Gholamreza Memarzadeh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Gholamreza Memarzadeh has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
Farshid Keynia
3 shared publications- Farshid Keynia
Department of Energy Management and Optimization, Institute of Science and High Technology and Environmental Sciences, Graduate University of Advanced Technology, Kerman, Iran
3 shared publications - Faezeh Amirteimoury
Department of Computer Engineering, Kerman Branch, Islamic Azad University, Kerman, Iran
2 shared publications - Afef Fekih
Department of Electrical and Computer Engineering, University of Louisiana at Lafayette, Lafayette, USA
1 shared publication - Azim Heydari
Department of Astronautics, Electrical and Energetic Engineering (DIAEE) Sapienza University, 00184 Rome, Italy
1 shared publication Elaheh Amirteimoury
1 shared publication
Latest Publications
- 18 October 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 354
MSMCFA-Net: A multi-scale multi-channel feature attention network for enhanced wind speed forecasting in renewable energy systems
- 18 October 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 354
MSMCFA-Net: A multi-scale multi-channel feature attention network for enhanced wind speed forecasting in renewable energy systems
- Open Access
- 23 December 2025
- Published by Elsevier in Results in Engineering
- Vol. 29
Integrated planning and operation of distributed power generators and energy storages for active distribution networks by new ML-based two-level optimization model
- 23 December 2025
- Published by Elsevier in Results in Engineering
- Vol. 29
Open AccessIntegrated planning and operation of distributed power generators and energy storages for active distribution networks by new ML-based two-level optimization model
- Open Access
- 17 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 165173-165188
A Novel Multi-Scale Feature Attention Network-Based Prediction Model for the Accurate Forecasting of Photovoltaic Power Generation
The global rise in energy demand has driven the large-scale integration of photovoltaic (PV) systems into the power grids, increasing the need for accurate forecasting models to manage solar energy variability and uncertainty. This study proposes a novel 24-hour-ahead PV power generation prediction model based on the Multi-Scale Feature Attention Network (MSFAN), which integrates convolutional neural networks (CNNs), attention mechanisms, and gated recurrent units within a non-sequential architecture to enhance prediction accuracy. The model also incorporates a two-step feature selection technique, Mutual Information-Interaction Gain (MI-IG), to extract the most relevant input features whilst minimizing redundancies. The proposed model was validated using real-world PV power generation data from the Arvand power plant in Mahan, Iran. The results indicate that the the model outperformed traditional methods, including LSTM, MLP, and Elman networks. It achieved a mean squared error (MSE) of 0.001, mean absolute error (MAE) of 0.02, mean absolute percentage error (MAPE) of 2.5%, and a coefficient of determination (R²) of 0.991—substantially surpassing the performance of the comparison models. These results underscore the model's potential to improve PV forecasting accuracy and support more stable and efficient power grid operations.
- 17 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 165173-165188
Open AccessA Novel Multi-Scale Feature Attention Network-Based Prediction Model for the Accurate Forecasting of Photovoltaic Power Generation
The global rise in energy demand has driven the large-scale integration of photovoltaic (PV) systems into the power grids, increasing the need for accurate forecasting models to manage solar energy variability and uncertainty. This study proposes a novel 24-hour-ahead PV power generation prediction model based on the Multi-Scale Feature Attention Network (MSFAN), which integrates convolutional neural networks (CNNs), attention mechanisms, and gated recurrent units within a non-sequential architecture to enhance prediction accuracy. The model also incorporates a two-step feature selection technique, Mutual Information-Interaction Gain (MI-IG), to extract the most relevant input features whilst minimizing redundancies. The proposed model was validated using real-world PV power generation data from the Arvand power plant in Mahan, Iran. The results indicate that the the model outperformed traditional methods, including LSTM, MLP, and Elman networks. It achieved a mean squared error (MSE) of 0.001, mean absolute error (MAE) of 0.02, mean absolute percentage error (MAPE) of 2.5%, and a coefficient of determination (R²) of 0.991—substantially surpassing the performance of the comparison models. These results underscore the model's potential to improve PV forecasting accuracy and support more stable and efficient power grid operations.
