Comparative study of long short-term memory (LSTM), bidirectional LSTM, and traditional machine learning approaches for energy consumption prediction
Responsible, efficient, and environmentally conscious energy consumption practices are increasingly essential for ensuring the reliability of the modern electricity grid. This study focuses on leveraging time series analysis to improve forecasting accuracy, crucial for various application domains wh...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2025-01-01
|
| Series: | Energy Exploration & Exploitation |
| Online Access: | https://doi.org/10.1177/01445987241269496 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841527606234578944 |
|---|---|
| author | Hamed Alizadegan Behzad Rashidi Malki Arian Radmehr Hossein Karimi Mohsen Asghari Ilani |
| author_facet | Hamed Alizadegan Behzad Rashidi Malki Arian Radmehr Hossein Karimi Mohsen Asghari Ilani |
| author_sort | Hamed Alizadegan |
| collection | DOAJ |
| description | Responsible, efficient, and environmentally conscious energy consumption practices are increasingly essential for ensuring the reliability of the modern electricity grid. This study focuses on leveraging time series analysis to improve forecasting accuracy, crucial for various application domains where real-world time series data often exhibit complex, non-linear patterns. Our approach advocates for utilizing long short-term memory (LSTM) and bidirectional long short-term memory (Bi-LSTM) models for precise time series forecasting. To ensure a fair evaluation, we compare the performance of our proposed approach with traditional neural networks, time-series forecasting methods, and conventional decline curves. Additionally, individual models based on LSTM, Bi-LSTM, and other machine learning methods are implemented for a comprehensive assessment. Experimental results consistently demonstrate that our proposed model outperforms all benchmarking methods in terms of mean absolute error (MAE) across most datasets. Addressing the imbalance between activations by consumer and prosumer groups, our predictions show superior performance compared to several traditional forecasting methods, such as the autoregressive integrated moving average (ARIMA) model and seasonal autoregressive integrated moving average (SARIMA) model. Specifically, the root mean square error (RMSE) of Bi-LSTM is 5.35%, 46.08%, and 50.6% lower than LSTM, ARIMA, and SARIMA, respectively, on the May test data. |
| format | Article |
| id | doaj-art-55e909e3fdf24240a4243cd705eb1733 |
| institution | Kabale University |
| issn | 0144-5987 2048-4054 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Energy Exploration & Exploitation |
| spelling | doaj-art-55e909e3fdf24240a4243cd705eb17332025-01-15T11:04:16ZengSAGE PublishingEnergy Exploration & Exploitation0144-59872048-40542025-01-014310.1177/01445987241269496Comparative study of long short-term memory (LSTM), bidirectional LSTM, and traditional machine learning approaches for energy consumption predictionHamed Alizadegan0Behzad Rashidi Malki1Arian Radmehr2Hossein Karimi3Mohsen Asghari Ilani4 Department of Computer and Information Technology Engineering, , Qazvin, Iran Department of Computer, , Bonab, East Azerbaijan, Iran Department of Computer Engineering, , Tehran, Iran Department of Electrical, Computer and IT Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran School of Mechanical Engineering, College of Engineering, , Tehran, IranResponsible, efficient, and environmentally conscious energy consumption practices are increasingly essential for ensuring the reliability of the modern electricity grid. This study focuses on leveraging time series analysis to improve forecasting accuracy, crucial for various application domains where real-world time series data often exhibit complex, non-linear patterns. Our approach advocates for utilizing long short-term memory (LSTM) and bidirectional long short-term memory (Bi-LSTM) models for precise time series forecasting. To ensure a fair evaluation, we compare the performance of our proposed approach with traditional neural networks, time-series forecasting methods, and conventional decline curves. Additionally, individual models based on LSTM, Bi-LSTM, and other machine learning methods are implemented for a comprehensive assessment. Experimental results consistently demonstrate that our proposed model outperforms all benchmarking methods in terms of mean absolute error (MAE) across most datasets. Addressing the imbalance between activations by consumer and prosumer groups, our predictions show superior performance compared to several traditional forecasting methods, such as the autoregressive integrated moving average (ARIMA) model and seasonal autoregressive integrated moving average (SARIMA) model. Specifically, the root mean square error (RMSE) of Bi-LSTM is 5.35%, 46.08%, and 50.6% lower than LSTM, ARIMA, and SARIMA, respectively, on the May test data.https://doi.org/10.1177/01445987241269496 |
| spellingShingle | Hamed Alizadegan Behzad Rashidi Malki Arian Radmehr Hossein Karimi Mohsen Asghari Ilani Comparative study of long short-term memory (LSTM), bidirectional LSTM, and traditional machine learning approaches for energy consumption prediction Energy Exploration & Exploitation |
| title | Comparative study of long short-term memory (LSTM), bidirectional LSTM, and traditional machine learning approaches for energy consumption prediction |
| title_full | Comparative study of long short-term memory (LSTM), bidirectional LSTM, and traditional machine learning approaches for energy consumption prediction |
| title_fullStr | Comparative study of long short-term memory (LSTM), bidirectional LSTM, and traditional machine learning approaches for energy consumption prediction |
| title_full_unstemmed | Comparative study of long short-term memory (LSTM), bidirectional LSTM, and traditional machine learning approaches for energy consumption prediction |
| title_short | Comparative study of long short-term memory (LSTM), bidirectional LSTM, and traditional machine learning approaches for energy consumption prediction |
| title_sort | comparative study of long short term memory lstm bidirectional lstm and traditional machine learning approaches for energy consumption prediction |
| url | https://doi.org/10.1177/01445987241269496 |
| work_keys_str_mv | AT hamedalizadegan comparativestudyoflongshorttermmemorylstmbidirectionallstmandtraditionalmachinelearningapproachesforenergyconsumptionprediction AT behzadrashidimalki comparativestudyoflongshorttermmemorylstmbidirectionallstmandtraditionalmachinelearningapproachesforenergyconsumptionprediction AT arianradmehr comparativestudyoflongshorttermmemorylstmbidirectionallstmandtraditionalmachinelearningapproachesforenergyconsumptionprediction AT hosseinkarimi comparativestudyoflongshorttermmemorylstmbidirectionallstmandtraditionalmachinelearningapproachesforenergyconsumptionprediction AT mohsenasghariilani comparativestudyoflongshorttermmemorylstmbidirectionallstmandtraditionalmachinelearningapproachesforenergyconsumptionprediction |