A comprehensive framework for effective long-short term solar yield forecasting
Due to the variability of Photovoltaic (PV) output, a forecasting framework is essential for grid connected PV plants to ensure a stable and uninterrupted power supply. Among existing prediction and forecasting algorithms, only some have attempted to provide a holistic framework for short and long-t...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-04-01
|
| Series: | Energy Conversion and Management: X |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590174524000138 |
| _version_ | 1827360784216227840 |
|---|---|
| author | Biplob Ray Dimuth Lasantha Vijayalaxmi Beeravalli Adnan Anwar Md Nurun Nabi Hanmin Sheng Fazlur Rashid S.M. Muyeen |
| author_facet | Biplob Ray Dimuth Lasantha Vijayalaxmi Beeravalli Adnan Anwar Md Nurun Nabi Hanmin Sheng Fazlur Rashid S.M. Muyeen |
| author_sort | Biplob Ray |
| collection | DOAJ |
| description | Due to the variability of Photovoltaic (PV) output, a forecasting framework is essential for grid connected PV plants to ensure a stable and uninterrupted power supply. Among existing prediction and forecasting algorithms, only some have attempted to provide a holistic framework for short and long-term forecasting of PV yield together using automated input feature selections and data cleaning features. Furthermore, it has been identified that many existing algorithms only predicted PV output instead of forecasting in future times; therefore, their reported accuracy needs to be upheld in forecasting scenarios. This paper has proposed a framework to streamline solar yield forecasting for both the short and long term to ensure effective integration of PV plant output with the main grid. The proposed framework has used a novel combination of XGBoost (eXtreme Gradient Boosting), time series seasonal decomposition and rolling LSTM (Long- and Short-Term Memory) model to address the need for a comprehensive forecasting framework in hourly, daily and yearly periods. Based on our experiment result, the developed framework has performed in 98% − 95% prediction accuracy with less than 0.15% normalized Root Mean Squire error (nRMSE). The framework has performed in 89%- 87% forecasting accuracy with less than 0.45% nRMSE. Both the prediction and forecasting performance of the proposed model have outperformed many benchmarks forecasting frameworks, including Long short-term memory (LSTM) based recurrent neural network (RNN), Full RNN (FRNN), Neural Network Ensemble (NNE), Neural Network with AdaBoost, and many more as detailed in our comparative study section. |
| first_indexed | 2024-03-08T06:54:22Z |
| format | Article |
| id | doaj.art-ce71634ead424b03a42a99ea5b249403 |
| institution | Directory Open Access Journal |
| issn | 2590-1745 |
| language | English |
| last_indexed | 2024-03-08T06:54:22Z |
| publishDate | 2024-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy Conversion and Management: X |
| spelling | doaj.art-ce71634ead424b03a42a99ea5b2494032024-02-03T06:39:17ZengElsevierEnergy Conversion and Management: X2590-17452024-04-0122100535A comprehensive framework for effective long-short term solar yield forecastingBiplob Ray0Dimuth Lasantha1Vijayalaxmi Beeravalli2Adnan Anwar3Md Nurun Nabi4Hanmin Sheng5Fazlur Rashid6S.M. Muyeen7Central Queensland University, Melbourne, AustraliaCentral Queensland University, Rockhampton, AustraliaCentral Queensland University, Rockhampton, AustraliaCentre for Cyber Resilience and Trust (CREST), School of IT, Deakin University, AustraliaCentral Queensland University, Melbourne, Australia; Corresponding author.School of Automation Engineering, University of Science and Technology, Chengdu, ChinaRajshahi University of Engineering & Technology, Bangladesh; Missouri University of Science and Technology, Rolla, MO 65401, USAQatar University, Doha, QatarDue to the variability of Photovoltaic (PV) output, a forecasting framework is essential for grid connected PV plants to ensure a stable and uninterrupted power supply. Among existing