Machine Learning Application for Voltage Sag Characterization in Distribution Systems
Considering the analysis performed by companies of the electrical sector, an increase in electrical energy demand is expected, as well a higher level of distribution generation. Considering this increase in renewable energy, the loads of different types of consumers and non-linear devices, the complexity of electrical systems increases. Thus, the voltage sag in distribution systems is an important event to be monitored, as it can affect consumers several times a year, and may compromise the production of industrial consumers.
Therefore, to overcome the existing limitations, Artificial Intelligence techniques are currently being explored for the characterization of voltage sags, however the topic has not yet reached the stagnation point. With the oscillography stored in intelligent electronic devices, present in distribution systems, characterization using Artificial Intelligence techniques becomes possible.
This research aims to establish a method for characterization of voltage sags using Artificial Intelligence techniques, for three common situations in distribution systems – energizing a transformer, stating a motor, or presence of a fault. The proposed methodology can differentiate the previously mentioned events from those observed during the normal operation of the electrical network, helping decision makers. Furthermore, the proposed method will be implemented with three different intelligent techniques, providing a performance comparison between these techniques. SVM (Support Vector Machine) was the most suitable technique to be used in more complex distribution systems.