Self-Optimizing Vapor Compression Cycles Online With Bayesian Optimization Under Local Search Region Constraints
Self-Optimizing Vapor Compression Cycles Online With Bayesian Optimization Under Local Search Region Constraints
复制标题
DOI：
10.1115/1.4064027
复制
发表时间：
2023-11
期刊：
影响因子：
--
通讯作者：
J. Paulson;Farshud Sorourifar;C. Laughman;A. Chakrabarty
中科院分区：
文献类型：
--
作者：
J. Paulson;Farshud Sorourifar;C. Laughman;A. Chakrabarty
蒸汽压缩循环（VCCs）的自优化效率涉及同时分配多个决策变量，以最大限度地减少功耗，同时保持安全运行条件。由于与循环动力学（和其他智能建筑能源系统）相关的建模复杂性，在线自优化需要能够以无导数和模型不可知的方式安全有效地探索搜索空间的算法。这使得贝叶斯优化（BO）成为自优化的有力候选。不幸的是，经典的BO算法忽略了连续优化器候选者之间的关系，导致搜索空间中的跳转，这可能导致触发故障安全机制，或者违反操作约束的不希望的瞬态动态。为此，我们提出了安全LSR-BO，这是一种基于BO框架的全局优化方法，同时强制执行两种类型的安全约束，包括输出的黑盒约束和输入的局部搜索区域（LSR）约束。我们提供了理论保证，在对性能和约束函数的标准假设下，LSR-BO保证在所有迭代中约束都有高概率得到满足。此外，在仅存在输入LSR约束的情况下，我们证明了该方法将收敛到真正的（未知的）全局最优解。我们在一个商用蒸汽压缩系统的高保真仿真模型上展示了我们提出的LSR- bo方法的潜力，该模型具有LSR对膨胀阀位置和风扇速度的约束，以及对排放和蒸发器温度的其他安全约束。
Self-optimizing efficiency of vapor compression cycles (VCCs) involves assigning multiple decision variables simultaneously in order to minimize power consumption while maintaining safe operating conditions. Due to the modeling complexity associated with cycle dynamics (and other smart building energy systems), online self-optimization requires algorithms that can safely and efficiently explore the search space in a derivative-free and model-agnostic manner. This makes Bayesian optimization (BO) a strong candidate for self-optimization. Unfortunately, classical BO algorithms ignore the relationship between consecutive optimizer candidates, resulting in jumps in the search space that can lead to fail-safe mechanisms being triggered, or undesired transient dynamics that violate operational constraints. To this end, we propose safe LSR-BO, a global optimization methodology that builds on the BO framework while enforcing two types of safety constraints including black-box constraints on the output and local search region (LSR) constraints on the input. We provide theoretical guarantees that under standard assumptions on the performance and constraint functions, LSR-BO guarantees constraints will be satisfied at all iterations with high probability. Furthermore, in the presence of only input LSR constraints, we show the method will converge to the true (unknown) globally optimal solution. We demonstrate the potential of our proposed LSR-BO method on a high-fidelity simulation model of a commercial vapor compression system with both LSR constraints on expansion valve positions and fan speeds, in addition to other safety constraints on discharge and evaporator temperatures.