Fahad M. Almasoudi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Fahad M. Almasoudi has a total of 52 co-authors. Here are the top co-authors by number of shared publications:
- Khaled Saleem S. Alatawi
Electrical Engineering Department, Faculty of Engineering, University of Tabuk, Tabuk 47913, Saudi Arabia
6 shared publications - Muhammad Shoaib Bhutta
School of Automobile Engineering, Guilin University of Aerospace Technology, Guilin, China
5 shared publications - Ibrahim Alsaidan
Department of Electrical Engineering, College of Engineering, Qassim University, Buraydah, Saudi Arabia
3 shared publications Khaled Saleem S. Alatawi
3 shared publications- Abualkasim Bakeer
Department of Electrical Engineering, Faculty of Engineering, Aswan University, Aswan 81542, Egypt
2 shared publications - Mohammad Rashed Altimania
Department of Electrical Engineering University of Tabuk Tabuk Saudi Arabia
2 shared publications
Latest Publications
- Open Access
- 21 September 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (18) , 9677
SFOA-Optimized Fractional-Order Super-Twisting Sliding Mode Control for Sustainable Operation of a Wind–PV–ESS Microgrid Supplying a Fast EV Charging Station
Renewable-powered electric vehicle charging can support sustainable transport electrification by coupling low-carbon electricity generation with charging demand. Autonomous microgrids (MGs) combining wind, solar, and energy storage offer a pathway to this integration, including at locations with limited grid access. However, it can be challenging to monitor and manage the energy of standalone microgrids because they are time-varying and nonlinear. Solar and wind energy were the main sources of power for the microgrid. A microgrid’s primary load is thought to be an electric vehicle charging station (EVCS). The EVCS can charge quickly and uses a lot of power. Additionally, an energy storage system (ESS) is incorporated into the microgrid. This research evaluates a fractional-order-super-twisting sliding mode controller (FOSTSMC) for DC-bus regulation and ESS-assisted power balancing to support reliable renewable-powered fast EV charging. The FOSTSMC scheme includes three key parameters that are optimally tuned using the starfish optimization algorithm (SFOA). Regarding changes in wind velocity and solar irradiance, the response of the FOSTSMC was contrasted to that of a conventional proportional-integral (PI), super-twisting sliding mode controller (STSMC), and the fractional-order-PI (FOPI) regulators. MATLAB/Simulink (R2023a version 9.14) was used to simulate and model the MG. The findings show that the introduced FOSTSMC enhanced the MG’s transient response when compared to the other controllers. The proposed optimal FOSTSMC provides an improvement in the peak overshoot of 41.8% and 47.6% in the settling times over the best values of the other controllers. Moreover, simulation-based evaluation using NASA POWER weather profiles for solar irradiance and wind speed are applied to the proposed system to validate energy management effectiveness. Despite changes in wind velocity, solar intensity, and other parameters, the EVCS charging process and the DC-bus voltage tracked the set point with the least amount of disruption. To prove the effectiveness of SFOA, it is compared to particle swarm optimization (PSO).
- 21 September 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (18) , 9677
Open AccessSFOA-Optimized Fractional-Order Super-Twisting Sliding Mode Control for Sustainable Operation of a Wind–PV–ESS Microgrid Supplying a Fast EV Charging Station
Renewable-powered electric vehicle charging can support sustainable transport electrification by coupling low-carbon electricity generation with charging demand. Autonomous microgrids (MGs) combining wind, solar, and energy storage offer a pathway to this integration, including at locations with limited grid access. However, it can be challenging to monitor and manage the energy of standalone microgrids because they are time-varying and nonlinear. Solar and wind energy were the main sources of power for the microgrid. A microgrid’s primary load is thought to be an electric vehicle charging station (EVCS). The EVCS can charge quickly and uses a lot of power. Additionally, an energy storage system (ESS) is incorporated into the microgrid. This research evaluates a fractional-order-super-twisting sliding mode controller (FOSTSMC) for DC-bus regulation and ESS-assisted power balancing to support reliable renewable-powered fast EV charging. The FOSTSMC scheme includes three key parameters that are optimally tuned using the starfish optimization algorithm (SFOA). Regarding changes in wind velocity and solar irradiance, the response of the FOSTSMC was contrasted to that of a conventional proportional-integral (PI), super-twisting sliding mode controller (STSMC), and the fractional-order-PI (FOPI) regulators. MATLAB/Simulink (R2023a version 9.14) was used to simulate and model the MG. The findings show that the introduced FOSTSMC enhanced the MG’s transient response when compared to the other controllers. The proposed optimal FOSTSMC provides an improvement in the peak overshoot of 41.8% and 47.6% in the settling times over the best values of the other controllers. Moreover, simulation-based evaluation using NASA POWER weather profiles for solar irradiance and wind speed are applied to the proposed system to validate energy management effectiveness. Despite changes in wind velocity, solar intensity, and other parameters, the EVCS charging process and the DC-bus voltage tracked the set point with the least amount of disruption. To prove the effectiveness of SFOA, it is compared to particle swarm optimization (PSO).
