Power Quality in Smart Grids

1Jing Dai, 1Ronald G. Harley, and 2Ganesh Kumar Venayagamoorthy

1School of Electrical and Computer Engineering
Georgia Institute of Technology
Atlanta, GA 30332, USA

2Real-Time Power and Intelligent Systems Laboratory
Missouri University of Science and Technology,
Rolla, MO 65409, USA

Sponsored by the US NSF EFRI #0836017

In recent years, with the wide use of power electronic devices in the electric power grid, large amounts of harmonic currents are being injected into the system, known as “harmonic pollution”, which affects the power quality. Although IEEE standards have required utilities and customers to limit the amount of harmonic current and voltage, any practical evaluation is complicated, as it is difficult to separate the contributions from the utilities and customers. The Smart grid will contain conventional and renewable sources including wind, solar, plug-in vehicles and smart devices. Harmonic pollution control will become critical for the benefits of smart grid technology to be maximized.

On way to address the power quality problem is to use an advanced neural network-based harmonic current prediction scheme to first estimate the true harmonic current contributed by the nonlinearity of the load, instead of the distorted power supply; then, use a neuro-controlled active power filter to compensate the harmonic current drawn by the nonlinear loads, leaving the source current flowing out of the PCC (Point of Common Coupling) clean and nearly purely sinusoidal.  Advanced neural networks for prediction, estimation and control that can handle several variables are needed for the smart grid environment.

References

  • J Dai, P Zhang, J Mazumdar , R G Harley, G K Venayagamoorthy, “A Comparison of MLP, RNN and ESN in Determining Harmonic Contributions from Nonlinear Loads”, 34th Annual Conference of the IEEE Industrial Electronics Society, Orlando, FL, USA, November 10-13, 2008, pp. 3025-3032
  • J. Dai, G. K. Venayagamoorthy and R. G. Harley, ” Harmonic Identification using an Echo State Network for Adaptive Control of an Active Filter in an Electric Ship,” Proc. IEEE International Joint Conference on Neural Networks, IJCNN’09, Atlanta, GA, USA, June 14-19, 2009, pp. 634 – 640