Generation of harmonics and the existence of waveform pollution in power system networks is one of the major problems facing the utilities. This paper proposes a neural network solution methodology for the problem of measuring the actual amount of harmonic current injected into a power network by a nonlinear load. The determination of harmonic currents is complicated by the fact that the supply voltage waveform is distorted by other loads and is rarely a pure sinusoid. A recurrent neural network trained with the backpropagation through time (BPTT) training algorithm is used to find a way of distinguishing between the load harmonics and supply harmonics, without disconnecting the load from the network. The biggest advantage of this method is that only waveforms of voltages and currents have to be measured. This method is applicable for both single and three phase loads. This technology could be fabricated into a commercial instrument that could be installed in substations of large customer loads, or used as a hand-held clip on instrument.

Meeting Name

31st Annual Conference of IEEE Industrial Electronics Society, 2005. IECON 2005


Electrical and Computer Engineering

Keywords and Phrases

Backpropagation; Backpropagation Through Time Training Algorithm; Current Waveform Measurement; Electric Current Measurement; Hand-Held Clip on Instrument; Harmonic Current Injection; Harmonics Generation; Neural Network; Nonlinear Loads; Power Engineering Computing; Power System Harmonics; Power System Network; Recurrent Neural Nets; Recurrent Neural Network; Single Phase Load; Substation; Three Phase Load; Voltage Measurement; Voltage Waveform Measurement; Waveform Pollution

Document Type

Article - Conference proceedings

Document Version

Final Version

File Type





© 2005 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Full Text Link