Due to the intermittent, fluctuating and random characteristics of wind system, the output of wind power will become unstable with the change of wind, which brings severe challenges to the safe and stable operation of the power system. An effective way to solve this problem is to accurately forecast the wind speed. This paper presents a novel wind speed combination forecasting model based on decomposition. The innovation of the forecasting model is as follows. (a) In view of the unstable characteristics of wind speed, variational mode decomposition algorithm is introduced to decompose the historical wind speed data to obtain a series of stable components with different frequencies. (b) Echo state network with good forecasting ability is selected as the forecasting model of each component. (c) To solve the problem that the forecasting performance of echo state network is greatly affected by the parameters of the reservoir, an improved whale optimization algorithm is proposed to optimize these parameters. The optimized echo state network improves the forecasting effect. (d) The final forecasting results are obtained by adding the forecasting values of each component. (e) The performance of the developed forecasting model is verified by using two actual collected data sets of ultra-short-term wind speed and short-term wind speed. Compared with some state-of-the-art forecasting models, the comparison result curve between the forecasting value and actual value of wind speed, the forecasting error distribution, the histogram of the forecasting error distribution, the performance indicators, related statistical indicators, and Taylor diagram show that the developed forecasting model has higher prediction accuracy and is able to reflect the change laws of wind speed correctly.

中文翻译：

---

基于分解的风速组合预测模型

由于风系统的间歇性、波动性、随机性等特点，风电出力会随着风向的变化而变得不稳定，给电力系统的安全稳定运行带来严峻挑战。解决这一问题的有效途径是准确预报风速。提出一种基于分解的新型风速组合预测模型。预测模型的创新点如下。(a)针对风速不稳定的特点，引入变分模态分解算法对历史风速数据进行分解，得到一系列不同频率的稳定分量。(b)选择具有良好预测能力的回波状态网络作为各分量的预测模型。(c)针对回波状态网络的预测性能受水库参数影响较大的问题，提出一种改进的鲸鱼优化算法对这些参数进行优化。优化后的回波状态网络提高了预测效果。(d) 将各分量的预测值相加得到最终的预测结果。(e)利用实际采集的超短期风速和短期风速两个数据集验证了所开发的预测模型的性能。与一些先进的预测模型相比，风速预测值与实际值的比较结果曲线、预测误差分布、预测误差分布直方图、性能指标、相关统计指标、泰勒图表明，所建立的预测模型具有较高的预测精度，能够正确反映风速的变化规律。