Data set visualization.
<div><p>This paper proposes a model called X-LSTM-EO, which integrates explainable artificial intelligence (XAI), long short-term memory (LSTM), and equilibrium optimizer (EO) to reliably forecast solar power generation. The LSTM component forecasts power generation rates based on enviro...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , |
| Published: |
2024
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852026208595738624 |
|---|---|
| author | Rizk M. Rizk-Allah (18625751) |
| author2 | Lobna M. Abouelmagd (19787120) Ashraf Darwish (19207662) Vaclav Snasel (4489414) Aboul Ella Hassanien (15572857) |
| author2_role | author author author author |
| author_facet | Rizk M. Rizk-Allah (18625751) Lobna M. Abouelmagd (19787120) Ashraf Darwish (19207662) Vaclav Snasel (4489414) Aboul Ella Hassanien (15572857) |
| author_role | author |
| dc.creator.none.fl_str_mv | Rizk M. Rizk-Allah (18625751) Lobna M. Abouelmagd (19787120) Ashraf Darwish (19207662) Vaclav Snasel (4489414) Aboul Ella Hassanien (15572857) |
| dc.date.none.fl_str_mv | 2024-10-02T17:31:16Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0308002.g002 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/Data_set_visualization_/27155417 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Genetics Ecology Science Policy Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified smart solar systems power generation patterns photovoltaic power units machine learning algorithm implemented utilizing tensorflow based local interpretable original model ’ eo component optimizes div >< p rmse ), coefficient model called x lstm model ’ proposed x efficiency coefficient proposed model lstm ), eo model term memory simulations demonstrate pso optimizer paper proposes paper improve keras within independent explanation improvement rate gradient boosting five metrics explainable ai equilibrium optimizer eo optimizer environmental conditions employed instead ec respectively ec ). decision tree critical factors conventional lstm abrupt changes |
| dc.title.none.fl_str_mv | Data set visualization. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <div><p>This paper proposes a model called X-LSTM-EO, which integrates explainable artificial intelligence (XAI), long short-term memory (LSTM), and equilibrium optimizer (EO) to reliably forecast solar power generation. The LSTM component forecasts power generation rates based on environmental conditions, while the EO component optimizes the LSTM model’s hyper-parameters through training. The XAI-based Local Interpretable and Model-independent Explanation (LIME) is adapted to identify the critical factors that influence the accuracy of the power generation forecasts model in smart solar systems. The effectiveness of the proposed X-LSTM-EO model is evaluated through the use of five metrics; R-squared (R<sup>2</sup>), root mean square error (RMSE), coefficient of variation (COV), mean absolute error (MAE), and efficiency coefficient (EC). The proposed model gains values 0.99, 0.46, 0.35, 0.229, and 0.95, for R<sup>2</sup>, RMSE, COV, MAE, and EC respectively. The results of this paper improve the performance of the original model’s conventional LSTM, where the improvement rate is; 148%, 21%, 27%, 20%, 134% for R<sup>2</sup>, RMSE, COV, MAE, and EC respectively. The performance of LSTM is compared with other machine learning algorithm such as Decision tree (DT), Linear regression (LR) and Gradient Boosting. It was shown that the LSTM model worked better than DT and LR when the results were compared. Additionally, the PSO optimizer was employed instead of the EO optimizer to validate the outcomes, which further demonstrated the efficacy of the EO optimizer. The experimental results and simulations demonstrate that the proposed model can accurately estimate PV power generation in response to abrupt changes in power generation patterns. Moreover, the proposed model might assist in optimizing the operations of photovoltaic power units. The proposed model is implemented utilizing TensorFlow and Keras within the Google Collab environment.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_308b7eeaeee9490b5b06f06ef571b5e1 |
| identifier_str_mv | 10.1371/journal.pone.0308002.g002 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/27155417 |
