A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural Network
Accurate electrical load forecasting is of great significance to help power companies in better scheduling and efficient management. Since high levels of uncertainties exist in the load time series, it is a challenging task to make accurate short-term load forecast (STLF). In recent years, deep lear...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-12-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/11/12/3493 |
| _version_ | 1828138856123203584 |
|---|---|
| author | Chujie Tian Jian Ma Chunhong Zhang Panpan Zhan |
| author_facet | Chujie Tian Jian Ma Chunhong Zhang Panpan Zhan |
| author_sort | Chujie Tian |
| collection | DOAJ |
| description | Accurate electrical load forecasting is of great significance to help power companies in better scheduling and efficient management. Since high levels of uncertainties exist in the load time series, it is a challenging task to make accurate short-term load forecast (STLF). In recent years, deep learning approaches provide better performance to predict electrical load in real world cases. The convolutional neural network (CNN) can extract the local trend and capture the same pattern, and the long short-term memory (LSTM) is proposed to learn the relationship in time steps. In this paper, a new deep neural network framework that integrates the hidden feature of the CNN model and the LSTM model is proposed to improve the forecasting accuracy. The proposed model was tested in a real-world case, and detailed experiments were conducted to validate its practicality and stability. The forecasting performance of the proposed model was compared with the LSTM model and the CNN model. The Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) were used as the evaluation indexes. The experimental results demonstrate that the proposed model can achieve better and stable performance in STLF. |
| first_indexed | 2024-04-11T18:43:57Z |
| format | Article |
| id | doaj.art-35775ae244f54f45a95c01018ff0c644 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-11T18:43:57Z |
| publishDate | 2018-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-35775ae244f54f45a95c01018ff0c6442022-12-22T04:08:54ZengMDPI AGEnergies1996-10732018-12-011112349310.3390/en11123493en11123493A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural NetworkChujie Tian0Jian Ma1Chunhong Zhang2Panpan Zhan3Institute of Network Technology, Beijing University of Posts and Telecommunications, Xitucheng Road No.10 Hadian District, Beijing 100876, ChinaInstitute of Network Technology, Beijing University of Posts and Telecommunications, Xitucheng Road No.10 Hadian District, Beijing 100876, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Xitucheng Road No.10 Hadian District, Beijing 100876, ChinaBeijing Institute of Spacecraft System Engineering, 104 YouYi Road Hadian District, Beijing 100094, ChinaAccurate electrical load forecasting is of great significance to help power companies in better scheduling and efficient management. Since high levels of uncertainties exist in the load time series, it is a challenging task to make accurate short-term load forecast (STLF). In recent years, deep learning approaches provide better performance to predict electrical load in real world cases. The convolutional neural network (CNN) can extract the local trend and capture the same pattern, and the long short-term memory (LSTM) is proposed to learn the relationship in time steps. In this paper, a new deep neural network framework that integrates the hidden feature of the CNN model and the LSTM model is proposed to improve the forecasting accuracy. The proposed model was tested in a real-world case, and detailed experiments were conducted to validate its practicality and stability. The forecasting performance of the proposed model was compared with the LSTM model and the CNN model. The Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) were used as the evaluation indexes. The experimental results demonstrate that the proposed model can achieve better and stable performance in STLF.https://www.mdpi.com/1996-1073/11/12/3493short-term load forecastlong short-term memory networksconvolutional neural networksdeep neural networksartificial intelligence |
| spellingShingle | Chujie Tian Jian Ma Chunhong Zhang Panpan Zhan A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural Network Energies short-term load forecast long short-term memory networks convolutional neural networks deep neural networks artificial intelligence |
| title | A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural Network |
| title_full | A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural Network |
| title_fullStr | A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural Network |
| title_full_unstemmed | A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural Network |
| title_short | A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural Network |
| title_sort | deep neural network model for short term load forecast based on long short term memory network and convolutional neural network |
| topic | short-term load forecast long short-term memory networks convolutional neural networks deep neural networks artificial intelligence |
| url | https://www.mdpi.com/1996-1073/11/12/3493 |
| work_keys_str_mv | AT chujietian adeepneuralnetworkmodelforshorttermloadforecastbasedonlongshorttermmemorynetworkandconvolutionalneuralnetwork AT jianma adeepneuralnetworkmodelforshorttermloadforecastbasedonlongshorttermmemorynetworkandconvolutionalneuralnetwork AT chunhongzhang adeepneuralnetworkmodelforshorttermloadforecastbasedonlongshorttermmemorynetworkandconvolutionalneuralnetwork AT panpanzhan adeepneuralnetworkmodelforshorttermloadforecastbasedonlongshorttermmemorynetworkandconvolutionalneuralnetwork AT chujietian deepneuralnetworkmodelforshorttermloadforecastbasedonlongshorttermmemorynetworkandconvolutionalneuralnetwork AT jianma deepneuralnetworkmodelforshorttermloadforecastbasedonlongshorttermmemorynetworkandconvolutionalneuralnetwork AT chunhongzhang deepneuralnetworkmodelforshorttermloadforecastbasedonlongshorttermmemorynetworkandconvolutionalneuralnetwork AT panpanzhan deepneuralnetworkmodelforshorttermloadforecastbasedonlongshorttermmemorynetworkandconvolutionalneuralnetwork |