prediction and forecasting algorithms, only some have attempted to provide a holistic framework for short and long-term forecasting of PV yield together using automated input feature selections and data cleaning features. Furthermore, it has been identified that many existing algorithms only predicted PV output instead of forecasting in future times; therefore, their reported accuracy needs to be upheld in forecasting scenarios. This paper has proposed a framework to streamline solar yield forecasting for both the short and long term to ensure effective integration of PV plant output with the main grid. The proposed framework has used a novel combination of XGBoost (eXtreme Gradient Boosting), time series seasonal decomposition and rolling LSTM (Long- and Short-Term Memory) model to address the need for a comprehensive forecasting framework in hourly, daily and yearly periods. Based on our experiment result, the developed framework has performed in 98% − 95% prediction accuracy with less than 0.15% normalized Root Mean Squire error (nRMSE). The framework has performed in 89%- 87% forecasting accuracy with less than 0.45% nRMSE. Both the prediction and forecasting performance of the proposed model have outperformed many benchmarks forecasting frameworks, including Long short-term memory (LSTM) based recurrent neural network (RNN), Full RNN (FRNN), Neural Network Ensemble (NNE), Neural Network with AdaBoost, and many more as detailed in our comparative study section.http://www.sciencedirect.com/science/article/pii/S2590174524000138PredictionForecastingPhotovoltaicMachine LearningFramework |
| spellingShingle | Biplob Ray Dimuth Lasantha Vijayalaxmi Beeravalli Adnan Anwar Md Nurun Nabi Hanmin Sheng Fazlur Rashid S.M. Muyeen A comprehensive framework for effective long-short term solar yield forecasting Energy Conversion and Management: X Prediction Forecasting Photovoltaic Machine Learning Framework |
| title | A comprehensive framework for effective long-short term solar yield forecasting |
| title_full | A comprehensive framework for effective long-short term solar yield forecasting |
| title_fullStr | A comprehensive framework for effective long-short term solar yield forecasting |
| title_full_unstemmed | A comprehensive framework for effective long-short term solar yield forecasting |
| title_short | A comprehensive framework for effective long-short term solar yield forecasting |
| title_sort | comprehensive framework for effective long short term solar yield forecasting |
| topic | Prediction Forecasting Photovoltaic Machine Learning Framework |
| url | http://www.sciencedirect.com/science/article/pii/S2590174524000138 |
| work_keys_str_mv | AT biplobray acomprehensiveframeworkforeffectivelongshorttermsolaryieldforecasting AT dimuthlasantha acomprehensiveframeworkforeffectivelongshorttermsolaryieldforecasting AT vijayalaxmibeeravalli acomprehensiveframeworkforeffectivelongshorttermsolaryieldforecasting AT adnananwar acomprehensiveframeworkforeffectivelongshorttermsolaryieldforecasting AT mdnurunnabi acomprehensiveframeworkforeffectivelongshorttermsolaryieldforecasting AT hanminsheng acomprehensiveframeworkforeffectivelongshorttermsolaryieldforecasting AT fazlurrashid acomprehensiveframeworkforeffectivelongshorttermsolaryieldforecasting AT smmuyeen acomprehensiveframeworkforeffectivelongshorttermsolaryieldforecasting AT biplobray comprehensiveframeworkforeffectivelongshorttermsolaryieldforecasting AT dimuthlasantha comprehensiveframeworkforeffectivelongshorttermsolaryieldforecasting AT vijayalaxmibeeravalli comprehensiveframeworkforeffectivelongshorttermsolaryieldforecasting AT adnananwar comprehensiveframeworkforeffectivelongshorttermsolaryieldforecasting AT mdnurunnabi comprehensiveframeworkforeffectivelongshorttermsolaryieldforecasting AT hanminsheng comprehensiveframeworkforeffectivelongshorttermsolaryieldforecasting AT fazlurrashid comprehensiveframeworkforeffectivelongshorttermsolaryieldforecasting AT smmuyeen comprehensiveframeworkforeffectivelongshorttermsolaryieldforecasting |