An analysis of case studies for advancing photovoltaic power forecasting through multi-scale fusion techniques
Abstract Integration renewable energy sources into current power generation systems necessitates accurate forecasting to optimize and preserve supply–demand restrictions in the electrical grids. Due to the highly random nature of environmental conditions, accurate prediction of PV power has limitati...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-03-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-57398-z |
| _version_ | 1797247349781692416 |
|---|---|
| author | Mawloud Guermoui Amor Fezzani Zaiani Mohamed Abdelaziz Rabehi Khaled Ferkous Nadjem Bailek Sabrina Bouallit Abdelkader Riche Mohit Bajaj Shir Ahmad Dost Mohammadi Enas Ali Sherif S. M. Ghoneim |
| author_facet | Mawloud Guermoui Amor Fezzani Zaiani Mohamed Abdelaziz Rabehi Khaled Ferkous Nadjem Bailek Sabrina Bouallit Abdelkader Riche Mohit Bajaj Shir Ahmad Dost Mohammadi Enas Ali Sherif S. M. Ghoneim |
| author_sort | Mawloud Guermoui |
| collection | DOAJ |
| description | Abstract Integration renewable energy sources into current power generation systems necessitates accurate forecasting to optimize and preserve supply–demand restrictions in the electrical grids. Due to the highly random nature of environmental conditions, accurate prediction of PV power has limitations, particularly on long and short periods. Thus, this research provides a new hybrid model for forecasting short PV power based on the fusing of multi-frequency information of different decomposition techniques that will allow a forecaster to provide reliable forecasts. We evaluate and provide insights into the performance of five multi-scale decomposition algorithms combined with a deep convolution neural network (CNN). Additionally, we compare the suggested combination approach's performance to that of existing forecast models. An exhaustive assessment is carried out using three grid-connected PV power plants in Algeria with a total installed capacity of 73.1 MW. The developed fusing strategy displayed an outstanding forecasting performance. The comparative analysis of the proposed combination method with the stand-alone forecast model and other hybridization techniques proves its superiority in terms of forecasting precision, with an RMSE varying in the range of [0.454–1.54] for the three studied PV stations. |
| first_indexed | 2024-04-24T19:57:17Z |
| format | Article |
| id | doaj.art-9b2bc810db1a439eb5b37afc8127cd0a |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-24T19:57:17Z |
| publishDate | 2024-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-9b2bc810db1a439eb5b37afc8127cd0a2024-03-24T12:16:06ZengNature PortfolioScientific Reports2045-23222024-03-0114112310.1038/s41598-024-57398-zAn analysis of case studies for advancing photovoltaic power forecasting through multi-scale fusion techniquesMawloud Guermoui0Amor Fezzani1Zaiani Mohamed2Abdelaziz Rabehi3Khaled Ferkous4Nadjem Bailek5Sabrina Bouallit6Abdelkader Riche7Mohit Bajaj8Shir Ahmad Dost Mohammadi9Enas Ali10Sherif S. M. Ghoneim11Centre de Développement des Energies Renouvelables, CDER, Unité de Recherche Appliquée en Energies Renouvelables, URAERCentre de Développement des Energies Renouvelables, CDER, Unité de Recherche Appliquée en Energies Renouvelables, URAERCentre de Développement des Energies Renouvelables, CDER, Unité de Recherche Appliquée en Energies Renouvelables, URAERTelecommunications and Smart Systems Laboratory, University of ZianeAchourMaterials, Energy Systems Technology and Environment Laboratory, Ghardaia UniversityEnergies and Materials Research Laboratory, Faculty of Sciences and Technology, University of TamanghassetCentre de Développement des Energies Renouvelables, CDER, Unité de Recherche Appliquée en Energies Renouvelables, URAERUniversity of Sciences and Technology Houari BoumedieneDepartment of Electrical Engineering, Graphic Era (Deemed to Be University)Department of Electrical and Electronics, Faculty of Engineering, Alberoni UniversityCentre of Research Impact and Outcome, Chitkara University Institute of Engineering and Technology, Chitkara UniversityDepartment of Electrical Engineering, College of Engineering, Taif UniversityAbstract Integration renewable energy sources into current power generation systems necessitates accurate forecasting to optimize and preserve supply–demand restrictions in the electrical grids. Due to the highly random nature of environmental conditions, accurate prediction of PV power has limitations, particularly on long and short periods. Thus, this research provides a new hybrid model for forecasting short PV power based on the fusing of multi-frequency information of different decomposition techniques that will allow a forecaster to provide reliable forecasts. We evaluate and provide insights into the performance of five multi-scale decomposition algorithms combined with a deep convolution neural network (CNN). Additionally, we compare the suggested combination approach's performance to that of existing forecast models. An exhaustive assessment is carried out using three grid-connected PV power plants in Algeria with a total installed capacity of 73.1 MW. The developed fusing strategy displayed an outstanding forecasting performance. The comparative analysis of the proposed combination method with the stand-alone forecast model and other hybridization techniques proves its superiority in terms of forecasting precision, with an RMSE varying in the range of [0.454–1.54] for the three studied PV stations.https://doi.org/10.1038/s41598-024-57398-zTime series forecastingPhotovoltaicDeep learningHybrid methodsSignal processing |
| spellingShingle | Mawloud Guermoui Amor Fezzani Zaiani Mohamed Abdelaziz Rabehi Khaled Ferkous Nadjem Bailek Sabrina Bouallit Abdelkader Riche Mohit Bajaj Shir Ahmad Dost Mohammadi Enas Ali Sherif S. M. Ghoneim An analysis of case studies for advancing photovoltaic power forecasting through multi-scale fusion techniques Scientific Reports Time series forecasting Photovoltaic Deep learning Hybrid methods Signal processing |
| title | An analysis of case studies for advancing photovoltaic power forecasting through multi-scale fusion techniques |
| title_full | An analysis of case studies for advancing photovoltaic power forecasting through multi-scale fusion techniques |
| title_fullStr | An analysis of case studies for advancing photovoltaic power forecasting through multi-scale fusion techniques |
| title_full_unstemmed | An analysis of case studies for advancing photovoltaic power forecasting through multi-scale fusion techniques |
| title_short | An analysis of case studies for advancing photovoltaic power forecasting through multi-scale fusion techniques |
| title_sort | analysis of case studies for advancing photovoltaic power forecasting through multi scale fusion techniques |
| topic | Time series forecasting Photovoltaic Deep learning Hybrid methods Signal processing |
| url | https://doi.org/10.1038/s41598-024-57398-z |
| work_keys_str_mv | AT mawloudguermoui ananalysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT amorfezzani ananalysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT zaianimohamed ananalysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT abdelazizrabehi ananalysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT khaledferkous ananalysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT nadjembailek ananalysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT sabrinabouallit ananalysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT abdelkaderriche ananalysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT mohitbajaj ananalysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT shirahmaddostmohammadi ananalysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT enasali ananalysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT sherifsmghoneim ananalysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT mawloudguermoui analysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT amorfezzani analysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT zaianimohamed analysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT abdelazizrabehi analysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT khaledferkous analysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT nadjembailek analysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT sabrinabouallit analysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT abdelkaderriche analysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT mohitbajaj analysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT shirahmaddostmohammadi analysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT enasali analysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques AT sherifsmghoneim analysisofcasestudiesforadvancingphotovoltaicpowerforecastingthroughmultiscalefusiontechniques |