Mohammad Babaie
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mohammad Babaie has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Kamal Al-Haddad
Department of Ecole de Technologie Superieure, University of Quebec, Montreal, QC, Canada
6 shared publications - Rawad Zgheib
Institut de Recherche dHydro-Qubec (IREQ), Varennes, QC, Canada
2 shared publications - Chunyan Lai
Department of Electrical and Computer Engineering, Concordia University, Montreal, Canada
1 shared publication Pouria Qashqai
Department of Electrical Engineering, cole de Technologie Suprieure (TS), Montreal, QC, Canada
1 shared publication- Pouria Qashqai
Department of Electrical Engineering, cole de Technologie Suprieure (TS), Montreal, Canada
1 shared publication - Pragasen Pillay
Department of Electrical and Computer Engineering, Concordia University, Montreal, QC, Canada
1 shared publication
Latest Publications
- Open Access
- 3 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 172293-172305
Implementation of Deep Reinforcement Learning for Model-Free Switching and Control of a 23-Level Single DC Source Hybrid Packed U-Cell (HPUC) Converter
This paper proposes a novel Deep Reinforcement Learning (DRL) method for controlling a 23-level Single DC Source Hybrid Packed U-Cell (HPUC) converter. The HPUC topology generates a high number of voltage levels with minimal components but presents control challenges due to its numerous switching states and dynamic charging behavior. Unlike conventional control methods, which require accurate models and are sensitive to noise and parameter mismatches, DRL offers a model-free and resilient approach to the non-linear control of such complex systems. A Deep Q-Network (DQN) agent which is inherently model-free and suited for high-dimensional state spaces and discrete action spaces, is employed to address these issues. To validate the proposed method, simulations were conducted in the MATLAB/Simulink environment. The obtained results demonstrated the satisfactory performance of the proposed DRL method, achieving a Total Harmonic Distortion (THD) of 2.71% in the output current under steady-state, maintaining stable capacitor voltage balancing, and exhibiting rapid dynamic response (e.g., settling within approximately 40 ms for current step changes). Furthermore, its resilience was highlighted by its ability to maintain control despite a 25dB SNR noise condition and up to 15% variations in capacitor values.
- 3 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 172293-172305
Open AccessImplementation of Deep Reinforcement Learning for Model-Free Switching and Control of a 23-Level Single DC Source Hybrid Packed U-Cell (HPUC) Converter
This paper proposes a novel Deep Reinforcement Learning (DRL) method for controlling a 23-level Single DC Source Hybrid Packed U-Cell (HPUC) converter. The HPUC topology generates a high number of voltage levels with minimal components but presents control challenges due to its numerous switching states and dynamic charging behavior. Unlike conventional control methods, which require accurate models and are sensitive to noise and parameter mismatches, DRL offers a model-free and resilient approach to the non-linear control of such complex systems. A Deep Q-Network (DQN) agent which is inherently model-free and suited for high-dimensional state spaces and discrete action spaces, is employed to address these issues. To validate the proposed method, simulations were conducted in the MATLAB/Simulink environment. The obtained results demonstrated the satisfactory performance of the proposed DRL method, achieving a Total Harmonic Distortion (THD) of 2.71% in the output current under steady-state, maintaining stable capacitor voltage balancing, and exhibiting rapid dynamic response (e.g., settling within approximately 40 ms for current step changes). Furthermore, its resilience was highlighted by its ability to maintain control despite a 25dB SNR noise condition and up to 15% variations in capacitor values.
- 10 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 72 (9) , 8810-8822
Harmonic Compensation of a Power-Hardware-in-the-Loop Based Emulator for Induction Machines
Power-hardware-in-the-loop (PHIL)-based machine emulator systems use controlled power converters to mimic the behavior of an electric machine. In this article, a PHIL-based machine emulation system is proposed for grid-tied three-phase induction machines (IM). Typically, a switched voltage source inverter (VSI) is employed as an emulator converter in the motor emulation system. However, the VSI introduces various harmonics into the motor emulation system. These harmonics are mainly attributed to dead time, switching components, and control signals. These harmonics deteriorate motor emulation accuracy. Thus, it is important to investigate and compensate for emulator converter harmonics in motor emulation systems. As an important source of these harmonics is dead time, a detailed analysis of the dead time effect on motor emulation will be presented first. Subsequently, a novel artificial neural network (ANN)-based harmonic compensation technique is developed to ensure the mitigation of harmonics in the emulated motor currents. The proposed ANN-based intelligent harmonic compensator leads to the improvement of motor emulation accuracy. Experimental results are obtained from the emulator system and a 5 hp squirrel cage induction motor to validate the proposed emulator with harmonic compensation.