- Open Access
- 18 September 2026
- Published by Elsevier in SSRN Electronic Journal
Battery-to-Grid Impedance Propagation and Weak-Grid Stability of Two-Stage Battery Energy Storage Systems
Battery impedance varies with state of charge, temperature, and aging, but the extent to which these variations propagate through the power-conversion stages of a grid-connected battery energy storage system remains unclear. This study develops a battery-to-grid impedance framework for a 10-kW two-stage battery energy storage system comprising a second-order battery equivalent circuit, bidirectional DC/DC converter, regulated DC link, grid-following converter, phase-locked loop, LCL filter, and weak-grid equivalent. The simulation-based framework combines nonlinear averaged modeling, explicit DC-link-normalized modulation, frequency-domain dq-impedance identification, eigenvalue tracking, generalized-Nyquist analysis, and AC-side switching-model verification. Across the investigated parametric battery conditions, the resistance multiplier ranges from 0.8075 to 6.12. From the nominal to the extreme condition, the battery operating point changes from 393.79 V and 25.95 A to 293.90 V and 34.82 A, while the DC-link voltage remains close to 700 V. Ideal averaged voltage actuation suppresses the first-order DC-to-AC coupling pathway, whereas explicit modulation restores measurable battery-to-grid propagation. With a 100-μs measurement and feedforward lag, the nominal-to-extreme true-PCC dq-impedance change is 1.3187% at 20 Hz but only 0.00348% at 392 Hz. The corresponding critical short-circuit-ratio change is approximately 0.010%, compared with a 0.418% envelope produced by varying the lag from 50 to 200 μs. Generalized-Nyquist analysis confirms the stability boundary near an SCR of 4.288 and a frequency of 390.43 Hz. The averaged and switching converter models differ by 2.10% near the critical frequency. The results show that battery impedance remains relevant to low-frequency terminal behavior, whereas the investigated high-frequency weak-grid mode is governed primarily by converter, control, filter, and grid dynamics.
- 18 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessBattery-to-Grid Impedance Propagation and Weak-Grid Stability of Two-Stage Battery Energy Storage Systems
Battery impedance varies with state of charge, temperature, and aging, but the extent to which these variations propagate through the power-conversion stages of a grid-connected battery energy storage system remains unclear. This study develops a battery-to-grid impedance framework for a 10-kW two-stage battery energy storage system comprising a second-order battery equivalent circuit, bidirectional DC/DC converter, regulated DC link, grid-following converter, phase-locked loop, LCL filter, and weak-grid equivalent. The simulation-based framework combines nonlinear averaged modeling, explicit DC-link-normalized modulation, frequency-domain dq-impedance identification, eigenvalue tracking, generalized-Nyquist analysis, and AC-side switching-model verification. Across the investigated parametric battery conditions, the resistance multiplier ranges from 0.8075 to 6.12. From the nominal to the extreme condition, the battery operating point changes from 393.79 V and 25.95 A to 293.90 V and 34.82 A, while the DC-link voltage remains close to 700 V. Ideal averaged voltage actuation suppresses the first-order DC-to-AC coupling pathway, whereas explicit modulation restores measurable battery-to-grid propagation. With a 100-μs measurement and feedforward lag, the nominal-to-extreme true-PCC dq-impedance change is 1.3187% at 20 Hz but only 0.00348% at 392 Hz. The corresponding critical short-circuit-ratio change is approximately 0.010%, compared with a 0.418% envelope produced by varying the lag from 50 to 200 μs. Generalized-Nyquist analysis confirms the stability boundary near an SCR of 4.288 and a frequency of 390.43 Hz. The averaged and switching converter models differ by 2.10% near the critical frequency. The results show that battery impedance remains relevant to low-frequency terminal behavior, whereas the investigated high-frequency weak-grid mode is governed primarily by converter, control, filter, and grid dynamics.
