Abstract
In power electronics, prediction of states may be used for identification of faults, determination of aging of components, identification of bad data measurements, among others. Prediction of states in power electronics have broadly been based on: (a) physics-based models, (b) data-driven models, and (c) hybrid models. In this paper, data-driven approaches are presented for intelligent prediction of states in multi-port autonomous reconfigurable solar power plant (MARS) and compared. The data-set needed to train the data-driven models based on artificial intelligence (AI) algorithms has been identified and the trained models are evaluated under different extrapolated normal and abnormal operating conditions. The AI algorithms include nonlinear auto-regressive exogenous model (NARX), spiking neural networks (SNN), and decision tree. The models are compared and contrasted. The best model (NARX) is evaluated under different normal and abnormal operating conditions that have indicated accurate prediction.
| Original language | English |
|---|---|
| Title of host publication | 2021 IEEE Energy Conversion Congress and Exposition, ECCE 2021 - Proceedings |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 1339-1346 |
| Number of pages | 8 |
| ISBN (Electronic) | 9781728151359 |
| DOIs | |
| State | Published - 2021 |
| Event | 13th IEEE Energy Conversion Congress and Exposition, ECCE 2021 - Virtual, Online, Canada Duration: Oct 10 2021 → Oct 14 2021 |
Publication series
| Name | 2021 IEEE Energy Conversion Congress and Exposition, ECCE 2021 - Proceedings |
|---|
Conference
| Conference | 13th IEEE Energy Conversion Congress and Exposition, ECCE 2021 |
|---|---|
| Country/Territory | Canada |
| City | Virtual, Online |
| Period | 10/10/21 → 10/14/21 |
Funding
conditions like grid events. The evaluations have shown that the predictions generated from the NARX models closely match the results obtained from EMT simulation of high-fidelity MARS models. The data prediction from these models can be used to detect anomalies arising from faults or bad data measurements. VII. ACKNOWLEDGEMENTS This paper is based upon work supported by the U.S. Department of Energy’s Office of Energy Efficiency and Renewable Energy (EERE) under Solar Energy Technologies Office (SETO) Agreement Number 34019. The views expressed herein do not necessarily represent the views of the U.S. Department of Energy or the United States Government. This work was supported by the U.S. Department of Energy, Office of Energy Efficiency and Renewable Energy through its Solar Energy Technologies Office.