Control
alireza khoshsoadat; mohamad Abedini; mohammad reza mirzaei
Abstract
Objective: Three-phase boost rectifier is a Voltage-Source Converter that converts three-phase AC input voltage to a higher DC voltage. In this paper, an artificial intelligent-based system, with learning and adapting ability, is designed for using in the two voltage-based control methods of rectifiers, ...
Read More
Objective: Three-phase boost rectifier is a Voltage-Source Converter that converts three-phase AC input voltage to a higher DC voltage. In this paper, an artificial intelligent-based system, with learning and adapting ability, is designed for using in the two voltage-based control methods of rectifiers, with the names of Voltage Oriented Control (VOC) and Direct Power Control (DPC). For implementation of this intelligent controller a hybrid structure of the Fuzzy Logic (FL) and Neural Networks (NN) that named as Adaptive Network-based Fuzzy Inference System (ANFIS) is used. Among the common network training algorithms, the error back propagation algorithm is known as the most common solution by providing an efficient computational method, so in this article, the above method is used to design the controller. This neuro-fuzzy-based control model is applicable in both VOC and DPC methods and increases the correctness of the output current and DC voltage with low ripple, short settling time and also dynamic operation. The implementation of the proposed controller is simple and requires only 49 fuzzy rules. Compared to other controllers whose structure is neural network and fuzzy, it has fewer layers and its accuracy is higher.
Power systems
Hojatolah Makvandi; Mahmood Joorabian; Hassan Barati
Abstract
The present study introduces a new extensive-area ANFIS (Adaptive Neuro-Fuzzy Interface System)-based method to detect wide area instability and control the time of controlled islanding execution within power systems. The ANFIS parameters are optimized by the PSO method to increase the method’s ...
Read More
The present study introduces a new extensive-area ANFIS (Adaptive Neuro-Fuzzy Interface System)-based method to detect wide area instability and control the time of controlled islanding execution within power systems. The ANFIS parameters are optimized by the PSO method to increase the method’s accuracy at various disturbances and loading circumstances. In addition, to take various stability margins within the areas into account, a novel parallel ANFIS network (P-ANFIS) is implemented in which a distinct ANFIS is allocated for every nearby area. Extended off-line studies are performed to train ANFIS to respond in real-time accurately based on the selected wide area input signals. These parameters are monitored continuously through a wide area measurement system (WAMS) and the proposed P-ANFIS starts to assess the stability between related areas in real-time in the case of potentially unstable oscillations. Once an unstable oscillation is detected, the islanding command is transmitted to perform the controlled islanding scheme. The suggested technique is used in an IEEE 39 bus power system and its performance is demonstrated at different disturbances in terms of both speed and accuracy. It is found that the suggested ANFIS-based technique can determine islanding requirement and its time of execution properly at different disturbances.
Power systems
Akbar Karimipouya; Shahram Karimi; Hamdi Abdi
Abstract
the main challenge in associate islanded Micro grid (MG) is the frequency stability due to the inherent low-inertia feature of distributed energy resources. That is why, energy storage devices, are utilized in MGs as the promising sources for grid short-term frequency regulation. Though energy storage ...
Read More
the main challenge in associate islanded Micro grid (MG) is the frequency stability due to the inherent low-inertia feature of distributed energy resources. That is why, energy storage devices, are utilized in MGs as the promising sources for grid short-term frequency regulation. Though energy storage devices, improve the dynamic response of the load frequency control system, these devices increase system costs. Moreover, the modification or uncertainty of the system parameters will significantly degrade the performance of the conventional load-frequency control system. This article proposes the implementation of rotating-mass-based virtual inertia in Double-Fed Induction Generator (DFIG) to support the primary frequency control associated an adaptive Neuro-Fuzzy Inference System (ANFIS) controller, as the secondary frequency control. The simulation results illustrate that the suggested control scheme ameliorate the dynamic response and performance of the load frequency control system and also the studied islanded MG remains stable, despite severe load variation and parametric uncertainties.