- Open Access
- 29 May 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
A LION-optimized GAN for multi-target battery state prediction in battery management system
Accurately predicting battery target variables is essential for reliable battery management, but the nonlinear and time-varying nature of batteries makes this task difficult. This study introduces GAN-LION, a conditional adversarial regression framework designed for multi-target battery prediction using historical operating sequences. Unlike traditional noise-driven GANs, the proposed model formulates prediction as a deterministic sequence-to-one regression task, where the generator predicts the next target value from a lookback window and the discriminator judges whether the input-target pair aligns with the real data distribution. To specifically examine the impact of optimization, the same adversarial architecture is trained with either the Lion or Adam optimizer and is also compared with CNN-LSTM-GRU and Autoencoder-LSTM baselines. A single end-to-end pipeline is used for preprocessing, normalization, temporal sequence construction, and chronological train-validation-test splitting to avoid information leakage. Results from two benchmark battery datasets indicate that GAN-LION achieves the strongest overall performance. Its advantage is most evident on the more challenging dataset, where it yields lower prediction errors, smoother convergence, and more stable gradient behavior. On the simpler dataset, the performance differences are less pronounced, but GAN-LION still remains competitive and stable. Overall, these results suggest that conditional adversarial regression with Lion-based optimization is an effective and technically sound method for battery target prediction.
- 29 May 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessA LION-optimized GAN for multi-target battery state prediction in battery management system
Accurately predicting battery target variables is essential for reliable battery management, but the nonlinear and time-varying nature of batteries makes this task difficult. This study introduces GAN-LION, a conditional adversarial regression framework designed for multi-target battery prediction using historical operating sequences. Unlike traditional noise-driven GANs, the proposed model formulates prediction as a deterministic sequence-to-one regression task, where the generator predicts the next target value from a lookback window and the discriminator judges whether the input-target pair aligns with the real data distribution. To specifically examine the impact of optimization, the same adversarial architecture is trained with either the Lion or Adam optimizer and is also compared with CNN-LSTM-GRU and Autoencoder-LSTM baselines. A single end-to-end pipeline is used for preprocessing, normalization, temporal sequence construction, and chronological train-validation-test splitting to avoid information leakage. Results from two benchmark battery datasets indicate that GAN-LION achieves the strongest overall performance. Its advantage is most evident on the more challenging dataset, where it yields lower prediction errors, smoother convergence, and more stable gradient behavior. On the simpler dataset, the performance differences are less pronounced, but GAN-LION still remains competitive and stable. Overall, these results suggest that conditional adversarial regression with Lion-based optimization is an effective and technically sound method for battery target prediction.
- Open Access
- 3 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 53116-53144
Glow Plug Integrated Solar Heater for Reducing Initial Waiting Period of Evaporation Lag and Improve Thermal Efficiency in Solar Still Desalination
The current solar desalination process is facing a challenge of longer time for the brine temperature to reach the evaporation threshold during the winter with cooler ambient temperature, cloudy, and the initial hours of the day. This study aims to address the challenge by reducing initial waiting period of evaporation lag through integrating a glow plug enabled solar powered water heater (SPWH), operates at low resistance (0.48 – 0.81 Ω) and high power (12 V, 25 A, 300 W). Prior to implementation, mathematical modelling is employed to determine the appropriate sizing of the PV system, battery, cable, and maximum power point tracking (MPPT) controller. The results demonstrate a significant increase in the temperature of the brine, reaching 79.2°C within 45 minutes at a rate of 0.96°C/min. The temperature profile demonstrates that the brine water, reaching a steady peak with minimal fluctuations of ± 2°C, retains heat more effectively than the chamber temperature due to its higher specific heat capacity. Throughout the experiment, the average brine temperature is maintained at 70.58°C, even on a day with heavy cloud cover (average irradiance 418 W/m2). Another noteworthy finding is that the system can produce more than 3.35 kg/m2 of freshwater per day with the highest thermal efficiency of 68.18% under cloudy ambient conditions. The electrical performance of the system proves to be highly stable, with the voltages of both the PV system and battery experiencing minimal fluctuations not more than 0.9%. In addition, the system has achieved a cost-effective production rate of $0.09/kg. By employing this technique, challenges related to limited access to clean drinking water, scarcity of freshwater sources, and water quality issues in remote Malaysian islands can be effectively overcome.