- Open Access
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Renewable Power Generation
- Vol. 19 (1)
A New Multi Deep Learning Technique With MR‐IG Input Selection Algorithm for Multi‐Step Wind Forecasting
In recent years, the use of renewable energy sources has increased significantly. Among these, wind energy stands out as abundant, cost‐effective, highly efficient in energy conversion, and environmentally sustainable. This study proposes a hybrid approach based on advanced deep learning techniques for multi‐step wind forecasting. The hybrid model integrates enhanced deep learning methods, optimal feature selection techniques, and decomposition transformation models to achieve precise multi‐step wind forecasts. Our proposed method incorporates a sequence of robust techniques, including variational mode decomposition for signal discretization, maximum relevance interaction gain for selecting valuable input features, and a predictive model combining convolutional neural networks, gated recurrent units, and bidirectional long short‐term memory. This integration leverages the strengths of each model while minimizing their limitations, resulting in improved efficiency and accuracy in forecasting. To evaluate the proposed method, wind power generation data from the Pennsylvania–New Jersey–Maryland (PJM) electricity market and wind speed data from the Favignana Island microgrid were analysed. The results of multi‐step wind power forecasting demonstrate the hybrid model's commendable accuracy. For instance, in the PJM electricity market, the average mean absolute percentage error for 2018 ranges from 3.8401% for 1‐h‐ahead forecasting to 13.8123% for 12‐h‐ahead forecasting.
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Renewable Power Generation
- Vol. 19 (1)
Open AccessA New Multi Deep Learning Technique With MR‐IG Input Selection Algorithm for Multi‐Step Wind Forecasting
In recent years, the use of renewable energy sources has increased significantly. Among these, wind energy stands out as abundant, cost‐effective, highly efficient in energy conversion, and environmentally sustainable. This study proposes a hybrid approach based on advanced deep learning techniques for multi‐step wind forecasting. The hybrid model integrates enhanced deep learning methods, optimal feature selection techniques, and decomposition transformation models to achieve precise multi‐step wind forecasts. Our proposed method incorporates a sequence of robust techniques, including variational mode decomposition for signal discretization, maximum relevance interaction gain for selecting valuable input features, and a predictive model combining convolutional neural networks, gated recurrent units, and bidirectional long short‐term memory. This integration leverages the strengths of each model while minimizing their limitations, resulting in improved efficiency and accuracy in forecasting. To evaluate the proposed method, wind power generation data from the Pennsylvania–New Jersey–Maryland (PJM) electricity market and wind speed data from the Favignana Island microgrid were analysed. The results of multi‐step wind power forecasting demonstrate the hybrid model's commendable accuracy. For instance, in the PJM electricity market, the average mean absolute percentage error for 2018 ranges from 3.8401% for 1‐h‐ahead forecasting to 13.8123% for 12‐h‐ahead forecasting.
- Open Access
- 18 September 2023
- Published by Springer Nature in Energy Informatics
- Vol. 6 (1) , 1-18
A new optimal allocation of DGs in distribution networks by using coot bird optimization method
Energy is one of the most important topics in the world today and is considered as one of the most effective factors for the development of countries. Due to the limitation of non-renewable energy sources and undesirable effects of consuming these resources on the environment, the strategy of countries has changed towards the use of renewable energy. Renewable energy sources do not decrease over time and operate independently of price fluctuations and are more available, thus being able to play a greater role in modern power systems. Therefore, the optimal location and use of these resources will have an impact on modifying the parameters of the power grid. In this paper an analytical approach for optimal placement and sizing of distributed generation (DG) in power distribution networks to minimize the power loss, bus voltage limits, DG capacity limits, current limits, and DG penetration limit. In the first step, determines the DG capacity causing maximum benefit at different buses, and then selects the best location for DG placement which corresponds to highest benefit in the buses. This method is applicable for sizing and siting of single as well as multiple DG units. The coot bird optimization method (CBOM) is proposed for solving optimal placement, size, and power factor (PF) of DG in distribution network. The suggested method is tested on the IEEE 33-bus, 69-bus, Distribution Networks. The proposed CBOM method has good performance to find optimal placement, size, and PF of DG and it can be applied for various distribution system.
- 18 September 2023
- Published by Springer Nature in Energy Informatics
- Vol. 6 (1) , 1-18
Open AccessA new optimal allocation of DGs in distribution networks by using coot bird optimization method
Energy is one of the most important topics in the world today and is considered as one of the most effective factors for the development of countries. Due to the limitation of non-renewable energy sources and undesirable effects of consuming these resources on the environment, the strategy of countries has changed towards the use of renewable energy. Renewable energy sources do not decrease over time and operate independently of price fluctuations and are more available, thus being able to play a greater role in modern power systems. Therefore, the optimal location and use of these resources will have an impact on modifying the parameters of the power grid. In this paper an analytical approach for optimal placement and sizing of distributed generation (DG) in power distribution networks to minimize the power loss, bus voltage limits, DG capacity limits, current limits, and DG penetration limit. In the first step, determines the DG capacity causing maximum benefit at different buses, and then selects the best location for DG placement which corresponds to highest benefit in the buses. This method is applicable for sizing and siting of single as well as multiple DG units. The coot bird optimization method (CBOM) is proposed for solving optimal placement, size, and power factor (PF) of DG in distribution network. The suggested method is tested on the IEEE 33-bus, 69-bus, Distribution Networks. The proposed CBOM method has good performance to find optimal placement, size, and PF of DG and it can be applied for various distribution system.
