Forecasting day-ahead electricity prices in Europe: The importance of considering market integration

Lago, Jesus; Ridder, Fjo De; Vrancx, Peter; Schutter, Bart De

doi:10.1016/j.apenergy.2017.11.098

Cited by 198 publications

(104 citation statements)

References 52 publications

Supporting

Mentioning

104

Contrasting

Order By: Relevance

“…In Reference [27], Deep Neural Network (DNN) is used to extract complex patterns from the price dataset of Belgium. In Reference [28], Gray Correlation Analysis (GCA) is used along with Kernel Principal Component Analysis (KPCA) to deal with the dimensionality reduction issue. For prediction, Support Vector Machine (SVM) is used in combination with Differential Evolution (DE), where DE is used to tune the parameters of SVM.…”

Section: Electricity Price Forecastingmentioning

confidence: 99%

Short-Term Electric Load and Price Forecasting Using Enhanced Extreme Learning Machine Optimization in Smart Grids

et al. 2019

View full text Add to dashboard Cite

A Smart Grid (SG) is a modernized grid to provide efficient, reliable and economic energy to the consumers. Energy is the most important resource in the world. An efficient energy distribution is required as smart devices are increasing dramatically. The forecasting of electricity consumption is supposed to be a major constituent to enhance the performance of SG. Various learning algorithms have been proposed to solve the forecasting problem. The sole purpose of this work is to predict the price and load efficiently. The first technique is Enhanced Logistic Regression (ELR) and the second technique is Enhanced Recurrent Extreme Learning Machine (ERELM). ELR is an enhanced form of Logistic Regression (LR), whereas, ERELM optimizes weights and biases using a Grey Wolf Optimizer (GWO). Classification and Regression Tree (CART), Relief-F and Recursive Feature Elimination (RFE) are used for feature selection and extraction. On the basis of selected features, classification is performed using ELR. Cross validation is done for ERELM using Monte Carlo and K-Fold methods. The simulations are performed on two different datasets. The first dataset, i.e., UMass Electric Dataset is multi-variate while the second dataset, i.e., UCI Dataset is uni-variate. The first proposed model performed better with UMass Electric Dataset than UCI Dataset and the accuracy of second model is better with UCI than UMass. The prediction accuracy is analyzed on the basis of four different performance metrics: Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), Mean Square Error (MSE) and Root Mean Square Error (RMSE). The proposed techniques are then compared with four benchmark schemes. The comparison is done to verify the adaptivity of the proposed techniques. The simulation results show that the proposed techniques outperformed benchmark schemes. The proposed techniques efficiently increased the prediction accuracy of load and price. However, the computational time is increased in both scenarios. ELR achieved almost 5% better results than Convolutional Neural Network (CNN) and almost 3% than LR. While, ERELM achieved almost 6% better results than ELM and almost 5% than RELM. However, the computational time is almost 20% increased with ELR and 50% with ERELM. Scalability is also addressed for the proposed techniques using half-yearly and yearly datasets. Simulation results show that ELR gives 5% better results while, ERELM gives 6% better results when used for yearly dataset.

show abstract

Section: Electricity Price Forecastingmentioning

confidence: 99%

Short-Term Electric Load and Price Forecasting Using Enhanced Extreme Learning Machine Optimization in Smart Grids

et al. 2019

View full text Add to dashboard Cite

show abstract

“…θ * ← BestHyperparameters(H) 12: return θ * 13: end procedure In addition to optimizing the hyperparameters, the TPE algorithm is also employed for optimizing the selection of input features. In particular, the feature selection method proposed in [27] is considered, which selects the input features by first defining the input features as model hyperparameters and then using the TPE algorithm to optimally choose among them. More specifically, the method considers that each possible input feature can be either modeled as a binary hyperparameter representing its inclusion/exclusion or as an integer hyperparameter representing how many historical values of the specific input are used.…”

Section: Hyperparameter Optimization and Feature Selectionmentioning

confidence: 99%

“…A key element to build a prediction model that can be used without the need of ground data is to employ a model whose structure is flexible enough to generalize across multiple geographical locations. As DNNs are powerful models that can generalize across tasks [17,27], they are selected as the base model for the proposed forecaster. This concept of generalization is further explained in Section 3.6.1.…”