- 3 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 53116-53144
Open AccessGlow Plug Integrated Solar Heater for Reducing Initial Waiting Period of Evaporation Lag and Improve Thermal Efficiency in Solar Still Desalination
The current solar desalination process is facing a challenge of longer time for the brine temperature to reach the evaporation threshold during the winter with cooler ambient temperature, cloudy, and the initial hours of the day. This study aims to address the challenge by reducing initial waiting period of evaporation lag through integrating a glow plug enabled solar powered water heater (SPWH), operates at low resistance (0.48 – 0.81 Ω) and high power (12 V, 25 A, 300 W). Prior to implementation, mathematical modelling is employed to determine the appropriate sizing of the PV system, battery, cable, and maximum power point tracking (MPPT) controller. The results demonstrate a significant increase in the temperature of the brine, reaching 79.2°C within 45 minutes at a rate of 0.96°C/min. The temperature profile demonstrates that the brine water, reaching a steady peak with minimal fluctuations of ± 2°C, retains heat more effectively than the chamber temperature due to its higher specific heat capacity. Throughout the experiment, the average brine temperature is maintained at 70.58°C, even on a day with heavy cloud cover (average irradiance 418 W/m2). Another noteworthy finding is that the system can produce more than 3.35 kg/m2 of freshwater per day with the highest thermal efficiency of 68.18% under cloudy ambient conditions. The electrical performance of the system proves to be highly stable, with the voltages of both the PV system and battery experiencing minimal fluctuations not more than 0.9%. In addition, the system has achieved a cost-effective production rate of $0.09/kg. By employing this technique, challenges related to limited access to clean drinking water, scarcity of freshwater sources, and water quality issues in remote Malaysian islands can be effectively overcome.
- 13 November 2025
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 51 (1) , 273-286
Continuous Smooth Adaptive Barrier Function-Based Sliding Mode Controller for Hybrid Energy Storage System of Electric Vehicle
- 13 November 2025
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 51 (1) , 273-286
Continuous Smooth Adaptive Barrier Function-Based Sliding Mode Controller for Hybrid Energy Storage System of Electric Vehicle
- Open Access
- 24 July 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-25
Optimizing solar power efficiency in smart grids using hybrid machine learning models for accurate energy generation prediction
The fourth energy revolution is characterized by the incorporation of renewable energy supplies into intelligent networks. As the world is shifting towards cleaner energy sources, there is a need for efficient and reliable methods to predict the output of renewable energy plants. Hybrid machine learning modified models are emerging as a promising solution for energy generation prediction. Renewable energy generation plants, such as solar, biogas, hydropower plants, wind farms, etc. are becoming increasingly popular due to their environmental benefits. However, their output can be highly variable and dependent on weather conditions, making integrating them into the existing energy grid challenging. Smart grids with artificial intelligent systems have the potential to solve this challenge by using real-time data to optimize energy production and distribution. Although by incorporating sensors, analytics, and automation, these grids can manage energy demand and supply more efficiently, reducing carbon emissions, increase energy security, and improve access to electricity in remote areas. However, this research aims to enhance the efficiency of solar power generation systems in a smart grid context using machine learning hybrid models such as Hybrid Convolutional-Recurrence Net (HCRN), Hybrid Convolutional-LSTM Net (HCLN), and Hybrid Convolutional-GRU Net (HCGRN). For this purpose, this study considers various parameters of a solar plant such as power production (MWh), irradiance or plane of array (POA), and performance ratio (PR). The HCLN model demonstrates superior accuracy with the RMSE values of 0.012027 for MWh, 0.013734 for POA and 0.003055 for PR, along with the lowest MAE values of 0.069523 for MWh, 0.082813 for POA, and 0.042815 for PR. The obtained results suggest that the proposed machine learning models can effectively enhance the efficiency of solar power generation systems by accurately predicting the required measurements.
