A novel prediction of the PV system output current based on integration of optimized hyperparameters of multi-layer neural networks and polynomial regression models
The renewable energy system has yielded substantial enhancements to worldwide power generation. Therefore, precise prediction of long-term renewable energy conductivity is vital for grid system. This study introduces a new predictive output current for the photovoltaic (PV) system using actual exper...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier B.V.
2025
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/120530/ http://psasir.upm.edu.my/id/eprint/120530/1/120530.pdf |
| _version_ | 1848868198204571648 |
|---|---|
| author | Ridha, Hussein Mohammed Hizam, Hashim Mirjalili, Seyedali Othman, Mohammad Lutfi Ya’acob, Mohammad Effendy Abdul Wahab, Noor Izzri Ahmadipour, Masoud |
| author_facet | Ridha, Hussein Mohammed Hizam, Hashim Mirjalili, Seyedali Othman, Mohammad Lutfi Ya’acob, Mohammad Effendy Abdul Wahab, Noor Izzri Ahmadipour, Masoud |
| author_sort | Ridha, Hussein Mohammed |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | The renewable energy system has yielded substantial enhancements to worldwide power generation. Therefore, precise prediction of long-term renewable energy conductivity is vital for grid system. This study introduces a new predictive output current for the photovoltaic (PV) system using actual experimental data. This research proposes three key contributions: The IMGO method is enhanced using several hybrid tactics to improve local search capabilities and increase exploration of significant regions within the feature space. Subsequently, the architecture of the multilayer feedforward artificial neural network is developed. The IMGO is employed to determine the appropriate hyperparameters of the model, ranging from the number of neurons in the hidden layers and learning rate. The Bayesian regularization backpropagation procedure is applied to update the weights and bias of the network. The proposed IMGOMFFNN model is ultimately combined with Polynomial regression model to improve the predictability of the PV system. The experimental results demonstrated that the proposed IMGO algorithm is very effective in addressing complex problems with high accuracy, capability, and speedy convergence. The proposed hybrid IMGOPMFFNN model proved its superior correlation evaluations, surpassing the performance of ant lion optimizer based on random forest (ALORF) model, two stages of ANN (ALO2ANN) model, long short-term memory (LSTM), gated recurrent unit (GRU), extreme learning machine (ELM), least square support vector machine (LSSVM), and convolutional neural network (CNN) models. The MATLAB code of the IMGO is free available at: https://www.mathworks.com/matlabcentral/fileexchange/177214-improved-mgo-method. |
| first_indexed | 2025-11-15T14:48:34Z |
| format | Article |
| id | upm-120530 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T14:48:34Z |
| publishDate | 2025 |
| publisher | Elsevier B.V. |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-1205302025-10-06T01:20:59Z http://psasir.upm.edu.my/id/eprint/120530/ A novel prediction of the PV system output current based on integration of optimized hyperparameters of multi-layer neural networks and polynomial regression models Ridha, Hussein Mohammed Hizam, Hashim Mirjalili, Seyedali Othman, Mohammad Lutfi Ya’acob, Mohammad Effendy Abdul Wahab, Noor Izzri Ahmadipour, Masoud The renewable energy system has yielded substantial enhancements to worldwide power generation. Therefore, precise prediction of long-term renewable energy conductivity is vital for grid system. This study introduces a new predictive output current for the photovoltaic (PV) system using actual experimental data. This research proposes three key contributions: The IMGO method is enhanced using several hybrid tactics to improve local search capabilities and increase exploration of significant regions within the feature space. Subsequently, the architecture of the multilayer feedforward artificial neural network is developed. The IMGO is employed to determine the appropriate hyperparameters of the model, ranging from the number of neurons in the hidden layers and learning rate. The Bayesian regularization backpropagation procedure is applied to update the weights and bias of the network. The proposed IMGOMFFNN model is ultimately combined with Polynomial regression model to improve the predictability of the PV system. The experimental results demonstrated that the proposed IMGO algorithm is very effective in addressing complex problems with high accuracy, capability, and speedy convergence. The proposed hybrid IMGOPMFFNN model proved its superior correlation evaluations, surpassing the performance of ant lion optimizer based on random forest (ALORF) model, two stages of ANN (ALO2ANN) model, long short-term memory (LSTM), gated recurrent unit (GRU), extreme learning machine (ELM), least square support vector machine (LSSVM), and convolutional neural network (CNN) models. The MATLAB code of the IMGO is free available at: https://www.mathworks.com/matlabcentral/fileexchange/177214-improved-mgo-method. Elsevier B.V. 2025 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/120530/1/120530.pdf Ridha, Hussein Mohammed and Hizam, Hashim and Mirjalili, Seyedali and Othman, Mohammad Lutfi and Ya’acob, Mohammad Effendy and Abdul Wahab, Noor Izzri and Ahmadipour, Masoud (2025) A novel prediction of the PV system output current based on integration of optimized hyperparameters of multi-layer neural networks and polynomial regression models. Next Energy, 8. art. no. 100256. pp. 1-15. ISSN 2949-821X https://www.sciencedirect.com/science/article/pii/S2949821X25000195?via%3Dihub 10.1016/j.nxener.2025.100256 |
| spellingShingle | Ridha, Hussein Mohammed Hizam, Hashim Mirjalili, Seyedali Othman, Mohammad Lutfi Ya’acob, Mohammad Effendy Abdul Wahab, Noor Izzri Ahmadipour, Masoud A novel prediction of the PV system output current based on integration of optimized hyperparameters of multi-layer neural networks and polynomial regression models |
| title | A novel prediction of the PV system output current based on integration of optimized hyperparameters of multi-layer neural networks and polynomial regression models |
| title_full | A novel prediction of the PV system output current based on integration of optimized hyperparameters of multi-layer neural networks and polynomial regression models |
| title_fullStr | A novel prediction of the PV system output current based on integration of optimized hyperparameters of multi-layer neural networks and polynomial regression models |
| title_full_unstemmed | A novel prediction of the PV system output current based on integration of optimized hyperparameters of multi-layer neural networks and polynomial regression models |
| title_short | A novel prediction of the PV system output current based on integration of optimized hyperparameters of multi-layer neural networks and polynomial regression models |
| title_sort | novel prediction of the pv system output current based on integration of optimized hyperparameters of multi-layer neural networks and polynomial regression models |
| url | http://psasir.upm.edu.my/id/eprint/120530/ http://psasir.upm.edu.my/id/eprint/120530/ http://psasir.upm.edu.my/id/eprint/120530/ http://psasir.upm.edu.my/id/eprint/120530/1/120530.pdf |