning literature, Amjady and Keynia [5] proposed a feature selection algorithm based on mutual information that was later utilized in [6,7], among others. On the other hand, Gianfreda and Grossi [8] used a very simple technique-single-step elimination of insignificant predictors in a regression setting.…”

Section: Introductionmentioning

confidence: 99%

Efficient Forecasting of Electricity Spot Prices with Expert and LASSO Models

Uniejewski

Weron

2018

Energies

View full text Add to dashboard Cite

Recent electricity price forecasting (EPF) studies suggest that the least absolute shrinkage and selection operator (LASSO) leads to well performing models that are generally better than those obtained from other variable selection schemes. By conducting an empirical study involving datasets from two major power markets (Nord Pool and PJM Interconnection), three expert models, two multi-parameter regression (called baseline) models and four variance stabilizing transformations combined with the seasonal component approach, we discuss the optimal way of implementing the LASSO. We show that using a complex baseline model with nearly 400 explanatory variables, a well chosen variance stabilizing transformation (asinh or N-PIT), and a procedure that recalibrates the LASSO regularization parameter once or twice a day indeed leads to significant accuracy gains compared to the typically considered EPF models. Moreover, by analyzing the structures of the best LASSO-estimated models, we identify the most important explanatory variables and thus provide guidelines to structuring better performing models.

show abstract

An electricity price interval forecasting by using residual neural network

Chaweewat

Singh

2020

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

Summary This article proposed a new electricity price interval forecasting method based on a novel Residual Neural Network (ResNet) for the electricity price interval forecasting. The significant outcome of the ResNet model was that the model performs excellently on normal and spike price interval forecasting in accuracy and reliability point of view. The proposed ResNet was consisting of two network layers. The first neural network layers were probabilistic normal, high, and spike prices prediction part. The Lower and Upper Bound Estimation (LUBE) formulates the price interval forecasting from the output of the second neural network layers. The LUBE methods included Quantile Regression and Mean and Variance estimation. The proposed forecasting models were demonstrated with the GEFCom2014 dataset. The dataset is consisting of 15 tasks for electricity prices forecasting. The results of proposed ResNet models compared with GEFCom2014's benchmarks, Quantile Regression Average, and Multilayer Perceptron Network approaches. The performances of forecasting models are evaluated in terms of accuracy and reliability metrics by Pinball Loss Function and Coverage Width‐based Criterion (CWC), respectively. Also, this article shows the effect of an increase in confidence level, which could generate lower CWC values and represent high reliability's satisfaction.

show abstract

Extended forecast methods for day-ahead electricity spot prices applying artificial neural networks

Cited by 238 publications

References 44 publications

Automated Variable Selection and Shrinkage for Day-Ahead Electricity Price Forecasting

Automated Variable Selection and Shrinkage for Day-Ahead Electricity Price Forecasting

Efficient Forecasting of Electricity Spot Prices with Expert and LASSO Models

An electricity price interval forecasting by using residual neural network

Contact Info

Product

Resources

About