Data-Driven Techniques for Short-Term Electricity Price Forecasting through Novel Deep Learning Approaches with Attention Mechanisms
The electricity market is constantly evolving, being driven by factors such as market liberalization, the increasing use of renewable energy sources (RESs), and various economic and political influences. These dynamics make it challenging to predict wholesale electricity prices. Accurate short-term...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/17/7/1625 |
| _version_ | 1797212634899021824 |
|---|---|
| author | Vasileios Laitsos Georgios Vontzos Dimitrios Bargiotas Aspassia Daskalopulu Lefteri H. Tsoukalas |
| author_facet | Vasileios Laitsos Georgios Vontzos Dimitrios Bargiotas Aspassia Daskalopulu Lefteri H. Tsoukalas |
| author_sort | Vasileios Laitsos |
| collection | DOAJ |
| description | The electricity market is constantly evolving, being driven by factors such as market liberalization, the increasing use of renewable energy sources (RESs), and various economic and political influences. These dynamics make it challenging to predict wholesale electricity prices. Accurate short-term forecasting is crucial to maintaining system balance and addressing anomalies such as negative prices and deviations from predictions. This paper investigates short-term electricity price forecasting using historical time series data and employs advanced deep learning algorithms. First, four deep learning models are implemented and proposed, which are a convolutional neural network (CNN) with an integrated attention mechanism, a hybrid CNN followed by a gated recurrent unit model (CNN-GRU) with an attention mechanism, and two ensemble learning models, which are a soft voting ensemble and a stacking ensemble model. Also, the optimized version of a transformer model, the Multi-Head Attention model, is introduced. Finally, the perceptron model is used as a benchmark for comparison. Our results show excellent prediction accuracy, particularly in the hybrid CNN-GRU model with attention, thereby achieving a mean absolute percentage error (MAPE) of 6.333%. The soft voting ensemble model and the Multi-Head Attention model also performed well, with MAPEs of 6.125% and 6.889%, respectively. These findings are significant, as previous studies have not shown high performance with transformer models and attention mechanisms. The presented results offer promising insights for future research in this field. |
| first_indexed | 2024-04-24T10:45:31Z |
| format | Article |
| id | doaj.art-70e81a571614471eb1cd93203f3072bd |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-24T10:45:31Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-70e81a571614471eb1cd93203f3072bd2024-04-12T13:17:53ZengMDPI AGEnergies1996-10732024-03-01177162510.3390/en17071625Data-Driven Techniques for Short-Term Electricity Price Forecasting through Novel Deep Learning Approaches with Attention MechanismsVasileios Laitsos0Georgios Vontzos1Dimitrios Bargiotas2Aspassia Daskalopulu3Lefteri H. Tsoukalas4Department of Electrical and Computer Engineering, University of Thessaly, 383 34 Volos, GreeceDepartment of Electrical and Computer Engineering, University of Thessaly, 383 34 Volos, GreeceDepartment of Electrical and Computer Engineering, University of Thessaly, 383 34 Volos, GreeceDepartment of Electrical and Computer Engineering, University of Thessaly, 383 34 Volos, GreeceCenter for Intelligent Energy Systems (CiENS), School of Nuclear Engineering, Purdue University, West Lafayette, IN 47906, USAThe electricity market is constantly evolving, being driven by factors such as market liberalization, the increasing use of renewable energy sources (RESs), and various economic and political influences. These dynamics make it challenging to predict wholesale electricity prices. Accurate short-term forecasting is crucial to maintaining system balance and addressing anomalies such as negative prices and deviations from predictions. This paper investigates short-term electricity price forecasting using historical time series data and employs advanced deep learning algorithms. First, four deep learning models are implemented and proposed, which are a convolutional neural network (CNN) with an integrated attention mechanism, a hybrid CNN followed by a gated recurrent unit model (CNN-GRU) with an attention mechanism, and two ensemble learning models, which are a soft voting ensemble and a stacking ensemble model. Also, the optimized version of a transformer model, the Multi-Head Attention model, is introduced. Finally, the perceptron model is used as a benchmark for comparison. Our results show excellent prediction accuracy, particularly in the hybrid CNN-GRU model with attention, thereby achieving a mean absolute percentage error (MAPE) of 6.333%. The soft voting ensemble model and the Multi-Head Attention model also performed well, with MAPEs of 6.125% and 6.889%, respectively. These findings are significant, as previous studies have not shown high performance with transformer models and attention mechanisms. The presented results offer promising insights for future research in this field.https://www.mdpi.com/1996-1073/17/7/1625load forecastinglong short-term memoryperceptronconvolutional neural networks (CNN)Multi-Head Attentiontransformer |
| spellingShingle | Vasileios Laitsos Georgios Vontzos Dimitrios Bargiotas Aspassia Daskalopulu Lefteri H. Tsoukalas Data-Driven Techniques for Short-Term Electricity Price Forecasting through Novel Deep Learning Approaches with Attention Mechanisms Energies load forecasting long short-term memory perceptron convolutional neural networks (CNN) Multi-Head Attention transformer |
| title | Data-Driven Techniques for Short-Term Electricity Price Forecasting through Novel Deep Learning Approaches with Attention Mechanisms |
| title_full | Data-Driven Techniques for Short-Term Electricity Price Forecasting through Novel Deep Learning Approaches with Attention Mechanisms |
| title_fullStr | Data-Driven Techniques for Short-Term Electricity Price Forecasting through Novel Deep Learning Approaches with Attention Mechanisms |
| title_full_unstemmed | Data-Driven Techniques for Short-Term Electricity Price Forecasting through Novel Deep Learning Approaches with Attention Mechanisms |
| title_short | Data-Driven Techniques for Short-Term Electricity Price Forecasting through Novel Deep Learning Approaches with Attention Mechanisms |
| title_sort | data driven techniques for short term electricity price forecasting through novel deep learning approaches with attention mechanisms |
| topic | load forecasting long short-term memory perceptron convolutional neural networks (CNN) Multi-Head Attention transformer |
| url | https://www.mdpi.com/1996-1073/17/7/1625 |
| work_keys_str_mv | AT vasileioslaitsos datadriventechniquesforshorttermelectricitypriceforecastingthroughnoveldeeplearningapproacheswithattentionmechanisms AT georgiosvontzos datadriventechniquesforshorttermelectricitypriceforecastingthroughnoveldeeplearningapproacheswithattentionmechanisms AT dimitriosbargiotas datadriventechniquesforshorttermelectricitypriceforecastingthroughnoveldeeplearningapproacheswithattentionmechanisms AT aspassiadaskalopulu datadriventechniquesforshorttermelectricitypriceforecastingthroughnoveldeeplearningapproacheswithattentionmechanisms AT lefterihtsoukalas datadriventechniquesforshorttermelectricitypriceforecastingthroughnoveldeeplearningapproacheswithattentionmechanisms |