- 10 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 72 (9) , 8810-8822
Harmonic Compensation of a Power-Hardware-in-the-Loop Based Emulator for Induction Machines
Power-hardware-in-the-loop (PHIL)-based machine emulator systems use controlled power converters to mimic the behavior of an electric machine. In this article, a PHIL-based machine emulation system is proposed for grid-tied three-phase induction machines (IM). Typically, a switched voltage source inverter (VSI) is employed as an emulator converter in the motor emulation system. However, the VSI introduces various harmonics into the motor emulation system. These harmonics are mainly attributed to dead time, switching components, and control signals. These harmonics deteriorate motor emulation accuracy. Thus, it is important to investigate and compensate for emulator converter harmonics in motor emulation systems. As an important source of these harmonics is dead time, a detailed analysis of the dead time effect on motor emulation will be presented first. Subsequently, a novel artificial neural network (ANN)-based harmonic compensation technique is developed to ensure the mitigation of harmonics in the emulated motor currents. The proposed ANN-based intelligent harmonic compensator leads to the improvement of motor emulation accuracy. Experimental results are obtained from the emulator system and a 5 hp squirrel cage induction motor to validate the proposed emulator with harmonic compensation.
- Open Access
- 22 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 105394-105409
A Model-Free Switching and Control Method for Three-Level Neutral Point Clamped Converter Using Deep Reinforcement Learning
This paper presents a novel model-free switching and control method for three-level neutral point clamped (NPC) converter using deep reinforcement learning (DRL). In this method, voltage balancing, and selection of optimal switches are achieved using a reward function which is calculated based on various signals measured as observations of the DRL agent. Since the action space is discrete, a deep Q-network (DQN) agent is utilized. DQN is used due to its capability of handling high-dimensional state spaces. In order to highlight its pros and cons, the proposed method is compared with model predictive control (MPC), which is another popular non-linear control method for power electronic converters. The proposed method is evaluated and compared with the MPC method in grid-connected mode using simulations in Matlab/Simulink. To evaluate the practical performance of the DRL method, various experimental results are obtained. The simulation and experimental results demonstrate that the proposed method effectively achieves accurate voltage balancing and ensures steady operation even in the presence of various dynamic changes, including variations in the reference currents and grid voltage. Additionally, the method successfully handles uncertainties, such as sensor measurement noise, and accommodates parameter variations, such as changes in the capacity of the DC-link capacitors and line impedance. The results demonstrate that this method exhibits superior adaptability to real-time changes and uncertainties, delivering more robust performance compared to similar conventional methods like MPC. Thus, this method can be considered a promising approach for intelligent control of power electronic converters, especially when conventional methods such as MPC face challenges in performance and accuracy under severe parameter variations and uncertainties.
- 22 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 105394-105409
Open AccessA Model-Free Switching and Control Method for Three-Level Neutral Point Clamped Converter Using Deep Reinforcement Learning
This paper presents a novel model-free switching and control method for three-level neutral point clamped (NPC) converter using deep reinforcement learning (DRL). In this method, voltage balancing, and selection of optimal switches are achieved using a reward function which is calculated based on various signals measured as observations of the DRL agent. Since the action space is discrete, a deep Q-network (DQN) agent is utilized. DQN is used due to its capability of handling high-dimensional state spaces. In order to highlight its pros and cons, the proposed method is compared with model predictive control (MPC), which is another popular non-linear control method for power electronic converters. The proposed method is evaluated and compared with the MPC method in grid-connected mode using simulations in Matlab/Simulink. To evaluate the practical performance of the DRL method, various experimental results are obtained. The simulation and experimental results demonstrate that the proposed method effectively achieves accurate voltage balancing and ensures steady operation even in the presence of various dynamic changes, including variations in the reference currents and grid voltage. Additionally, the method successfully handles uncertainties, such as sensor measurement noise, and accommodates parameter variations, such as changes in the capacity of the DC-link capacitors and line impedance. The results demonstrate that this method exhibits superior adaptability to real-time changes and uncertainties, delivering more robust performance compared to similar conventional methods like MPC. Thus, this method can be considered a promising approach for intelligent control of power electronic converters, especially when conventional methods such as MPC face challenges in performance and accuracy under severe parameter variations and uncertainties.