- 24 July 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-25
Open AccessOptimizing solar power efficiency in smart grids using hybrid machine learning models for accurate energy generation prediction
The fourth energy revolution is characterized by the incorporation of renewable energy supplies into intelligent networks. As the world is shifting towards cleaner energy sources, there is a need for efficient and reliable methods to predict the output of renewable energy plants. Hybrid machine learning modified models are emerging as a promising solution for energy generation prediction. Renewable energy generation plants, such as solar, biogas, hydropower plants, wind farms, etc. are becoming increasingly popular due to their environmental benefits. However, their output can be highly variable and dependent on weather conditions, making integrating them into the existing energy grid challenging. Smart grids with artificial intelligent systems have the potential to solve this challenge by using real-time data to optimize energy production and distribution. Although by incorporating sensors, analytics, and automation, these grids can manage energy demand and supply more efficiently, reducing carbon emissions, increase energy security, and improve access to electricity in remote areas. However, this research aims to enhance the efficiency of solar power generation systems in a smart grid context using machine learning hybrid models such as Hybrid Convolutional-Recurrence Net (HCRN), Hybrid Convolutional-LSTM Net (HCLN), and Hybrid Convolutional-GRU Net (HCGRN). For this purpose, this study considers various parameters of a solar plant such as power production (MWh), irradiance or plane of array (POA), and performance ratio (PR). The HCLN model demonstrates superior accuracy with the RMSE values of 0.012027 for MWh, 0.013734 for POA and 0.003055 for PR, along with the lowest MAE values of 0.069523 for MWh, 0.082813 for POA, and 0.042815 for PR. The obtained results suggest that the proposed machine learning models can effectively enhance the efficiency of solar power generation systems by accurately predicting the required measurements.
- Top Cited PapersOpen Access
A Comprehensive Review of Microgrid Energy Management Strategies Considering Electric Vehicles, Energy Storage Systems, and AI Techniques
The relentlessly depleting fossil-fuel-based energy resources worldwide have forbidden an imminent energy crisis that could severely impact the general population. This dire situation calls for the immediate exploitation of renewable energy resources to redress the balance between power consumption and generation. This manuscript confers about energy management tactics to optimize the methods of power production and consumption. Furthermore, this paper also discusses the solutions to enhance the reliability of the electrical power system. In order to elucidate the enhanced reliability of the electrical system, microgrids consisting of different energy resources, load types, and optimization techniques are comprehensively analyzed to explore the significance of energy management systems (EMSs) and demand response strategies. Subsequently, this paper discusses the role of EMS for the proper consumption of electrical power considering the advent of electric vehicles (EVs) in the energy market. The main reason to integrate EVs is the growing hazards of climate change due to carbon emissions. Moreover, this paper sheds light on the growing importance of artificial intelligence (AI) in the technological realm and its incorporation into electrical systems with the notion of strengthening existing smart grid technologies and to handle the uncertainties in load management. This paper also delineates the different methodologies to effectively mitigate the probability of facing cyber-attacks and to make the smart grids invulnerable.
Top Cited PapersOpen AccessA Comprehensive Review of Microgrid Energy Management Strategies Considering Electric Vehicles, Energy Storage Systems, and AI Techniques
The relentlessly depleting fossil-fuel-based energy resources worldwide have forbidden an imminent energy crisis that could severely impact the general population. This dire situation calls for the immediate exploitation of renewable energy resources to redress the balance between power consumption and generation. This manuscript confers about energy management tactics to optimize the methods of power production and consumption. Furthermore, this paper also discusses the solutions to enhance the reliability of the electrical power system. In order to elucidate the enhanced reliability of the electrical system, microgrids consisting of different energy resources, load types, and optimization techniques are comprehensively analyzed to explore the significance of energy management systems (EMSs) and demand response strategies. Subsequently, this paper discusses the role of EMS for the proper consumption of electrical power considering the advent of electric vehicles (EVs) in the energy market. The main reason to integrate EVs is the growing hazards of climate change due to carbon emissions. Moreover, this paper sheds light on the growing importance of artificial intelligence (AI) in the technological realm and its incorporation into electrical systems with the notion of strengthening existing smart grid technologies and to handle the uncertainties in load management. This paper also delineates the different methodologies to effectively mitigate the probability of facing cyber-attacks and to make the smart grids invulnerable.
