An optimization-oriented modeling approach using input convex neural networks and its application on optimal chiller loading

作     者：Shanshuo Xing Jili Zhang Song Mu Shanshuo Xing;Jili Zhang;Song Mu

作者机构：Dalian University of TechnologyDalian116024China Guangdong Airport Baiyun Information Technology Co.Ltd.Guangzhou510000China 

出 版 物：《Building Simulation》 (建筑模拟（英文）)

年 卷 期：2024年第17卷第4期

页      面：639-655页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0804[工学-仪器科学与技术] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work was supported by the Dalian Key Field Innovation Team Project(2020RT04) Airport Terminal Wisdom Environment Security and Energy Saving Laboratory of Guangdong Airport Baiyun Information Technology Co.,Ltd.in China 

主　　题：chiller plant input convex neural network optimal load distribution convex optimization 

摘      要：Optimization for the multi-chiller system is an indispensable approach for the operation of highly efficient chiller *** optima obtained by model-based optimization algorithms are dependent on precise and solvable objective *** classical neural networks cannot provide convex input-output mappings despite capturing impressive nonlinear fitting capabilities,resulting in a reduction in the robustness of model-based *** this paper,we leverage the input convex neural networks(ICNN)to identify the chiller model to construct a convex mapping between control variables and the objective function,which enables the NN-based OCL as a convex optimization problem and apply it to multi-chiller optimization for optimal chiller loading(OCL).Approximation performances are evaluated through a four-model comparison based on an experimental data set,and the statistical results show that,on the premise of retaining prior convexities,the proposed model depicts excellent approximation power for the data set,especially the unseen ***,the ICNN model is applied to a typical OCL problem for a multi-chiller system and combined with three types of optimization *** with conventional and meta-heuristic methods,the numerical results suggest that the gradient-based BFGS algorithm provides better energy-saving ratios facing consecutive cooling load inputs and an impressive convergence speed.