- 11 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Electronics
- Vol. 38 (10) , 12482-12496
Self-Training Intelligent Predictive Control for Grid-Tied Transformerless Multilevel Converters
Literature reviews affirm the constructive influence of the intelligent predictive multiobjective control (IPMOC) on the power quality, power ancillary services, efficiency, and reliability expected from grid-tied transformerless multilevel converters. Regarding, this article contributes to developing the IPMOC concept in terms of training, autonomous power management, and real-time harmonic mitigation. In the proposed IPMOC, model predictive control (MPC) adjusts the power, regulates the dc-link capacitors’ voltages, reduces the switching transitions, suppresses CMV, and alleviates harmonics using a novel real-time selective-predictive harmonic mitigation objective. As the intelligent part, two artificial neural networks trained by a novel data-free, fast, self-training strategy reinforce the MPC to handle the multiobjective task. The first one adapts the weighting factors of the MPC dynamically, while the second one as a model-free controller autonomously adjusts the active and reactive power references of the MPC to assure the unity power factor of the grid in the presence of unknown loads. The proposed IPMOC has been applied to a three-phase neutral point clamped converter and evaluated via various test scenarios run by dSPACE 1202 and MATLAB to verify its effectiveness and feasibility.
- 11 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Electronics
- Vol. 38 (10) , 12482-12496
Self-Training Intelligent Predictive Control for Grid-Tied Transformerless Multilevel Converters
Literature reviews affirm the constructive influence of the intelligent predictive multiobjective control (IPMOC) on the power quality, power ancillary services, efficiency, and reliability expected from grid-tied transformerless multilevel converters. Regarding, this article contributes to developing the IPMOC concept in terms of training, autonomous power management, and real-time harmonic mitigation. In the proposed IPMOC, model predictive control (MPC) adjusts the power, regulates the dc-link capacitors’ voltages, reduces the switching transitions, suppresses CMV, and alleviates harmonics using a novel real-time selective-predictive harmonic mitigation objective. As the intelligent part, two artificial neural networks trained by a novel data-free, fast, self-training strategy reinforce the MPC to handle the multiobjective task. The first one adapts the weighting factors of the MPC dynamically, while the second one as a model-free controller autonomously adjusts the active and reactive power references of the MPC to assure the unity power factor of the grid in the presence of unknown loads. The proposed IPMOC has been applied to a three-phase neutral point clamped converter and evaluated via various test scenarios run by dSPACE 1202 and MATLAB to verify its effectiveness and feasibility.
- 21 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. 59 (1) , 554-566
Boost Packed E-Cell: A Compact Multilevel Converter for Power Quality Ancillary Services
This paper proposes Boost Packed E-Cell (BPEC) as an affordable Compact Multilevel Converter (CMLC) for the power quality ancillary services. The BPEC is a transformerless bidirectional CMLC topology and can generate symmetrical and asymmetrical multilevel voltage waveforms with 5-to-11-level resolution using only three low-voltage dc capacitors and eight power switches. Thanks to the serial expansion of the two dc capacitors, BPEC has two dc-links, which means two voltage sensors are enough to control three dc capacitors. Despite other CMLCs, BPEC does not need a fault detector and inherently generates a symmetrical 5-level or an asymmetrical 7-level voltage waveform in the event of a fault of the middle switches or their gate drivers. As a case study, a single-phase Compact Active Power Filter (CAPF) is designed in this paper based on the BPEC to compensate for harmonics and reactive power caused by unknown non/linear loads, simultaneously. Finite control set predictive control strategy is also adopted based on the switched model of the power system containing the grid, unknown non/linear loads, and the BPEC to address the grid power quality concerns. The experiments performed by a prototype including the BPEC power board, MicroLabBox, OPAL-RT OP8662, and Chroma 61086 verify the merits of the proposed CAPF in practice.
- 21 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. 59 (1) , 554-566
Boost Packed E-Cell: A Compact Multilevel Converter for Power Quality Ancillary Services
This paper proposes Boost Packed E-Cell (BPEC) as an affordable Compact Multilevel Converter (CMLC) for the power quality ancillary services. The BPEC is a transformerless bidirectional CMLC topology and can generate symmetrical and asymmetrical multilevel voltage waveforms with 5-to-11-level resolution using only three low-voltage dc capacitors and eight power switches. Thanks to the serial expansion of the two dc capacitors, BPEC has two dc-links, which means two voltage sensors are enough to control three dc capacitors. Despite other CMLCs, BPEC does not need a fault detector and inherently generates a symmetrical 5-level or an asymmetrical 7-level voltage waveform in the event of a fault of the middle switches or their gate drivers. As a case study, a single-phase Compact Active Power Filter (CAPF) is designed in this paper based on the BPEC to compensate for harmonics and reactive power caused by unknown non/linear loads, simultaneously. Finite control set predictive control strategy is also adopted based on the switched model of the power system containing the grid, unknown non/linear loads, and the BPEC to address the grid power quality concerns. The experiments performed by a prototype including the BPEC power board, MicroLabBox, OPAL-RT OP8662, and Chroma 61086 verify the merits of the proposed CAPF in practice.
