Real-time digital twin-based optimization with predictive simulation learning
Real-time digital twin-based optimization with predictive simulation learning
复制标题
DOI：
10.1080/17477778.2022.2046520
复制
发表时间：
2022-03
影响因子：
2.5
通讯作者：
Travis Goodwin-;Jie Xu;N. Çelik;Chun-Hung Chen
中科院分区：
文献类型：
--
作者：
Travis Goodwin-;Jie Xu;N. Çelik;Chun-Hung Chen
摘要数字孪生提供了一个令人兴奋的机会，使实时优化的控制和操作的信息物理系统（CPS）与数据驱动的模拟，同时面临着令人望而却步的计算负担。本文介绍了一种方法，使用机器学习预测作为轻量级估计（SAMPLE）的顺序分配，通过利用在实时决策之前在预测模拟学习设置中离线训练的机器学习模型来解决这一计算挑战。SAMPLE以严格而灵活的方式将机器学习预测与数字孪生实时执行生成的数据相集成，并以最佳方式指导数字孪生模拟，以实现CPS中实时决策所需的计算效率。数值实验证明了SAMPLE的可行性，选择最佳决策实时CPS控制和操作，相比，只使用机器学习或模拟。
ABSTRACT Digital twinning presents an exciting opportunity enabling real-time optimization of the control and operations of cyber-physical systems (CPS) with data-driven simulations, while facing prohibitive computational burdens. This paper introduces a method, Sequential Allocation using Machine-learning Predictions as Light-weight Estimates (SAMPLE) to address this computational challenge by leveraging machine learning models trained off-line in a predictive simulation learning setting prior to a real-time decision. SAMPLE integrates machine learning predictions with data generated by real-time execution of a digital twin in a rigorous yet flexible way, and optimally guides the digital twin simulation to achieve the computational efficiency required for real-time decision-making in a CPS. Numerical experiments demonstrate the viability of SAMPLE to select optimal decisions in real-time for CPS control and operations, compared to those of using only machine learning or simulations.