Research and application of a novel hybrid forecasting system based on multi-objective optimization for wind speed forecasting

Accurate and stable wind speed forecasting is a crucial issue in the wind power industry, which has a significant effect on power system operation, power grid security and market economics. However, most prior articles only attach importance to improving the accuracy or stability, few of them focus on the accuracy and stability, simultaneously. Therefore, considering one criterion i.e. accuracy or stability is insufficient, in this study a novel powerful hybrid forecasting system is successfully developed, which contains four modules: data preprocessing module, optimization module, forecasting module and evaluation module. In this system, decomposing algorithm is applied to divide the original wind speed data into a finite set of components. Moreover, to achieve high accuracy and strong stability simultaneously, multi-objective ant lion optimization is employed to optimize the initial weights between layers and thresholds of the Elman neutral network in the optimization module, which overcomes the drawbacks of single-objective optimization algorithms. Finally, evaluation module including hypothesis testing and evaluation criteria is introduced to make a comprehensive evaluation for this system. The experimental results indicate that the average values of the mean absolute percent errors of the developed model utilizing 10-min, 30-min and 60-min interval data are 2.8220%, 5.0216% and 7.7205%, respectively, which are much lower than those of the comparison models.