Performance analysis of DFIG support microgrid using GA optimized restricted Boltzmann Machine algorithm.

Voltage and reactive power regulation in a deregulated microgrid can be achieved by strategically placing the Static Synchronous Compensator (STATCOM) in coordination with other renewable energy sources, thus ensuring high-end stability and independent control. STATCOM plays a crucial role in effectively addressing power quality issues such as voltage fluctuation and reactive power imbalances caused by the intermittent nature of wind energy conversion systems. To successfully integrate STATCOM into the existing system, it is essential that the control system employed for STATCOM coordination aligns with the Doubly-Fed Induction Generator (DFIG) controller within the microgrid. Therefore, an efficient control algorithm is required in the microgrid, capable of coordinating with the DFIG controller while maintaining system stability. The utilization of a Genetic Algorithm (GA) in calibrating the Restricted Boltzmannn Machine (RBM) can streamline the process of determining optimal hyperparameters for specific tasks, eliminating the need for computationally intensive and time-consuming grid searches or manual tuning. This approach is particularly advantageous when dealing with large datasets within short time durations. In this research, a Simulink model comprising a DFIG-based microgrid and STATCOM has been developed to demonstrate the effectiveness of the proposed control system using RBM in managing STATCOM and facilitating microgrid operations.

Design and development of PI controller for DFIG grid integration using neural tuning method ensembled with dense plexus terminals.

In a DFIG grid interconnected system, the control of real and reactive power relies on various factors. This paper presents an approach to regulate the flow of real and reactive power using a Neural Tuning Machine (NTM) based on a recurrent neural network. The focus is on controlling the flow of reactive power from the rotor-side converter, which is proportional to the grid-side controller through a coupling voltage. The proposed NTM method leverages neural networks to fine-tune the parameters of the PI controller, optimizing performance for DFIG grid integration. By integrating dense plexus terminals, also known as dense connections, within the neural network, the control system achieves enhanced adaptability, robustness, and nonlinear dynamics, addressing the challenges of the grid. Grid control actions are based on the voltage profile at different bus locations, thereby regulating voltage. This article meticulously examines the analysis in terms of DFIG configuration and highlights the advantages of the neural tuning machine in controlling inner current loop parameters compared to conventional PI controllers. To demonstrate the robustness of the control algorithm, a MATLAB Simulink model is designed, and validation is conducted with three different benchmarking models. All calculations and results presented in the article strictly adhere to IEEE and IEC standards. This research contributes to advancing control methodologies for DFIG grid integration and lays the groundwork for further exploration of neural tuning methods in power system control.

Analysis of DFIG-STATCOM P2P control action using simulated annealing techniques.

This paper discusses the performance of Double Fed Induction Generator (DFIG) and static synchronous compensator (STATCOM) in a transmission system using simulated annealing techniques. The rotor speed of DFIG is always changing with respect to wind speed in a nonlinear manner, which makes the system to be more unstable. Under such a condition the performance of the system is disturbed. To improve voltage stability throughout the line, an integration of STATCOM is essential at proper location of the transmission system. The STATCOM integrated DFIG system can enhance the system voltage profile and flexible flow of power in a transmission system. In case of a large disturbance or during the shunt fault condition, the performance study is very important which can be assessed using simulated annealing techniques. The proposed model present in this research work is a multi-objective optimization problem. The parameters for the objective function were identified as voltage at the point of common coupling of wind turbine and low frequency oscillation present in the post restored active power. Therefore a stochastic algorithm based on normalized simulated annealing has been applied where the performance of the system can be tested. Coordinated reactive power control combining with DFIG and STATCOM has been analysed together during various shunt fault condition. To achieve better performance of the system Low voltage rides through the capability of the wind farm and FRT (Fault Ride Through) have been tested under the presence of STATCOM including mutual coordinated control action.