Training Neural-Network-Based Controller on Distributed Machine Learning Platform for Power Electronics Systems
Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
| Original language | English |
|---|---|
| Title of host publication | 2017 IEEE Energy Conversion Congress and Exposition (ECCE) |
| Publisher | Institute of Electrical and Electronics Engineers, Inc. |
| Pages | 3083-3089 |
| ISBN (electronic) | 9781509029983 |
| Publication status | Published - Nov 2017 |
Publication series
| Name | IEEE Energy Conversion Congress and Exposition, ECCE |
|---|---|
| Publisher | IEEE |
Conference
| Title | 9th Annual IEEE Energy Conversion Congress and Exposition, ECCE 2017 |
|---|---|
| Location | Duke Energy Convention Center |
| Place | United States |
| City | Cincinnati |
| Period | 1 - 5 October 2017 |
Link(s)
Abstract
A new training scheme for neural-network-based controller for power electronics systems is proposed. It utilizes the circuit model of the power conversion stage (PCS) in the training process. The training algorithm is a distributed form of evolutionary computation, being able to run on a computer cluster equipped with multiple graphics processing units (GPUs). As a design example, a boost converter has been built and evaluated to exemplify the performance of the neural-network controller trained by the proposed scheme. The experimental results showed that the neural-network controller excels in speed of response and rejection of disturbance once trained properly.
Research Area(s)
- Artificial intelligence, Distributed computing, Evolutionary computation, Graphics processing units, Neural network, Power electronics
Citation Format(s)
Training Neural-Network-Based Controller on Distributed Machine Learning Platform for Power Electronics Systems. / Wang, Wenguan; Chung, Henry Shu-hung; Cheng, Ralph et al.
2017 IEEE Energy Conversion Congress and Exposition (ECCE). Institute of Electrical and Electronics Engineers, Inc., 2017. p. 3083-3089 8096563 (IEEE Energy Conversion Congress and Exposition, ECCE).
2017 IEEE Energy Conversion Congress and Exposition (ECCE). Institute of Electrical and Electronics Engineers, Inc., 2017. p. 3083-3089 8096563 (IEEE Energy Conversion Congress and Exposition, ECCE).
Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review
