论文标题
可靠的学习模型预测控制，以定期相关的建筑物控制
Robust Learning Model Predictive Control for Periodically Correlated Building Control
论文作者
论文摘要
占全球能源消耗，住宅和商业建筑的40％以上，将是任何未来的绿色能源系统中的关键参与者。为了在确保乘员舒适的同时充分利用其潜力，需要一个健壮的控制方案来处理各种不确定性，例如外部天气和乘员行为。然而，在大多数不确定性来源中，突出的模式，尤其是周期性都被广泛看到。本文将这种相关结构纳入学习模型预测控制框架中，以学习用于建筑操作的全球最佳稳健控制方案。
Accounting for more than 40% of global energy consumption, residential and commercial buildings will be key players in any future green energy systems. To fully exploit their potential while ensuring occupant comfort, a robust control scheme is required to handle various uncertainties, such as external weather and occupant behaviour. However, prominent patterns, especially periodicity, are widely seen in most sources of uncertainty. This paper incorporates this correlated structure into the learning model predictive control framework, in order to learn a global optimal robust control scheme for building operations.
