With the increasing demand for electrical energy in the household and industrial sectors, reliability in the distribution of electrical energy is very important. Disturbance in electricity distribution is a routine problem that will always occur in the field. To improve the quality of service, readiness in overcoming distribution disturbances is needed, for example by knowing the disturbances that will occur in the field. This study was conducted to solve this problem by applying the Knowledge Growing System (KGS) method in predicting the type of electricity distribution disturbance that occurred in the PLN unit. In this study, the scope of the research object is limited to PLN units in the South Surabaya area. This prediction is done by recognizing the pattern of disturbances that occur every month based on data taken in 2020. This method was chosen because it is an intelligent agent that can generate its knowledge through observing certain phenomena so that it can produce its own knowledge in making predictions. In this study, 5 patterns of electrical disturbances were used at the location of the electricity distribution. From the results of calculations and analysis using the KGS method, it was found that the prediction of electrical distribution disturbances in the form of animal disturbances with the highest degree of confidence value (DoC) occurred at the Sukolilo substation of 34.77%. Predictions of other disturbances in the form of "material" disturbances occur in Rungkut, Waru, and Darmo Grand feeders with DoC values ​​of 28.33%, 29.72%, and 34.72%, respectively.