风电预测方法与新趋势综述

Review of wind power forecasting methods and new trends

风力发电作为一种技术成熟、规模较大的新能源发电形式,目前在世界各国得到了广泛应用和发展。风电具有不确定性的特点,必须对其进行准确的预测才能保证并网后电力系统的正常运行。针对风电预测的传统方法和新的研究趋势开展了综述。首先对物理方法、时间序列方法、人工智能方法和组合方法进行了总结,然后针对目前风电预测的几个重要的发展方向:空间相关性预测、集群预测、不确定性预测和爬坡预测的研究进展进行了重点阐述。对现有的风电功率预测方法进行综述后,进一步对这一领域的研究方向进行了展望。

As a mature and large-scale form of new energy power generation, wind power has been widely used and developed in countries all over the world. Wind power has the characteristics of uncertainty, and it must be accurately predicted to ensure the normal operation of the power system after grid connection. This paper reviews the traditional methods and new research trends of wind power forecasting. Firstly, the physical methods, time series methods, artificial intelligence methods and combined methods are summarized. Then, the research progress of several important development directions of wind power forecasting: spatial correlation forecasting, cluster forecasting, uncertainty forecasting and ramp forecasting are highlighted. After reviewing the existing wind power forecasting methods, the research direction in this field is further prospected.