Significant Events Detection and Identification through Electrical Grid Load Profile

Paper discusses the approach that supports data mining on significant events from electrical consumption load profile. The proposed approach leads to the detection and identification of significant events which do not violate the process of energy distribution, but are of significant importance for power utilities functioning. The data available from power meters and intelligent sensors is used to classify the events in power supply process. This information is of high importance and can be utilized to predict violations. It leads to rapid decision-making and allows to avoid the penalties on behalf of the power distribution utilities. For the certain types of significant events the distinctive features based on expert knowledge are introduced. Artificial neural networks (ANNs) of rather simple form application were tested through the numerical procedure of the proposed method. A profile of full load consumed power averaged in the time interval of two weeks, as well as data on the nominal current consumption of metallurgical enterprise were accepted for illustration of the method working capacity.