- 5 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Single-Phase Compact Active Rectifier with 31-Level Voltage Resolution using Modified Packed U-Cell Topology and Model Predictive Control
Regarding the increasing penetration of renewable energy sources and dc loads into grids, improving the harmonic performance of the converters has become a substantial power electronic concern during the last two decades. As a promising accomplishment, this paper introduces a new compact multilevel active rectifier with a31-1eve1vo1tage resolution on the grid side to address the power quality concerns. The proposed high-resolution Compact Active Rectifier (CAR) is configured based on modified packed U-cell topology and is able to supply four independent dc loads with different voltages. Concerning the variable structure behavior of the CAR, a Model Predictive Controller (MPC) is also considered to track the desired objectives. The implementation results under various dynamic test conditions confirm that the MPC-based CAR remarkably improves the power quality in both ac and dc sides of the converter while using a second-order filter is no longer required.
- 5 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Single-Phase Compact Active Rectifier with 31-Level Voltage Resolution using Modified Packed U-Cell Topology and Model Predictive Control
Regarding the increasing penetration of renewable energy sources and dc loads into grids, improving the harmonic performance of the converters has become a substantial power electronic concern during the last two decades. As a promising accomplishment, this paper introduces a new compact multilevel active rectifier with a31-1eve1vo1tage resolution on the grid side to address the power quality concerns. The proposed high-resolution Compact Active Rectifier (CAR) is configured based on modified packed U-cell topology and is able to supply four independent dc loads with different voltages. Concerning the variable structure behavior of the CAR, a Model Predictive Controller (MPC) is also considered to track the desired objectives. The implementation results under various dynamic test conditions confirm that the MPC-based CAR remarkably improves the power quality in both ac and dc sides of the converter while using a second-order filter is no longer required.
- 10 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Boost Packed E-Cell: A Compact Multilevel Converter for Power Quality Ancillary Services
Beyond question, replacing conventional two-level power converters by their bidirectional multilevel rivals improves Flexible AC Transmission Systems (FACTS) and Active Power Filters (APF) in terms of efficiency, power quality and switching losses. Regarding the constructive impact of multilevel converters on the performance of FACTSs and APFs, this paper proposes Boost Packed E-Cell (BPEC) as an affordable and reliable compact multilevel converter for the power ancillary services. BPEC is able to generate a voltage waveform with either 9 or 11 levels using three dc capacitors and eight semiconductor switches. The boost operation empowers BPEC to dominate the grid voltage using low power dc-links. Horizontal expansion of the capacitors in BPEC reduces the dc voltage measurements and remarkably enhances the converter reliability. For the case study, BPEC is investigated in the form of a single-phase Compact Active Power Filter (CAPF) when reactive/nonlinear loads are connected to grid. Finite Control Set Model Predictive Control (FCSMPC) is also dedicated to assure the desired performance of BPEC in the CAPC application. The validation tests performed by dSPACE and MATLAB prove successful active damping of the load current harmonics at the point of common coupling.
- 10 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Boost Packed E-Cell: A Compact Multilevel Converter for Power Quality Ancillary Services
Beyond question, replacing conventional two-level power converters by their bidirectional multilevel rivals improves Flexible AC Transmission Systems (FACTS) and Active Power Filters (APF) in terms of efficiency, power quality and switching losses. Regarding the constructive impact of multilevel converters on the performance of FACTSs and APFs, this paper proposes Boost Packed E-Cell (BPEC) as an affordable and reliable compact multilevel converter for the power ancillary services. BPEC is able to generate a voltage waveform with either 9 or 11 levels using three dc capacitors and eight semiconductor switches. The boost operation empowers BPEC to dominate the grid voltage using low power dc-links. Horizontal expansion of the capacitors in BPEC reduces the dc voltage measurements and remarkably enhances the converter reliability. For the case study, BPEC is investigated in the form of a single-phase Compact Active Power Filter (CAPF) when reactive/nonlinear loads are connected to grid. Finite Control Set Model Predictive Control (FCSMPC) is also dedicated to assure the desired performance of BPEC in the CAPC application. The validation tests performed by dSPACE and MATLAB prove successful active damping of the load current harmonics at the point of common coupling.