Intermittency in wind offers the major challenge in accomplishing the wind energy as a dependable sustainable energy resource in power grid. Fluctuations in wind speed occur seasonally over a year and if this seasonality is considered, the prediction of the speed of wind can be made more accurate. In this paper, an attempt is made to apply a signal decomposition technique called Variational Mode Decomposition (VMD), which decomposes series of wind speed data into several intrinsic mode functions (IMFs) to make the data more regular thereby enhancing the accuracy of the wind speed forecast model. Then, artificial intelligence technique, Adaptive neuro fuzzy inference system (ANFIS) is applied for the wind speed prediction by combining the obtained modes from VMD. Here, wind data of two sites in India, Jogimatti and Lamba are taken for the study. Each site data is grouped into high and low wind speed months and later, this series is decomposed into regular modes using VMD. Later, ANFIS is applied for training and predicting the wind speed for different time horizons.

中文翻译：

---

使用变分模式分解的基于人工智能的风预测

风的间歇性为实现风能作为电网中可靠的可持续能源提供了主要挑战。风速的波动在一年中季节性地发生，如果考虑到这种季节性，可以使风速的预测更加准确。在本文中，尝试应用一种称为变分模式分解（VMD）的信号分解技术，该技术将一系列风速数据分解为几个固有模式函数（IMF），使数据更规则，从而提高风速的准确性。速度预测模型。然后，通过结合从 VMD 获得的模式，将人工智能技术，自适应神经模糊推理系统（ANFIS）应用于风速预测。在这里，研究采用了印度 Jogimatti 和 Lamba 两个站点的风力数据。每个站点数据被分组为高和低风速月份，之后，使用VMD将该系列分解为常规模式。后来，ANFIS 被应用于训练和预测不同时间范围的风速。