Improving prediction accuracy of cooling load using EMD, PSR and RBFNN

2nd Annual International Conference on Information System and Artificial Intelligence

物理学;计算机科学

Shen, Limin^1 ; Wen, Yuanmei^2 ; Li, Xiaohong^2

Department of Mechanical and Electronic Engineering, Guangzhou Institute of Railway Technology, 100 Qinglong Middle Road, GZ, China^1

School of Information Engineering, Guangdong University of Technology, 100 Waihuan Xi Road, GZ, China^2

关键词: Differential methods;    Empirical Mode Decomposition;    Higher-frequency components;    Intrinsic Mode functions;    Lower frequency components;    Phase space reconstruction;    Radial basis function neural networks;    Reconstructed phase space;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/887/1/012016/pdf
DOI  :  10.1088/1742-6596/887/1/012016

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

To increase the accuracy for the prediction of cooling load demand, this work presents an EMD (empirical mode decomposition)-PSR (phase space reconstruction) based RBFNN (radial basis function neural networks) method. Firstly, analyzed the chaotic nature of the real cooling load demand, transformed the non-stationary cooling load historical data into several stationary intrinsic mode functions (IMFs) by using EMD. Secondly, compared the RBFNN prediction accuracies of each IMFs and proposed an IMF combining scheme that is combine the lower-frequency components (called IMF4-IMF6 combined) while keep the higher frequency component (IMF1, IMF2, IMF3) and the residual unchanged. Thirdly, reconstruct phase space for each combined components separately, process the highest frequency component (IMF1) by differential method and predict with RBFNN in the reconstructed phase spaces. Real cooling load data of a centralized ice storage cooling systems in Guangzhou are used for simulation. The results show that the proposed hybrid method outperforms the traditional methods.