Extended-Window Algorithms for Model Prediction Applied to Hybrid Power Systems
This paper proposes extended-window algorithms for model prediction and applies them to optimize hybrid power systems. We consider a hybrid power system comprising solar panels, batteries, a fuel cell, and a chemical hydrogen generation system. The proposed algorithms enable the periodic updating of...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Technologies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7080/12/1/6 |
| _version_ | 1797342507828248576 |
|---|---|
| author | Fu-Cheng Wang Hsiao-Tzu Huang |
| author_facet | Fu-Cheng Wang Hsiao-Tzu Huang |
| author_sort | Fu-Cheng Wang |
| collection | DOAJ |
| description | This paper proposes extended-window algorithms for model prediction and applies them to optimize hybrid power systems. We consider a hybrid power system comprising solar panels, batteries, a fuel cell, and a chemical hydrogen generation system. The proposed algorithms enable the periodic updating of prediction models and corresponding changes in system parts and power management based on the accumulated data. We first develop a hybrid power model to evaluate system responses under different conditions. We then build prediction models using five artificial intelligence algorithms. Among them, the light gradient boosting machine and extreme gradient boosting methods achieve the highest accuracies for predicting solar radiation and load responses, respectively. Therefore, we apply these two models to forecast solar and load responses. Third, we introduce extended-window algorithms and investigate the effects of window sizes and replacement costs on system performance. The results show that the optimal window size is one week, and the system cost is 13.57% lower than the cost of the system that does not use the extended-window algorithms. The proposed method also tends to make fewer component replacements when the replacement cost increases. Finally, we design experiments to demonstrate the feasibility and effectiveness of systems using extended-window model prediction. |
| first_indexed | 2024-03-08T10:34:33Z |
| format | Article |
| id | doaj.art-8dbaea57cc5c4cafa78edd2ccd71a6aa |
| institution | Directory Open Access Journal |
| issn | 2227-7080 |
| language | English |
| last_indexed | 2024-03-08T10:34:33Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Technologies |
| spelling | doaj.art-8dbaea57cc5c4cafa78edd2ccd71a6aa2024-01-26T18:40:06ZengMDPI AGTechnologies2227-70802024-01-01121610.3390/technologies12010006Extended-Window Algorithms for Model Prediction Applied to Hybrid Power SystemsFu-Cheng Wang0Hsiao-Tzu Huang1Department of Mechanical Engineering, National Taiwan University, Taipei 106, TaiwanDepartment of Mechanical Engineering, National Taiwan University, Taipei 106, TaiwanThis paper proposes extended-window algorithms for model prediction and applies them to optimize hybrid power systems. We consider a hybrid power system comprising solar panels, batteries, a fuel cell, and a chemical hydrogen generation system. The proposed algorithms enable the periodic updating of prediction models and corresponding changes in system parts and power management based on the accumulated data. We first develop a hybrid power model to evaluate system responses under different conditions. We then build prediction models using five artificial intelligence algorithms. Among them, the light gradient boosting machine and extreme gradient boosting methods achieve the highest accuracies for predicting solar radiation and load responses, respectively. Therefore, we apply these two models to forecast solar and load responses. Third, we introduce extended-window algorithms and investigate the effects of window sizes and replacement costs on system performance. The results show that the optimal window size is one week, and the system cost is 13.57% lower than the cost of the system that does not use the extended-window algorithms. The proposed method also tends to make fewer component replacements when the replacement cost increases. Finally, we design experiments to demonstrate the feasibility and effectiveness of systems using extended-window model prediction.https://www.mdpi.com/2227-7080/12/1/6hybrid powerfuel cellpredictionmanagementoptimizationextended window |
| spellingShingle | Fu-Cheng Wang Hsiao-Tzu Huang Extended-Window Algorithms for Model Prediction Applied to Hybrid Power Systems Technologies hybrid power fuel cell prediction management optimization extended window |
| title | Extended-Window Algorithms for Model Prediction Applied to Hybrid Power Systems |
| title_full | Extended-Window Algorithms for Model Prediction Applied to Hybrid Power Systems |
| title_fullStr | Extended-Window Algorithms for Model Prediction Applied to Hybrid Power Systems |
| title_full_unstemmed | Extended-Window Algorithms for Model Prediction Applied to Hybrid Power Systems |
| title_short | Extended-Window Algorithms for Model Prediction Applied to Hybrid Power Systems |
| title_sort | extended window algorithms for model prediction applied to hybrid power systems |
| topic | hybrid power fuel cell prediction management optimization extended window |
| url | https://www.mdpi.com/2227-7080/12/1/6 |
| work_keys_str_mv | AT fuchengwang extendedwindowalgorithmsformodelpredictionappliedtohybridpowersystems AT hsiaotzuhuang extendedwindowalgorithmsformodelpredictionappliedtohybridpowersystems |