Application of Machine Learning and Big Data in Doubly Fed Induction Generator based Stability Analysis of Multi Machine System using Substantial Transformative Optimization Algorithm

With the increase in the amount of data captured during the manufacturing process, surveillance systems are the most important decision making decisions. Current technologies such as Internet of Things (IoT) can be considered a solution to provide efficient monitoring of productivity. In this study, it has suggested a real-time monitoring system that uses an IoT, big data processing and an Offshore Wind Farm (OWF) model is proposed. The Offshore Wind Farm (OWF) is an extended level invasion in modern power electronics systems, in this proposed work Doubly Fed Induction Generator (DFIG) based multi machined OWF was designed, and power stability was analyzed using Substantial Transformative Optimization Algorithm (STOA). The Voltage Source Converter (VSC) and High Voltage Direct Current (HVDC) system was combined with onshore network. The terminal voltage of onshore network was controlled through Onshore Side Converter (OSC), active and reactive power was regulated separately using VSC. The performance of the onshore network was evaluated under renewable network errors (Total Harmonics distortion and steady state error) beside with OWF. The OWF - DFIG active and reactive power was controlled smoothly with in the limit of HVDC, and the power framework security can be updated by controlling the active power of the OSC to help its terminal voltage using STOA methodology. From the voltage control mode, the electrical faults are recovered rapidly with minimum fluctuation. The dynamic simulation comes about additionally demonstrate that onshore network fault can't impact OWF behind HVDC transmission system. Because of the specialized favorable circumstance, VSC-HVDC innovation, the constancy in OWF is very much ensured against the onshore grid faults. The proposed STOA based system has validated through simulation in Matlab Simulink environment. General, 97% effectiveness, accomplished at full load condition in light of the proposed system. The results showed that the IoT system and the proposed large data processing system were sufficiently competent to monitor the manufacturing process.