Optimal Droop Control Design Using Artificial Intelligent Techniques for Electric Power Systems of More-Electric Aircraft

Hussaini, Habibu; Yang, Tao; Gao, Yuan; Wang, Cheng; Urrutia, Matías; Bozhko, Serhiy

Abstract

The design of the droop coefficient is one of the challenges for the droop control of converters, as it plays a key role in enhancing the performance of the droop control method. This article proposes an artificial neural network (ANN) based technique for the design of optimal droop control of parallel-connected converters in a fast and accurate manner without imposing an additional computational burden on the system. The developed ANN-based design strategy of droop coefficients is used for load sharing and dc bus voltage regulation for the more electric aircraft (MEA) application. In the design process, the optimal droop coefficient setting is obtained by evaluating a user-defined fitness function with the aid of a trained ANN-based surrogate model. It is observed that the system performance metrics predicted by the surrogate model matched very well with that obtained from the simulation model. The experimental results show that the selected optimal droop coefficient setting can enhance the performance of the traditional droop control method in both steady and transient conditions.

• Journal Article Type: Article
• Acceptance Date: Apr 10, 2023
• Online Publication Date: May 3, 2023
• Publication Date: 2024-03
• Deposit Date: Apr 29, 2024
• Publicly Available Date: Apr 29, 2024
• Journal: IEEE Transactions on Transportation Electrification
• Electronic ISSN: 2332-7782
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 10
• Issue: 1
• Pages: 2192-2206
• DOI: https://doi.org/10.1109/tte.2023.3271763
• Public URL: https://nottingham-repository.worktribe.com/output/20287876
• Publisher URL: https://ieeexplore.ieee.org/document/10115011