| publishDate | 2024 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Data set visualization.Rizk M. Rizk-Allah (18625751)Lobna M. Abouelmagd (19787120)Ashraf Darwish (19207662)Vaclav Snasel (4489414)Aboul Ella Hassanien (15572857)GeneticsEcologyScience PolicySpace ScienceBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedsmart solar systemspower generation patternsphotovoltaic power unitsmachine learning algorithmimplemented utilizing tensorflowbased local interpretableoriginal model ’eo component optimizesdiv >< prmse ), coefficientmodel called xlstm model ’proposed xefficiency coefficientproposed modellstm ),eo modelterm memorysimulations demonstratepso optimizerpaper proposespaper improvekeras withinindependent explanationimprovement rategradient boostingfive metricsexplainable aiequilibrium optimizereo optimizerenvironmental conditionsemployed insteadec respectivelyec ).decision treecritical factorsconventional lstmabrupt changes<div><p>This paper proposes a model called X-LSTM-EO, which integrates explainable artificial intelligence (XAI), long short-term memory (LSTM), and equilibrium optimizer (EO) to reliably forecast solar power generation. The LSTM component forecasts power generation rates based on environmental conditions, while the EO component optimizes the LSTM model’s hyper-parameters through training. The XAI-based Local Interpretable and Model-independent Explanation (LIME) is adapted to identify the critical factors that influence the accuracy of the power generation forecasts model in smart solar systems. The effectiveness of the proposed X-LSTM-EO model is evaluated through the use of five metrics; R-squared (R<sup>2</sup>), root mean square error (RMSE), coefficient of variation (COV), mean absolute error (MAE), and efficiency coefficient (EC). The proposed model gains values 0.99, 0.46, 0.35, 0.229, and 0.95, for R<sup>2</sup>, RMSE, COV, MAE, and EC respectively. The results of this paper improve the performance of the original model’s conventional LSTM, where the improvement rate is; 148%, 21%, 27%, 20%, 134% for R<sup>2</sup>, RMSE, COV, MAE, and EC respectively. The performance of LSTM is compared with other machine learning algorithm such as Decision tree (DT), Linear regression (LR) and Gradient Boosting. It was shown that the LSTM model worked better than DT and LR when the results were compared. Additionally, the PSO optimizer was employed instead of the EO optimizer to validate the outcomes, which further demonstrated the efficacy of the EO optimizer. The experimental results and simulations demonstrate that the proposed model can accurately estimate PV power generation in response to abrupt changes in power generation patterns. Moreover, the proposed model might assist in optimizing the operations of photovoltaic power units. The proposed model is implemented utilizing TensorFlow and Keras within the Google Collab environment.</p></div>2024-10-02T17:31:16ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0308002.g002https://figshare.com/articles/figure/Data_set_visualization_/27155417CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/271554172024-10-02T17:31:16Z |
| spellingShingle | Data set visualization. Rizk M. Rizk-Allah (18625751) Genetics Ecology Science Policy Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified smart solar systems power generation patterns photovoltaic power units machine learning algorithm implemented utilizing tensorflow based local interpretable original model ’ eo component optimizes div >< p rmse ), coefficient model called x lstm model ’ proposed x efficiency coefficient proposed model lstm ), eo model term memory simulations demonstrate pso optimizer paper proposes paper improve keras within independent explanation improvement rate gradient boosting five metrics explainable ai equilibrium optimizer eo optimizer environmental conditions employed instead ec respectively ec ). decision tree critical factors conventional lstm abrupt changes |
| status_str | publishedVersion |
| title | Data set visualization. |
| title_full | Data set visualization. |
| title_fullStr | Data set visualization. |
| title_full_unstemmed | Data set visualization. |
| title_short | Data set visualization. |
| title_sort | Data set visualization. |
| topic | Genetics Ecology Science Policy Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified smart solar systems power generation patterns photovoltaic power units machine learning algorithm implemented utilizing tensorflow based local interpretable original model ’ eo component optimizes div >< p rmse ), coefficient model called x lstm model ’ proposed x efficiency coefficient proposed model lstm ), eo model term memory simulations demonstrate pso optimizer paper proposes paper improve keras within independent explanation improvement rate gradient boosting five metrics explainable ai equilibrium optimizer eo optimizer environmental conditions employed instead ec respectively ec ). decision tree critical factors conventional lstm abrupt changes |