变尺度时间窗口和波动特征提取的短期风电功率组合预测

精确的风电功率预测对保障大规模风电接入电网后电力系统的安全稳定运行具有重要意义。其中,风速的随机变化是引起风电功率波动和影响风电功率预测精度的最主要原因。针对该问题,提出一种基于变尺度时间窗口和波动特征提取的短期风电功率组合预测方法。首先,通过多重分形谱分析不同天气类型下的风速特征。然后,根据当前风速的特征量采用变尺度滑动时间窗口算法,动态地进行特征提取,由提取结果对风电历史数据进行分类,在此基础上选择特定参数建立对应的功率预测模型。为使模型在功率大幅度波动时刻的预测结果更加精确,提出了基于频谱分析的修正方法。最后,将不同天气类型下的功率预测结果与修正结果进行时序组合。算例结果表明,所述变尺度时间窗口与波动特征提取相结合的短期风电功率组合预测方法可有效提高风速波动剧烈的风电场的风电功率预测精度。

Combined Prediction for Short-term Wind Power Based on Variable Time Window and Feature Extraction

Short-term wind power prediction is a crucial technology to ensure security and stable operation of power grid connected with large-scale wind farms. The fluctuation and predication accuracy of wind power are definitely affected by the intermittence and variability of wind speed. This paper proposes a combined prediction method for short-term wind power based on the variable time window and feature extraction in wind speed. At first, a multifractal spectrum is used to investigate wind speed characterizations. Then, on the basis of the wind fluctuation definition, an abstracting feature extraction approach is proposed by use of a sliding variable time window algorithm capable of self-adaptively adjusting the size of time window width. The historical data is classified according to the fluctuation events abstracting results. Different prediction models are developed by selecting specific parameters after analyzing the fluctuation events characteristics. The presented method employs spectrum analysis to correct errors in power prediction full aware of the complexity and multiformity of output wind power in different time periods. Finally, case studies are carried out to verify and evaluate the availability of the proposed model. Results show that the short-term forecasting accuracy of wind power has been improved in various wind situations.