Monitoring and classification of nonlinear loads based on artificial neural networks

In this paper artificial neural networks are used for identification of nonlinear loads on the network, as one of the methods for non-intrusive load monitoring. Specific parameters of a group of the nonlinear loads are first measured, and then a neural network is used in order to identify which load, or group of loads, is active on the network. It is shown within an example that the task of loads identification can be done successfully.