Hybrid Renewable Energy Storage Systems for Power Quality Improvement Using Mayfly Optimization Technique

The purpose of this research would be to dynamically assess the efficacy of interconnection networks using a range of important measures. The goal of this study was to provide recommendations for enhancing electricity transmission throughout the electrical grid. Connectivity between the wind farm and the grid is complete. The methods used in this research are Grid-interlinked DFIG Dynamic State Estimation, Optimal Substation Size and Location, and 3C’s Aware Wind Turbine Aggregation. Land form, wind speed, wind direction, and weather characteristics—which describe the weather at a particular time—are examples of environmental features. The wind turbines are grouped by combining the K Nearest Neighbor method and the Density-Based Spatial Clustering of Applications with Noise (also known as KNN-DBSCAN), which facilitates effective aggregation of wind turbines.Frequency variation is caused by the power imbalance between the grid and the installed wind turbines. The Phasor Measurement Unit (PMU), which is in charge of the system’s overall observability, is likewise housed in the substation. So, attaining reliability inside the grid-connected wind farms relies heavily on deciding on the scope and placement of substations. The bio-inspired meta-heuristic optimisation algorithm Mayfly Optimization Technique (MOA) is used for this purpose. To accomplish the dynamic state estimate, the transmitter level power and grid characteristics are predicted. The quality of power generated by a wind power system linked to the grid is evaluated using dynamic state estimation. Power characteristics such pitch angle, wind speed, voltage variation, notching, harmonics, frequency variation, noise, and terminal voltages were forecasted using the Dueling Deep Q Network. The grid’s short circuit impedance, inertia level, and X/R ratio are assessed using the Unscented Kalman Filter - Eigen analysis.