Forecasting Nodal Price Difference Between Day-Ahead and Real-Time Electricity Markets Using Long-Short Term Memory and Sequence-to-Sequence Networks
Price forecasting is at the center of decision making in electricity markets. Much research has been done in forecasting energy prices for a single market while little research has been reported on forecasting price difference between markets, which presents higher volatility and yet plays a critica...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9641818/ |
| _version_ | 1798040315570946048 |
|---|---|
| author | Ronit Das Rui Bo Haotian Chen Waqas Ur Rehman Donald Wunsch |
| author_facet | Ronit Das Rui Bo Haotian Chen Waqas Ur Rehman Donald Wunsch |
| author_sort | Ronit Das |
| collection | DOAJ |
| description | Price forecasting is at the center of decision making in electricity markets. Much research has been done in forecasting energy prices for a single market while little research has been reported on forecasting price difference between markets, which presents higher volatility and yet plays a critical role in applications such as virtual trading. To this end, this paper takes the first attempt at it and employs novel deep learning architecture with Bidirectional Long-Short Term Memory (LSTM) units and Sequence-to-Sequence (Seq2Seq) architecture to forecast nodal price difference between day-ahead and real-time markets. In addition to value prediction, these deep learning architectures are also used to develop classification models to predict the price difference bands/ranges. The proposed methods are tested using historical PJM market data, and evaluated using Root Mean Squared Error (RMSE) and other customized performance metrics. Case studies show that both deep learning methods outperform common methods including ARIMA, XGBoost and Support Vector Regression (SVR) methods. More importantly, the deep learning methods can capture the magnitude and timing of price difference spikes. Numerical results show the Seq2Seq model performs particularly well and demonstrates generalization capability to extended forecasting lead time. |
| first_indexed | 2024-04-11T22:05:54Z |
| format | Article |
| id | doaj.art-4549722f883a4eed953dd388d7e1123b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T22:05:54Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-4549722f883a4eed953dd388d7e1123b2022-12-22T04:00:42ZengIEEEIEEE Access2169-35362022-01-011083284310.1109/ACCESS.2021.31334999641818Forecasting Nodal Price Difference Between Day-Ahead and Real-Time Electricity Markets Using Long-Short Term Memory and Sequence-to-Sequence NetworksRonit Das0Rui Bo1https://orcid.org/0000-0001-9108-1093Haotian Chen2Waqas Ur Rehman3https://orcid.org/0000-0001-9690-3375Donald Wunsch4https://orcid.org/0000-0002-9726-9051Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USADepartment of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USADepartment of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USADepartment of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USADepartment of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USAPrice forecasting is at the center of decision making in electricity markets. Much research has been done in forecasting energy prices for a single market while little research has been reported on forecasting price difference between markets, which presents higher volatility and yet plays a critical role in applications such as virtual trading. To this end, this paper takes the first attempt at it and employs novel deep learning architecture with Bidirectional Long-Short Term Memory (LSTM) units and Sequence-to-Sequence (Seq2Seq) architecture to forecast nodal price difference between day-ahead and real-time markets. In addition to value prediction, these deep learning architectures are also used to develop classification models to predict the price difference bands/ranges. The proposed methods are tested using historical PJM market data, and evaluated using Root Mean Squared Error (RMSE) and other customized performance metrics. Case studies show that both deep learning methods outperform common methods including ARIMA, XGBoost and Support Vector Regression (SVR) methods. More importantly, the deep learning methods can capture the magnitude and timing of price difference spikes. Numerical results show the Seq2Seq model performs particularly well and demonstrates generalization capability to extended forecasting lead time.https://ieeexplore.ieee.org/document/9641818/Electricity marketsDA/RT price differenceforecastinglong-short term memoryLSTMsequence to sequence |
| spellingShingle | Ronit Das Rui Bo Haotian Chen Waqas Ur Rehman Donald Wunsch Forecasting Nodal Price Difference Between Day-Ahead and Real-Time Electricity Markets Using Long-Short Term Memory and Sequence-to-Sequence Networks IEEE Access Electricity markets DA/RT price difference forecasting long-short term memory LSTM sequence to sequence |
| title | Forecasting Nodal Price Difference Between Day-Ahead and Real-Time Electricity Markets Using Long-Short Term Memory and Sequence-to-Sequence Networks |
| title_full | Forecasting Nodal Price Difference Between Day-Ahead and Real-Time Electricity Markets Using Long-Short Term Memory and Sequence-to-Sequence Networks |
| title_fullStr | Forecasting Nodal Price Difference Between Day-Ahead and Real-Time Electricity Markets Using Long-Short Term Memory and Sequence-to-Sequence Networks |
| title_full_unstemmed | Forecasting Nodal Price Difference Between Day-Ahead and Real-Time Electricity Markets Using Long-Short Term Memory and Sequence-to-Sequence Networks |
| title_short | Forecasting Nodal Price Difference Between Day-Ahead and Real-Time Electricity Markets Using Long-Short Term Memory and Sequence-to-Sequence Networks |
| title_sort | forecasting nodal price difference between day ahead and real time electricity markets using long short term memory and sequence to sequence networks |
| topic | Electricity markets DA/RT price difference forecasting long-short term memory LSTM sequence to sequence |
| url | https://ieeexplore.ieee.org/document/9641818/ |
| work_keys_str_mv | AT ronitdas forecastingnodalpricedifferencebetweendayaheadandrealtimeelectricitymarketsusinglongshorttermmemoryandsequencetosequencenetworks AT ruibo forecastingnodalpricedifferencebetweendayaheadandrealtimeelectricitymarketsusinglongshorttermmemoryandsequencetosequencenetworks AT haotianchen forecastingnodalpricedifferencebetweendayaheadandrealtimeelectricitymarketsusinglongshorttermmemoryandsequencetosequencenetworks AT waqasurrehman forecastingnodalpricedifferencebetweendayaheadandrealtimeelectricitymarketsusinglongshorttermmemoryandsequencetosequencenetworks AT donaldwunsch forecastingnodalpricedifferencebetweendayaheadandrealtimeelectricitymarketsusinglongshorttermmemoryandsequencetosequencenetworks |