Section: Model Structurementioning

confidence: 99%

“…Enforcing generalization is not only good for obtaining a model that does not require ground data, but in general, it is also beneficial to obtain a DNN that does not overfit and that obtains more accurate predictions [17]. In particular, as it has been empirically shown in several studies [27,28], by forcing the network to solve multiple related task, 2 Note that minimizing the mean square error is equivalent to minimizing the rRMSE metric used throughout the paper to evaluate and compare the model. e.g.…”

Section: Generalizing Across Predictive Horizonsmentioning

confidence: 99%

See 1 more Smart Citation

Short-term forecasting of solar irradiance without local telemetry: A generalized model using satellite data

Lago

Brabandere

Ridder³

et al. 2018

Solar Energy

Self Cite

View full text Add to dashboard Cite

Due to the increasing integration of solar power into the electrical grid, forecasting short-term solar irradiance has become key for many applications, e.g. operational planning, power purchases, reserve activation, etc. In this context, as solar generators are geographically dispersed and ground measurements are not always easy to obtain, it is very important to have general models that can predict solar irradiance without the need of local data. In this paper, a model that can perform short-term forecasting of solar irradiance in any general location without the need of ground measurements is proposed. To do so, the model considers satellite-based measurements and weather-based forecasts, and employs a deep neural network structure that is able to generalize across locations; particularly, the network is trained only using a small subset of sites where ground data is available, and the model is able to generalize to a much larger number of locations where ground data does not exist. As a case study, 25 locations in The Netherlands are considered and the proposed model is compared against four local models that are individually trained for each location using ground measurements. Despite the general nature of the model, it is shown show that the proposed model is equal or better than the local models: when comparing the average performance across all the locations and prediction horizons, the proposed model obtains a 31.31% rRMSE (relative root mean square error) while the best local model achieves a 32.01% rRMSE. (Jesus Lago) forecasting irradiance over short time horizons. In particular, in addition to activation of reserves to manage the grid stability, short-term forecasts of solar irradiance are paramount for operational planning, switching sources, programming backup, short-term power trading, peak load matching, scheduling of power systems, congestion management, and cost reduction [2][3][4].

show abstract

“…The impact of artificial intelligence on society has increased due to the availability of big data and rapid advances in computer technology. The application of machine learning, an aspect of artificial intelligence, in business and economic analysis has been explored in energy economics by Tso and Yau (2005), Weron (2014), Ziel and Steinert (2016), and Lago et al (2018); stock price forecasting by Zhang et al (1998), Hegazy et al (2013), Rather et al (2015), and Moghaddam et al (2016); early warning systems by Tanaka et al (2016); financial hazard map by Tanaka et al (2018); and credit risk assessment by Angelini et al (2008), Khashman (2009), Khashman (2010, Khemakhem and Boujelbene (2015), and Hamori et al (2018).…”

Section: Introductionmentioning

confidence: 99%

Does Ensemble Learning Always Lead to Better Forecasts?

Hamori¹,

Hamori²

2020

AEF

View full text Add to dashboard Cite

Ensemble learning is a common machine learning technique applied to business and economic analysis in which several classifiers are combined using majority voting for better forecasts as compared to those of individual classifier. This study presents a counterexample, which demonstrates that ensemble learning leads to worse classifications than those from individual classifiers, using two events and three classifiers. If there is an outstanding classifier, we should follow its forecast instead of using ensemble learning.

show abstract

Forecasting day-ahead electricity prices in Europe: The importance of considering market integration

Cited by 198 publications

References 52 publications

Short-Term Electric Load and Price Forecasting Using Enhanced Extreme Learning Machine Optimization in Smart Grids

Short-Term Electric Load and Price Forecasting Using Enhanced Extreme Learning Machine Optimization in Smart Grids

Short-term forecasting of solar irradiance without local telemetry: A generalized model using satellite data

Does Ensemble Learning Always Lead to Better Forecasts?

Contact Info

Product

Resources

About