Purpose
Aiming at the traditional multivariate grey forecasting model only considers the modelling of real numbers; therefore, the purpose of this paper is to construct an MGM(1, m) model based on the interval grey number sequences according to the grey modelling theory.
Design/methodology/approach
First, the multivariable grey number sequences are transformed into the kernel and grey radius sequences which are two feature sequences of interval grey number sequences. Then the MGM(1, m) model for kernel sequences and grey radius sequences are established, respectively. Finally, the simulation and prediction of the upper and lower bounds of the interval grey number sequences are realized by the reductive calculation of the predicted values of the kernel and grey radius.
Findings
The model is applied to the prediction of visibility and relative humidity, the identification factors of the haze. The results show that the model has high accuracy on the simulation and prediction of multivariable grey number sequences, which is reasonable and practical.
Originality/value
The main contribution of this paper is to propose a method to simulate and forecast the multivariable grey number sequence that is to establish the prediction models for the whitening sequences of multivariable grey number sequences which are kernel and grey radius sequences and extend the possibility boundary of kernel by grey radius. The model can reflect the development trend of multivariable grey number sequence accurately. When the grey information is continuously complemented, the multivariable grey number prediction model is transformed into the traditional MGM(1, m) model. Therefore, the MGM(1, m) model based on interval grey number sequence is the generalisation and expansion of the traditional MGM(1, m) model.
[1]
Li Xiao-xia.
MGM~p(1,n) Optimization Model
,
2003
.
[2]
Meng Wei,et al.
Standardization of interval grey number and research on its prediction modeling and application
,
2012
.
[3]
Sifeng Liu,et al.
A novel interval grey prediction model considering uncertain information
,
2013,
J. Frankl. Inst..
[4]
Si-feng Liu,et al.
Optimization of Background Value in GM(1,1) Model
,
2008
.
[5]
Wu Li-fen.
Grey prediction model for hybrid sequence
,
2013
.
[6]
Zhang Ke.
Prediction model for interval grey number based on trend and cognition
,
2011
.
[7]
Meng Wei.
Prediction model of discrete grey number based on kernels and areas
,
2011
.
[8]
Chaoqing Yuan,et al.
Grey Number Sequence Forecasting Approach for Interval Analysis: A case of China's Gross Domestic Product Prediction
,
2014
.