针对安全和鲁棒风力机队控制的对抗传感器误差
机器学习
2026-04-13 v1 系统与控制
系统与控制
摘要
基于植物的控制是一种新兴的风能技术，既有机会又面临挑战。通过中央控制器协调控制风机，可实现更高的风力发电效率。然而，测量误差可能干扰该过程，甚至可能被黑客篡改中央控制器接收的遥测信号。本文提出了一种框架，通过训练对抗性智能体来干扰控制器，从而开发出安全的植物控制器。这需要训练对抗性智能体以干扰控制器，形成一种“军备�赛”。本文考察了三种广泛的训练方法进行共训练主体和对抗者，发现军备�赛方法效果最佳。这些初始结果表明，军备�赛式的对抗训练将最坏情况下的性能下降从 39% 的功率损失降低到 7.9% 的功率收益，相对于基线运营策略。
引用
@article{arxiv.2604.08750,
title = {Adversarial Sensor Errors for Safe and Robust Wind Turbine Fleet Control},
author = {Julian Quick and Marcus Binder Nilsen and Andreas Bechmann and Tran Nguyen Le and Pierre-Elouan Mikael Rethore},
journal= {arXiv preprint arXiv:2604.08750},
year = {2026}
}
备注
Submitted to Journal of Physics: Conference Series (Torque 2026). This is the Accepted Manuscript version of an article accepted for publication in Journal of Physics: Conference Series. IOP Publishing Ltd is not responsible for any errors or omissions in this version of the manuscript or any version derived from it. This Accepted Manuscript is published under a CC BY licence