- 7 August 2023
- Published by Elsevier in Journal of Energy Storage
- Vol. 72, 108582
A new hybrid CBSA-GA optimization method and MRMI-LSTM forecasting algorithm for PV-ESS planning in distribution networks
- 7 August 2023
- Published by Elsevier in Journal of Energy Storage
- Vol. 72, 108582
A new hybrid CBSA-GA optimization method and MRMI-LSTM forecasting algorithm for PV-ESS planning in distribution networks
- Open Access
- 27 October 2021
- Published by Institution of Engineering and Technology (IET) in IET Generation, Transmission & Distribution
- Vol. 16 (5) , 851-868
A new financial loss/gain wind power forecasting method based on deep machine learning algorithm by using energy storage system
Nowadays, with the development of the global economy, traditional non‐renewable energy resources can not only meet the increasing energy demand but also bring severe ecological and environmental problems. Wind power, as one of the most economical types of renewable energies source, has become one of the essential resources for clean energy production. Because of the randomness, intermittency, and fluctuation of natural wind, the output power of wind turbines is greatly affected by wind uncertainty. Therefore, wind power generation forecasting and scheduling may be challenging. In this paper, for the successful and accurate presence of wind power producers in the electricity energy market, a method based on forecasting wind power production, the electricity price, and Financial Loss/Gain (FLG) in coordination with energy storage is proposed. To predict the electricity price, wind power production, and FLG for the next 24 h, the hybrid method based on deep learning time series prediction based on the LSTMs method and input selection based on the MRMI method has been used. For this purpose, first, based on historical data, the wind power producer forecasts the electricity price and wind power production for the next 24 h. According to the same predicted values, initial offers are set for participation in the day‐ahead electricity market. After that, wind power producers modify their wind power production based on the FLG prediction method. Since the FLG signal has highly volatile behaviour, therefore it is not efficient to forecast and apply it directly to the proposed wind power production offers. Therefore, classifying FLG by the FCM method and predicting the FLG class labels is much more helpful in improving the proposed bid of wind power producers to the electricity market. Finally, the wind power producer can improve its profit from participating in the electricity market by interacting with the energy storage unit. The presented numerical results demonstrate the efficiency of the proposed method. For example, if the initial offers are modified based on the FLG method, it has caused the expected profit to improve by 4.44–27.69% in the desired months of the year 2018. Also, in three months, the total profit of the wind power producer and energy storage will be higher than if the profit of the wind power producer participates in the day‐ahead market with 100% accuracy.
- 27 October 2021
- Published by Institution of Engineering and Technology (IET) in IET Generation, Transmission & Distribution
- Vol. 16 (5) , 851-868
Open AccessA new financial loss/gain wind power forecasting method based on deep machine learning algorithm by using energy storage system
Nowadays, with the development of the global economy, traditional non‐renewable energy resources can not only meet the increasing energy demand but also bring severe ecological and environmental problems. Wind power, as one of the most economical types of renewable energies source, has become one of the essential resources for clean energy production. Because of the randomness, intermittency, and fluctuation of natural wind, the output power of wind turbines is greatly affected by wind uncertainty. Therefore, wind power generation forecasting and scheduling may be challenging. In this paper, for the successful and accurate presence of wind power producers in the electricity energy market, a method based on forecasting wind power production, the electricity price, and Financial Loss/Gain (FLG) in coordination with energy storage is proposed. To predict the electricity price, wind power production, and FLG for the next 24 h, the hybrid method based on deep learning time series prediction based on the LSTMs method and input selection based on the MRMI method has been used. For this purpose, first, based on historical data, the wind power producer forecasts the electricity price and wind power production for the next 24 h. According to the same predicted values, initial offers are set for participation in the day‐ahead electricity market. After that, wind power producers modify their wind power production based on the FLG prediction method. Since the FLG signal has highly volatile behaviour, therefore it is not efficient to forecast and apply it directly to the proposed wind power production offers. Therefore, classifying FLG by the FCM method and predicting the FLG class labels is much more helpful in improving the proposed bid of wind power producers to the electricity market. Finally, the wind power producer can improve its profit from participating in the electricity market by interacting with the energy storage unit. The presented numerical results demonstrate the efficiency of the proposed method. For example, if the initial offers are modified based on the FLG method, it has caused the expected profit to improve by 4.44–27.69% in the desired months of the year 2018. Also, in three months, the total profit of the wind power producer and energy storage will be higher than if the profit of the wind power producer participates in the day‐ahead market with 100% accuracy.