System and method for determining harmonic contributions from nonlinear loads in power systems
MetadataShow full item record
The objective of this research is to introduce a neural network based solution for the problem of measuring the actual amount of harmonic current injected into a power network by an individual nonlinear load. Harmonic currents from nonlinear loads propagate through the system and cause harmonic pollution. As a result, voltage at the point of common coupling (PCC) is rarely sinusoidal. The IEEE 519 harmonic standard provides customer and utility harmonic limits and many utilities are now requiring their customers to comply with IEEE 519. Measurements of the customer’s current at the PCC are expected to determine the customer’s compliance with IEEE 519. However, results in this research show that the current measurements at the PCC are not always reliable in that determination. In such a case, it may be necessary to determine what the customer’s true current harmonic distortions would be if the PCC voltage could be a pure sinusoidal voltage. However, establishing a pure sinusoidal voltage at the PCC may not be feasible since that would mean performing utility switching to reduce the system impedance. An alternative approach is to use a neural network that is able to learn the customer’s load admittance. Then, it is possible to predict the customer’s true current harmonic distortions based on mathematically applying a pure sinusoidal voltage to the learned load admittance. The proposed method is called load modeling. Load modeling predicts the true harmonic current that can be attributed to a customer regardless of whether a resonant condition exists on the utility power system. If a corrective action is taken by the customer, another important parameter of interest is the change in the voltage distortion level at the PCC due to the corrective action of the customer. This issue is also addressed by using the dual of the load modeling method. Topologies of the neural networks used in this research include multilayer perceptron neural networks and recurrent neural networks. The theory and implementation of a new neural network topology known as an Echo State Networks is also introduced. The proposed methods are verified on a number of different power electronic test circuits as well as field data. The main advantages of the proposed methods are that only waveforms of voltages and currents are required for their operation and they are applicable to both single and three phase systems. The proposed methods can be integrated into any existing power quality instrument or can be fabricated into a commercial standalone instrument that could be installed in substations of large customer loads, or used as a hand-held clip on instrument.