A novel multivariate grey model for forecasting periodic oscillation time series

作者：

Highlights：

• A grey multivariate model with dynamic sinusoidal term is proposed.

• The Moore-Penrose generalized inverse matrix is used in the least square method.

• The validation set is introduced to the training process of model parameters.

• The relationship between sample size and model accuracy is discussed.

摘要

•A grey multivariate model with dynamic sinusoidal term is proposed.•The Moore-Penrose generalized inverse matrix is used in the least square method.•The validation set is introduced to the training process of model parameters.•The relationship between sample size and model accuracy is discussed.

论文关键词：Multivariate grey prediction model,Particle swarm optimization,Validation set,Electricity consumption,PM2.5 concentrations

论文评审过程：Received 21 March 2022, Revised 26 July 2022, Accepted 12 August 2022, Available online 19 August 2022, Version of Record 5 September 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118556