An Improved Nonhomogeneous Grey Model with Fractional-Order Accumulation and Its Application

The nonhomogeneous grey model has been seen as an effective method for forecasting time series with approximate index law, which widely used in diverse disciplines on account of its high prediction precision. However, there remains room improvements. For this, this study presents improved by incorporating the dynamic integral mean value theorem and fractional accumulation simultaneously. In order to promote efficacy optimised model, we apply whale optimization algorithm (WOA) ascertain optimal parameter. particular, two examples are conducted validate superiority proposed contrast other benchmarks, experimental results show that absolute percentage error approach is 808692% 6.0706%, respectively, indicating performs better than competing models.