Forecasting day-ahead electricity prices: A comparison of time series and neural network models taking external regressors into account

Lehna, Malte; Scheller, Fabian; Herwartz, Helmut

doi:10.1016/j.eneco.2021.105742

Cited by 55 publications

(24 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Four different approaches to forecasting the spot price of electricity in Germany for different horizons, 1, 7, and 30 days ahead, were compared by Lehna et al [9]. In addition to the prominent seasonal auto-regressive integrated moving average model and long-term memory (LSTM) models, an LSTM convolutional neural network and a twostage multivariate vector auto-regressive approach were used as hybrid models.…”

Section: Related Workmentioning

confidence: 99%

Structure Optimization of Ensemble Learning Methods and Seasonal Decomposition Approaches to Energy Price Forecasting in Latin America: A Case Study about Mexico

et al. 2023

View full text Add to dashboard Cite

The energy price influences the interest in investment, which leads to economic development. An estimate of the future energy price can support the planning of industrial expansions and provide information to avoid times of recession. This paper evaluates adaptive boosting (AdaBoost), bootstrap aggregation (bagging), gradient boosting, histogram-based gradient boosting, and random forest ensemble learning models for forecasting energy prices in Latin America, especially in a case study about Mexico. Seasonal decomposition of the time series is used to reduce unrepresentative variations. The Optuna using tree-structured Parzen estimator, optimizes the structure of the ensembles through a voter by combining several ensemble frameworks; thus an optimized hybrid ensemble learning method is proposed. The results show that the proposed method has a higher performance than the state-of-the-art ensemble learning methods, with a mean squared error of 3.37 × 10−9 in the testing phase.

show abstract

Section: Related Workmentioning

confidence: 99%

Structure Optimization of Ensemble Learning Methods and Seasonal Decomposition Approaches to Energy Price Forecasting in Latin America: A Case Study about Mexico

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The electricity price in the spot market is the result of many market factors. Since the construction of the spot market in China is in the initial stage, the rules of spot market operation in each pilot province are unique, which leads to differences in the operation conditions of the spot market and the laws of electricity price in each province [37]. Therefore, according to the similarities and differences between the construction of the European electricity market and the Chinese electricity market, this paper, combined with the general law of construction of spot markets in each province of China, proposes the steps of electricity price formation in Chinese spot market.…”

Section: Analysis On the Formation Mechanism Of Electricity Price In ...mentioning

confidence: 99%

Day-Ahead Spot Market Price Forecast Based on a Hybrid Extreme Learning Machine Technique: A Case Study in China

et al. 2022

View full text Add to dashboard Cite

With the deepening of China’s electricity spot market construction, spot market price prediction is the basis for making reasonable quotation strategies. This paper proposes a day-ahead spot market price forecast based on a hybrid extreme learning machine technology. Firstly, the trading center’s information is examined using the Spearman correlation coefficient to eliminate characteristics that have a weak link with the price of power. Secondly, a similar day-screening model with weighted grey correlation degree is constructed based on the grey correlation theory (GRA) to exclude superfluous samples. Thirdly, the regularized limit learning machine (RELM) is tuned using the Marine Predators Algorithm (MPA) to increase RELM parameter accuracy. Finally, the proposed forecasting model is applied to the Shanxi spot market, and other forecasting models and error computation methodologies are compared. The results demonstrate that the model suggested in this paper has a specific forecasting effect for power price forecasting technology.

show abstract

“…Φ (1) Φ ( 2) Φ ( 3) Φ ( 4) Φ ( 5) Φ ( 6) Φ (7) Φ ( 8) Φ ( 9) Φ (10) Φ (11) Φ (12) The first matrix has many nonzero elements, whilst the subsequent matrices get more sparse every period and the last matrices highly sparse.…”

Section: Sparsity Pattern Generated By Bigvarmentioning

confidence: 99%

“…Since its proposal by [1], vector autoregressive analysis is a cornerstone of the existing literature on economics, econometrics and finance. Their use covers the joint analysis of time series data (due to their multiple time series and lag structures [2]), structural inference and policy analysis (due to the unique tools that they offer such as impulse response functions and forecast error variance decompositions [3][4][5][6][7][8]), and forecasting, a task in which they have become a reference due to their performance [9][10][11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Regularization Methods in High-Dimensional Monetary and Financial VARs

García

Rambaud

2022

Mathematics

View full text Add to dashboard Cite

Vector autoregressions (VARs) and their multiple variants are standard models in economic and financial research due to their power for forecasting, data analysis and inference. These properties are a consequence of their capabilities to include multiple variables and lags which, however, turns into an exponential growth of the parameters to be estimated. This means that high-dimensional models with multiple variables and lags are difficult to estimate, leading to omitted variables, information biases and a loss of potential forecasting power. Traditionally, the existing literature has resorted to factor analysis, and specially, to Bayesian methods to overcome this situation. This paper explores the so-called machine learning regularization methods as an alternative to traditional methods of forecasting and impulse response analysis. We find that regularization structures, which allow for high dimensional models, perform better than standard Bayesian methods in nowcasting and forecasting. Moreover, impulse response analysis is robust and consistent with economic theory and evidence, and with the different regularization structures. Specifically, regarding the best regularization structure, an elementwise machine learning structure performs better in nowcasting and in computational efficiency, whilst a componentwise structure performs better in forecasting and cross-validation methods.

show abstract

Forecasting day-ahead electricity prices: A comparison of time series and neural network models taking external regressors into account

Cited by 55 publications

References 33 publications

Structure Optimization of Ensemble Learning Methods and Seasonal Decomposition Approaches to Energy Price Forecasting in Latin America: A Case Study about Mexico

Structure Optimization of Ensemble Learning Methods and Seasonal Decomposition Approaches to Energy Price Forecasting in Latin America: A Case Study about Mexico

Day-Ahead Spot Market Price Forecast Based on a Hybrid Extreme Learning Machine Technique: A Case Study in China

Machine Learning Regularization Methods in High-Dimensional Monetary and Financial VARs

Contact Info

Product

Resources

About