Feasibility Study on the Influence of Data Partition Strategies on Ensemble Deep Learning: The Case of Forecasting Power Generation in South Korea
Ensemble deep learning methods have demonstrated significant improvements in forecasting the solar panel power generation using historical time-series data. Although many studies have used ensemble deep learning methods with various data partitioning strategies, most have only focused on improving t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/20/7482 |
| _version_ | 1827650452494221312 |
|---|---|
| author | Tserenpurev Chuluunsaikhan Jeong-Hun Kim Yoonsung Shin Sanghyun Choi Aziz Nasridinov |
| author_facet | Tserenpurev Chuluunsaikhan Jeong-Hun Kim Yoonsung Shin Sanghyun Choi Aziz Nasridinov |
| author_sort | Tserenpurev Chuluunsaikhan |
| collection | DOAJ |
| description | Ensemble deep learning methods have demonstrated significant improvements in forecasting the solar panel power generation using historical time-series data. Although many studies have used ensemble deep learning methods with various data partitioning strategies, most have only focused on improving the predictive methods by associating several different models or combining hyperparameters and interactions. In this study, we contend that we can enhance the precision of power generation forecasting by identifying a suitable data partition strategy and establishing the ideal number of partitions and subset sizes. Thus, we propose a feasibility study of the influence of data partition strategies on ensemble deep learning. We selected five time-series data partitioning strategies—window, shuffle, pyramid, vertical, and seasonal—that allow us to identify different characteristics and features in the time-series data. We conducted various experiments on two sources of solar panel datasets collected in Seoul and Gyeongju, South Korea. Additionally, LSTM-based bagging ensemble models were applied to combine the advantages of several single LSTM models. The experimental results reveal that the data partition strategies positively influence the forecasting of power generation. Specifically, the results demonstrate that ensemble models with data partition strategies outperform single LSTM models by approximately 4–11% in terms of the coefficient of determination (R<sup>2</sup>) score. |
| first_indexed | 2024-03-09T20:18:20Z |
| format | Article |
| id | doaj.art-59058723d45c435b8e543e494f13f529 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T20:18:20Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-59058723d45c435b8e543e494f13f5292023-11-23T23:55:22ZengMDPI AGEnergies1996-10732022-10-011520748210.3390/en15207482Feasibility Study on the Influence of Data Partition Strategies on Ensemble Deep Learning: The Case of Forecasting Power Generation in South KoreaTserenpurev Chuluunsaikhan0Jeong-Hun Kim1Yoonsung Shin2Sanghyun Choi3Aziz Nasridinov4Department of Computer Science, Chungbuk National University, Cheongju 28644, KoreaDepartment of Computer Science, Chungbuk National University, Cheongju 28644, KoreaDepartment of Computer Science, Chungbuk National University, Cheongju 28644, KoreaDepartment of Management Information Systems, Chungbuk National University, Cheongju 28644, KoreaDepartment of Computer Science, Chungbuk National University, Cheongju 28644, KoreaEnsemble deep learning methods have demonstrated significant improvements in forecasting the solar panel power generation using historical time-series data. Although many studies have used ensemble deep learning methods with various data partitioning strategies, most have only focused on improving the predictive methods by associating several different models or combining hyperparameters and interactions. In this study, we contend that we can enhance the precision of power generation forecasting by identifying a suitable data partition strategy and establishing the ideal number of partitions and subset sizes. Thus, we propose a feasibility study of the influence of data partition strategies on ensemble deep learning. We selected five time-series data partitioning strategies—window, shuffle, pyramid, vertical, and seasonal—that allow us to identify different characteristics and features in the time-series data. We conducted various experiments on two sources of solar panel datasets collected in Seoul and Gyeongju, South Korea. Additionally, LSTM-based bagging ensemble models were applied to combine the advantages of several single LSTM models. The experimental results reveal that the data partition strategies positively influence the forecasting of power generation. Specifically, the results demonstrate that ensemble models with data partition strategies outperform single LSTM models by approximately 4–11% in terms of the coefficient of determination (R<sup>2</sup>) score.https://www.mdpi.com/1996-1073/15/20/7482solar panelspower generationsolar panels with weatherlong short-term memorydata partition |
| spellingShingle | Tserenpurev Chuluunsaikhan Jeong-Hun Kim Yoonsung Shin Sanghyun Choi Aziz Nasridinov Feasibility Study on the Influence of Data Partition Strategies on Ensemble Deep Learning: The Case of Forecasting Power Generation in South Korea Energies solar panels power generation solar panels with weather long short-term memory data partition |
| title | Feasibility Study on the Influence of Data Partition Strategies on Ensemble Deep Learning: The Case of Forecasting Power Generation in South Korea |
| title_full | Feasibility Study on the Influence of Data Partition Strategies on Ensemble Deep Learning: The Case of Forecasting Power Generation in South Korea |
| title_fullStr | Feasibility Study on the Influence of Data Partition Strategies on Ensemble Deep Learning: The Case of Forecasting Power Generation in South Korea |
| title_full_unstemmed | Feasibility Study on the Influence of Data Partition Strategies on Ensemble Deep Learning: The Case of Forecasting Power Generation in South Korea |
| title_short | Feasibility Study on the Influence of Data Partition Strategies on Ensemble Deep Learning: The Case of Forecasting Power Generation in South Korea |
| title_sort | feasibility study on the influence of data partition strategies on ensemble deep learning the case of forecasting power generation in south korea |
| topic | solar panels power generation solar panels with weather long short-term memory data partition |
| url | https://www.mdpi.com/1996-1073/15/20/7482 |
| work_keys_str_mv | AT tserenpurevchuluunsaikhan feasibilitystudyontheinfluenceofdatapartitionstrategiesonensembledeeplearningthecaseofforecastingpowergenerationinsouthkorea AT jeonghunkim feasibilitystudyontheinfluenceofdatapartitionstrategiesonensembledeeplearningthecaseofforecastingpowergenerationinsouthkorea AT yoonsungshin feasibilitystudyontheinfluenceofdatapartitionstrategiesonensembledeeplearningthecaseofforecastingpowergenerationinsouthkorea AT sanghyunchoi feasibilitystudyontheinfluenceofdatapartitionstrategiesonensembledeeplearningthecaseofforecastingpowergenerationinsouthkorea AT aziznasridinov feasibilitystudyontheinfluenceofdatapartitionstrategiesonensembledeeplearningthecaseofforecastingpowergenerationinsouthkorea |