- Open Access
Neuro-Fuzzy Based High-Voltage DC Model to Optimize Frequency Stability of an Offshore Wind Farm
Lack of synchronization between high voltage DC systems linking offshore wind farms and the onshore grid is a natural consequence owing to the stochastic nature of wind energy. The poor synchronization results in increased system disturbances, grid contingencies, power loss, and frequency instability. Emphasizing frequency stability analysis, this research investigates a dynamic coordination control technique for a Double Fed Induction Generator (DFIG) consisting of OWFs integrated with a hybrid multi-terminal HVDC (MTDC) system. Line commutated converters (LCC) and voltage source converters (VSC) are used in the suggested control method in order to ensure frequency stability. The adaptive neuro-fuzzy inference approach is used to accurately predict wind speed in order to further improve frequency stability. The proposed HVDC system can integrate multiple distributed OWFs with the onshore grid system, and the control strategy is designed based on this concept. In order to ensure the transient stability of the HVDC system, the DFIG-based OWF is regulated by a rotor side controller (RSC) and a grid side controller (GSC) at the grid side using a STATCOM. The devised HVDC (MTDC) is simulated in MATLAB/SIMULINK, and the performance is evaluated in terms of different parameters, such as frequency, wind power, rotor and stator side current, torque, speed, and power. Experimental results are compared to a conventional optimal power flow (OPF) model to validate the performance.
Open AccessNeuro-Fuzzy Based High-Voltage DC Model to Optimize Frequency Stability of an Offshore Wind Farm
Lack of synchronization between high voltage DC systems linking offshore wind farms and the onshore grid is a natural consequence owing to the stochastic nature of wind energy. The poor synchronization results in increased system disturbances, grid contingencies, power loss, and frequency instability. Emphasizing frequency stability analysis, this research investigates a dynamic coordination control technique for a Double Fed Induction Generator (DFIG) consisting of OWFs integrated with a hybrid multi-terminal HVDC (MTDC) system. Line commutated converters (LCC) and voltage source converters (VSC) are used in the suggested control method in order to ensure frequency stability. The adaptive neuro-fuzzy inference approach is used to accurately predict wind speed in order to further improve frequency stability. The proposed HVDC system can integrate multiple distributed OWFs with the onshore grid system, and the control strategy is designed based on this concept. In order to ensure the transient stability of the HVDC system, the DFIG-based OWF is regulated by a rotor side controller (RSC) and a grid side controller (GSC) at the grid side using a STATCOM. The devised HVDC (MTDC) is simulated in MATLAB/SIMULINK, and the performance is evaluated in terms of different parameters, such as frequency, wind power, rotor and stator side current, torque, speed, and power. Experimental results are compared to a conventional optimal power flow (OPF) model to validate the performance.
- Open Access
- 27 May 2023
- Published by MDPI AG in Fractal and Fractional
- Vol. 7 (6) , 435
A New Load Frequency Control Technique for Hybrid Maritime Microgrids: Sophisticated Structure of Fractional-Order PIDA Controller
This paper proposes an efficient load frequency control (LFC) technique based on a fractional-order proportional–integral–derivative–accelerator with a low-pass filter compensator (FOPIDA-LPF) controller, which can also be accurately referred to as the PIλDND2N2 controller. A trustworthy metaheuristic optimization algorithm, known as the gray wolf optimizer (GWO), is used to fine-tune the suggested PIλDND2N2 controller parameters. Moreover, the proposed PIλDND2N2 controller is designed for the LFC of a self-contained hybrid maritime microgrid system (HMμGS) containing solid oxide fuel cell energy units, a marine biodiesel generator, renewable energy sources (RESs), non-sensitive loads, and sensitive loads. The proposed controller enables the power system to deal with random variations in load and intermittent renewable energy sources. Comparisons with various controllers used in the literature demonstrate the excellence of the proposed PIλDND2N2 controller. Additionally, the proficiency of GWO optimization is checked against other powerful optimization techniques that have been extensively researched: particle swarm optimization and ant lion optimization. Finally, the simulation results performed by the MATLAB software prove the effectiveness and reliability of the suggested PIλDND2N2 controller built on the GWO under several contingencies of different load perturbations and random generation of RESs. The proposed controller can maintain stability within the system, while also greatly decreasing overshooting and minimizing the system’s settling time and rise time.
