Enhanced Power Quality and Forecasting for PV-Wind Microgrid Using Proactive Shunt Power Filter and Neural Network-Based Time Series Forecasting

This research proposes a proactive Shunt power filter to enhance the energy quality of a microgrid's distribution. The study aims to identify a suitable controller technique for increasing the compensating capacity of the active filter in a PV-Wind hybrid energy production system, enabling voltage management and stabilization in direct current energy conversion facilities. The proposed control system utilizes a modified fuzzy logic algorithm for an enhanced performance active shunt energy filter. Simulations in the SIMULINK and MATLAB model environment validate the effectiveness of the methods. Additionally, a neural network model with a scrolling time frame is proposed to address the nonlinearity and time-varying nature of electricity generation from PV modules. The adaptable forecasting model using the neural network outperforms fixed prediction models in accuracy and computational efficiency. This approach has the potential to significantly improve power quality and forecasting accuracy for real-world PV power production.