Fault/Event Induced Delayed Voltage Recovery Highlighting the Importance of Load Modelling & Machine Learning Based Load Modelling

Load characteristics have a significant effect on system performance and the results of load flow, voltage and transient stability simulations are known to be highly dependent on the type of load characteristics assumed. Load composition is changing due to technological advancements and specially in past few years it has changed substantially. The objective of this paper is to study an event induced delayed voltage recovery phenomenon occurred in the eastern region of India highlighting importance of dynamic load modelling to assess such conditions and take suitable remedial measures to avoid. Machine learning based approach is used to estimate the coefficient of Static ZIP load model which describes the load composition under steady-state conditions and can also predict the behaviour of modern loads under varying voltage conditions. Simulations and other techniques are also used to validate the results.