Optimization-driven extreme learning machine for floating photovoltaic power prediction: A teaching learning-based approach
Accurate power prediction for floating photovoltaic (FPV) systems is essential for reliable grid integration, yet existing forecasting methods suffer from suboptimal parameter configuration, excessive computational demands, and poor performance under dynamic conditions. This study presents a novel T...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Physics
2025
|
| Subjects: | |
| Online Access: | https://umpir.ump.edu.my/id/eprint/45379/ |
| _version_ | 1848827401936568320 |
|---|---|
| author | Mohd Redzuan, Ahmad Nor Farizan, Zakaria Mohd Shawal, Jadin Mohd Herwan, Sulaiman |
| author_facet | Mohd Redzuan, Ahmad Nor Farizan, Zakaria Mohd Shawal, Jadin Mohd Herwan, Sulaiman |
| author_sort | Mohd Redzuan, Ahmad |
| building | UMP Institutional Repository |
| collection | Online Access |
| description | Accurate power prediction for floating photovoltaic (FPV) systems is essential for reliable grid integration, yet existing forecasting methods suffer from suboptimal parameter configuration, excessive computational demands, and poor performance under dynamic conditions. This study presents a novel Teaching–Learning-Based Optimization enhanced Extreme Learning Machine (TLBO-ELM) framework that achieves optimal parameter configuration without algorithmic tuning while maintaining computational efficiency for real-time deployment. Unlike conventional approaches, the TLBO-ELM integrates the parameter-free optimization capabilities of TLBO with ELM’s analytical weight calculation, systematically optimizing input weights and biases through simulated teaching–learning processes, thereby eliminates random initialization sensitivity while ensuring global optimization convergence. The framework was validated using comprehensive year-long operational data from a Malaysian FPV installation and benchmarked against established optimization-based ELM variants (GA-ELM, PSO-ELM, BMO-ELM). Results demonstrate superior performance with R2 = 0.9384, RMSE = 7.82 kW, and MAE = 3.17 kW significantly outperforming all benchmark methods with statistical significance at p < 0.001. Notably, comprehensive interpretability analysis revealed that three-phase electrical current measurements dominate predictive capability, enabling cost-effective monitoring strategies for resource-constrained marine environments. The framework maintains robust performance across diverse operational conditions while acknowledging specific limitations during extreme weather transitions and rapid power fluctuations. This work represents the first parameter-free optimization approach for FPV forecasting that simultaneously achieves superior accuracy and computational efficiency, enabling practical real-time deployment in resource-constrained marine environments and advancing optimization-driven machine learning for renewable energy applications. |
| first_indexed | 2025-11-15T04:00:08Z |
| format | Article |
| id | ump-45379 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T04:00:08Z |
| publishDate | 2025 |
| publisher | Institute of Physics |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-453792025-08-18T07:38:16Z https://umpir.ump.edu.my/id/eprint/45379/ Optimization-driven extreme learning machine for floating photovoltaic power prediction: A teaching learning-based approach Mohd Redzuan, Ahmad Nor Farizan, Zakaria Mohd Shawal, Jadin Mohd Herwan, Sulaiman QA75 Electronic computers. Computer science TK Electrical engineering. Electronics Nuclear engineering Accurate power prediction for floating photovoltaic (FPV) systems is essential for reliable grid integration, yet existing forecasting methods suffer from suboptimal parameter configuration, excessive computational demands, and poor performance under dynamic conditions. This study presents a novel Teaching–Learning-Based Optimization enhanced Extreme Learning Machine (TLBO-ELM) framework that achieves optimal parameter configuration without algorithmic tuning while maintaining computational efficiency for real-time deployment. Unlike conventional approaches, the TLBO-ELM integrates the parameter-free optimization capabilities of TLBO with ELM’s analytical weight calculation, systematically optimizing input weights and biases through simulated teaching–learning processes, thereby eliminates random initialization sensitivity while ensuring global optimization convergence. The framework was validated using comprehensive year-long operational data from a Malaysian FPV installation and benchmarked against established optimization-based ELM variants (GA-ELM, PSO-ELM, BMO-ELM). Results demonstrate superior performance with R2 = 0.9384, RMSE = 7.82 kW, and MAE = 3.17 kW significantly outperforming all benchmark methods with statistical significance at p < 0.001. Notably, comprehensive interpretability analysis revealed that three-phase electrical current measurements dominate predictive capability, enabling cost-effective monitoring strategies for resource-constrained marine environments. The framework maintains robust performance across diverse operational conditions while acknowledging specific limitations during extreme weather transitions and rapid power fluctuations. This work represents the first parameter-free optimization approach for FPV forecasting that simultaneously achieves superior accuracy and computational efficiency, enabling practical real-time deployment in resource-constrained marine environments and advancing optimization-driven machine learning for renewable energy applications. Institute of Physics 2025-08-11 Article PeerReviewed pdf en https://umpir.ump.edu.my/id/eprint/45379/2/Optimization-driven%20extreme%20learning%20machine%20for%20floating%20photovoltaic.pdf Mohd Redzuan, Ahmad and Nor Farizan, Zakaria and Mohd Shawal, Jadin and Mohd Herwan, Sulaiman (2025) Optimization-driven extreme learning machine for floating photovoltaic power prediction: A teaching learning-based approach. Engineering Research Express, 7 (3). pp. 1-26. ISSN 2631-8695. (Published) https://doi.org/10.1088/2631-8695/adf693 https://doi.org/10.1088/2631-8695/adf693 https://doi.org/10.1088/2631-8695/adf693 |
| spellingShingle | QA75 Electronic computers. Computer science TK Electrical engineering. Electronics Nuclear engineering Mohd Redzuan, Ahmad Nor Farizan, Zakaria Mohd Shawal, Jadin Mohd Herwan, Sulaiman Optimization-driven extreme learning machine for floating photovoltaic power prediction: A teaching learning-based approach |
| title | Optimization-driven extreme learning machine for floating photovoltaic power prediction: A teaching learning-based approach |
| title_full | Optimization-driven extreme learning machine for floating photovoltaic power prediction: A teaching learning-based approach |
| title_fullStr | Optimization-driven extreme learning machine for floating photovoltaic power prediction: A teaching learning-based approach |
| title_full_unstemmed | Optimization-driven extreme learning machine for floating photovoltaic power prediction: A teaching learning-based approach |
| title_short | Optimization-driven extreme learning machine for floating photovoltaic power prediction: A teaching learning-based approach |
| title_sort | optimization-driven extreme learning machine for floating photovoltaic power prediction: a teaching learning-based approach |
| topic | QA75 Electronic computers. Computer science TK Electrical engineering. Electronics Nuclear engineering |
| url | https://umpir.ump.edu.my/id/eprint/45379/ https://umpir.ump.edu.my/id/eprint/45379/ https://umpir.ump.edu.my/id/eprint/45379/ |