IOT based adjustment mechanism for direct reference model adaptive IMC to support voltage sag in DFIG wind farm

Abstract

Sustainable energy sources are valuable energy sources.Renewable energy production boosts the economic status of a country. Wind energy is one of the most abundant renewable energy sources, and as a result, the technology to harvest energy from the wind is growing rapidly around the world. As load centers are far away from renewable energy sources, electricity must be transferred over long distances. The most common problems with power fluctuations are caused by long-range voltage sag riding (VSRT). DFIG (Doubly Fed Induction Generator) is very popular in wind energy conversion systems due to its variable speed, high energy collection, efficiency, excellent design and unique control of phase side converters and rotor side converters. Wind speed monitoring is done with the help of Internet of Things (IOT). This paper described the use of training networks in developing adjustment algorithms for direct reference model adaptive IMC for DFIG wind farms. Here, a novel training-based neural network MIT (NNMIT) adjustment mechanism using neural network method is developed and implemented in direct reference model adaptive IMC to improve the performance of the controller during voltage sag. Direct and quadrature axis rotor current controllers are developed and the resulting DFIG is balanced with the FuzzyMIT correction mechanism in the sag ride through the conditions in the wind farm. Improvements across the voltage sag are identified and presented using NNMIT. The proposed NNMIT attain 0.15% torque ripple and 1 ms response time better than the existing FuzzyMIT method. The proposed method preserves high accuracy ranges of 97.88% than the existing method. This approach gives better performance than other control design methods which assume that the flux in the stator is constant in amplitude.