Nafiseh Mazaheri Tehrani
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
Nafiseh Mazaheri Tehrani has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Ahmadreza Vali
Department of Electrical and Computer Engineering, Malek Ashter University of Technology, Tehran, Iran
1 shared publication - Daniel Pizarro
Department of Electronics, Universidad de Alcalá, Alcalá de Henares, Spain
1 shared publication - Daniel Santamargarita
Department of Electronics, Alcalá University (UAH), Plaza San Diego S/N, 28801 Madrid, Spain
1 shared publication - Elham Javanfar
Imam Khomeini International University,Department of Electrical Engineering,Qazvin,Iran,3414896818
1 shared publication - Emilio Jose Bueno
Department of Electronics, University of Alcal, Alcal de Henares, Spain
1 shared publication - Hesam Mazaheri Tehrani
Centro de Electrónica Industrial (CEI), Universidad Politécnica de Madrid, Madrid, Spain
1 shared publication
Latest Publications
- Open Access
A Deep Reinforcement Learning Approach to DC-DC Power Electronic Converter Control with Practical Considerations
In recent years, there has been a growing interest in using model-free deep reinforcement learning (DRL)-based controllers as an alternative approach to improve the dynamic behavior, efficiency, and other aspects of DC–DC power electronic converters, which are traditionally controlled based on small signal models. These conventional controllers often fail to self-adapt to various uncertainties and disturbances. This paper presents a design methodology using proximal policy optimization (PPO), a widely recognized and efficient DRL algorithm, to make near-optimal decisions for real buck converters operating in both continuous conduction mode (CCM) and discontinuous conduction mode (DCM) while handling resistive and inductive loads. Challenges associated with delays in real-time systems are identified. Key innovations include a chattering-reduction reward function, engineering of input features, and optimization of neural network architecture, which improve voltage regulation, ensure smoother operation, and optimize the computational cost of the neural network. The experimental and simulation results demonstrate the robustness and efficiency of the controller in real scenarios. The findings are believed to make significant contributions to the application of DRL controllers in real-time scenarios, providing guidelines and a starting point for designing controllers using the same method in this or other power electronic converter topologies.
Open AccessA Deep Reinforcement Learning Approach to DC-DC Power Electronic Converter Control with Practical Considerations
In recent years, there has been a growing interest in using model-free deep reinforcement learning (DRL)-based controllers as an alternative approach to improve the dynamic behavior, efficiency, and other aspects of DC–DC power electronic converters, which are traditionally controlled based on small signal models. These conventional controllers often fail to self-adapt to various uncertainties and disturbances. This paper presents a design methodology using proximal policy optimization (PPO), a widely recognized and efficient DRL algorithm, to make near-optimal decisions for real buck converters operating in both continuous conduction mode (CCM) and discontinuous conduction mode (DCM) while handling resistive and inductive loads. Challenges associated with delays in real-time systems are identified. Key innovations include a chattering-reduction reward function, engineering of input features, and optimization of neural network architecture, which improve voltage regulation, ensure smoother operation, and optimize the computational cost of the neural network. The experimental and simulation results demonstrate the robustness and efficiency of the controller in real scenarios. The findings are believed to make significant contributions to the application of DRL controllers in real-time scenarios, providing guidelines and a starting point for designing controllers using the same method in this or other power electronic converter topologies.
- 1 November 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 215-221
Full extracting kinematic and dynamic equations of X/Y pedestal with velocity analysis
In order to track the satellite, it is necessary to extract the pedestal kinematic equations by assuming to have the azimuth/elevation angles of satellite path. This paper deals with extracting of forward and inverse kinematic equations of the x/y pedestal with analysis of speed and extraction of singular points. Then equations are varied by the real Azimuth/Elevation of a LEO satellite. Finally the velocity and input torque of each link are examined during the period of work.
- 1 November 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 215-221
Full extracting kinematic and dynamic equations of X/Y pedestal with velocity analysis
In order to track the satellite, it is necessary to extract the pedestal kinematic equations by assuming to have the azimuth/elevation angles of satellite path. This paper deals with extracting of forward and inverse kinematic equations of the x/y pedestal with analysis of speed and extraction of singular points. Then equations are varied by the real Azimuth/Elevation of a LEO satellite. Finally the velocity and input torque of each link are examined during the period of work.