- 27 May 2023
- Published by MDPI AG in Fractal and Fractional
- Vol. 7 (6) , 435
Open AccessA New Load Frequency Control Technique for Hybrid Maritime Microgrids: Sophisticated Structure of Fractional-Order PIDA Controller
This paper proposes an efficient load frequency control (LFC) technique based on a fractional-order proportional–integral–derivative–accelerator with a low-pass filter compensator (FOPIDA-LPF) controller, which can also be accurately referred to as the PIλDND2N2 controller. A trustworthy metaheuristic optimization algorithm, known as the gray wolf optimizer (GWO), is used to fine-tune the suggested PIλDND2N2 controller parameters. Moreover, the proposed PIλDND2N2 controller is designed for the LFC of a self-contained hybrid maritime microgrid system (HMμGS) containing solid oxide fuel cell energy units, a marine biodiesel generator, renewable energy sources (RESs), non-sensitive loads, and sensitive loads. The proposed controller enables the power system to deal with random variations in load and intermittent renewable energy sources. Comparisons with various controllers used in the literature demonstrate the excellence of the proposed PIλDND2N2 controller. Additionally, the proficiency of GWO optimization is checked against other powerful optimization techniques that have been extensively researched: particle swarm optimization and ant lion optimization. Finally, the simulation results performed by the MATLAB software prove the effectiveness and reliability of the suggested PIλDND2N2 controller built on the GWO under several contingencies of different load perturbations and random generation of RESs. The proposed controller can maintain stability within the system, while also greatly decreasing overshooting and minimizing the system’s settling time and rise time.
- Open Access
- 25 May 2023
- Published by MDPI AG in Sustainability
- Vol. 15 (11) , 8555
Evaluation of Machine Learning Models for Smart Grid Parameters: Performance Analysis of ARIMA and Bi-LSTM
The integration of renewable energy resources into smart grids has become increasingly important to address the challenges of managing and forecasting energy production in the fourth energy revolution. To this end, artificial intelligence (AI) has emerged as a powerful tool for improving energy production control and management. This study investigates the application of machine learning techniques, specifically ARIMA (auto-regressive integrated moving average) and Bi-LSTM (bidirectional long short-term memory) models, for predicting solar power production for the next year. Using one year of real-time solar power production data, this study trains and tests these models on performance measures such as mean absolute error (MAE) and root mean squared error (RMSE). The results demonstrate that the Bi-LSTM (bidirectional long short-term memory) model outperforms the ARIMA (auto-regressive integrated moving average) model in terms of accuracy and is able to successfully identify intricate patterns and long-term relationships in the real-time-series data. The findings suggest that machine learning techniques can optimize the integration of renewable energy resources into smart grids, leading to more efficient and sustainable power systems.
- 25 May 2023
- Published by MDPI AG in Sustainability
- Vol. 15 (11) , 8555
Open AccessEvaluation of Machine Learning Models for Smart Grid Parameters: Performance Analysis of ARIMA and Bi-LSTM
The integration of renewable energy resources into smart grids has become increasingly important to address the challenges of managing and forecasting energy production in the fourth energy revolution. To this end, artificial intelligence (AI) has emerged as a powerful tool for improving energy production control and management. This study investigates the application of machine learning techniques, specifically ARIMA (auto-regressive integrated moving average) and Bi-LSTM (bidirectional long short-term memory) models, for predicting solar power production for the next year. Using one year of real-time solar power production data, this study trains and tests these models on performance measures such as mean absolute error (MAE) and root mean squared error (RMSE). The results demonstrate that the Bi-LSTM (bidirectional long short-term memory) model outperforms the ARIMA (auto-regressive integrated moving average) model in terms of accuracy and is able to successfully identify intricate patterns and long-term relationships in the real-time-series data. The findings suggest that machine learning techniques can optimize the integration of renewable energy resources into smart grids, leading to more efficient and sustainable power systems.