Evaluating Harmonic Distortions on Grid Voltages Due to Multiple Nonlinear Loads Using Artificial Neural Networks

Abstract

This paper presents a procedure to estimate the impacts on voltage harmonic distortion at a point of interest due to multiple nonlinear loads in the electrical network. Despite artificial neural networks (ANN) being a widely used technique for the solution of a large amount and variety of issues in electric power systems, including harmonics modeling, its utilization to establish relationships among the harmonic voltage at a point of interest in the electric grid and the corresponding harmonic currents generated by nonlinear loads was not found in the literature, thus this innovative procedure is considered in this article. A simultaneous measurement campaign must be carried out in all nonlinear loads and at the point of interest for data acquisition to train and test the ANN model. A sensitivity analysis is proposed to establish the percent contribution of load currents on the observed voltage distortion, which constitutes an original definition presented in this paper. Initially, alternative transient program (ATP) simulations are used to calculate harmonic voltages at points of interest in an industrial test system due to nonlinear loads whose harmonic currents are known. The resulting impacts on voltage harmonic distortions obtained by the ATP simulations are taken as reference values to compare with those obtained by using the proposed procedure based on ANN. By comparing ATP results with those obtained by the ANN model, it is observed that the proposed methodology is able to classify correctly the impact degree of nonlinear load currents on voltage harmonic distortions at points of interest, as proposed in this paper.

Using True RMS Current Measurements to Estimate Harmonic Impacts of Multiple Nonlinear Loads in Electric Distribution Grids

“…In order to validate the proposed methodology, two tests were executed. The first one, compares the impact factor performance calculated using the GBRT technique with Permutation Importance, and the impact factor calculated using Artificial Neural Network based procedure as presented in [10] for the IEEE-13 bus industrial system. The second test is accomplished using the AMI system installed at the Federal University of Pará campus.…”

“…Manito in [10] presented an artificial neural network (ANN) model to estimate the impacts of nonlinear loads on the voltage harmonic distortion at a point of interest. His method relies on a sensitivity analysis to establish the percentage contribution (impact factor) of load currents on the observed individual voltage harmonic distortion.…”

“…Although permutation importance is already used successfully to evaluate the impact of input variables on output variables in several applications [32][33][34], it is necessary to evaluate its performance in the problem addressed in this article. As previously mentioned, in the first test the GBRT technique combined with the permutation importance metric are used to calculate the impact factor in an ATP simulation study using the balanced IEEE-13 bus industrial distribution system, and the obtained results are compared with those obtained in [10] also using the same test system. Manito et al (2018) in [10] used an Artificial Neural Network to estimate the impacts of fifth harmonic currents generated by the nonlinear loads on the fifth harmonic voltage at a point of interest, in a scenario simulated in ATP Draw software (Alternative Transient Program [35]).…”

“…(1) Validation using the permutation importance as a metric to measure the impact factor for each nonlinear load by comparison with the result obtained by ATP software in a controlled simulation scheme using the IEEE-13 bus system [10]. (2) Applying the methodology to the AMI system installed at the Federal University of Pará campus located in the north of Brazil, so that it is possible to indicate the most representative nonlinear loads in impacting the THD u at the Common Coupling Point (CCP) with the utility electric grid.…”

“…(2) Applying the methodology to the AMI system installed at the Federal University of Pará campus located in the north of Brazil, so that it is possible to indicate the most representative nonlinear loads in impacting the THD u at the Common Coupling Point (CCP) with the utility electric grid. The result of this test case was also compared to the methodology presented by [10].…”