一种短期风电功率集成预测方法

发布时间：2018-04-03 17:03

本文选题：短期风电功率预测　切入点：集成预测方法　出处：《电力系统保护与控制》2016年07期

【摘要】：为提高短期风电功率预测精度,缩短模型训练时间,提出了一种短期风电功率集成预测方法。根据风速功率曲线和风速频率特征,将风速划分为高、中、低三段,并对每段的风速功率特征进行统计分析。高、低风速段功率波动较大,使用最小二乘支持向量机(Least Squares Support Vector Machine,LSSVM)方法可取得较高的预测精度。中风速段风速数据点较多,且风速和功率有明显的物理关系,使用高斯(Gaussian)模型预测。并用风速功率等级表对各段预测的结果进行订正,保证了算法的稳定性。用上海某风电场2014年的历史数据,验证了Gaussian模型以及高、中、低风速段对应的预测算法选取的合理性。与LSSVM预测方法相比较,集成预测方法既提高了预测精度又缩短了预测时间,适合风电场短期功率的实时预测。
[Abstract]:In order to improve the accuracy of short-term wind power prediction and shorten the training time of the model, a short-term wind power integrated forecasting method is proposed.According to the wind speed power curve and the wind speed frequency characteristic, the wind speed is divided into three sections: high, middle and low, and the wind speed power characteristic of each section is analyzed statistically.The power fluctuates greatly in high and low wind speeds. The least square support vector machine least Squares Support Vector Machine (LSSVM) method can achieve high prediction accuracy.There are many data points of wind speed in the middle wind speed section, and there are obvious physical relations between wind speed and power. Gao Si's Gaussian model is used to predict the wind speed.The predicted results are revised by the wind speed power scale to ensure the stability of the algorithm.Using the historical data of a wind farm in Shanghai in 2014, the rationality of the selection of the Gaussian model and the prediction algorithms corresponding to the high, middle and low wind speeds is verified.Compared with the LSSVM forecasting method, the integrated forecasting method not only improves the prediction accuracy but also shortens the prediction time, and is suitable for the real-time prediction of short-term power of wind farm.
【作者单位】：南京信息工程大学信息与控制学院;南京信息工程大学气象灾害预报预警与评估协同创新中心;
【基金】：江苏省六大人才高峰资助项目(WLW-021) 国家公益性行业(气象)科研专项资助项目(GYHY201106040) 江苏省高校优势学科建设工程资助项目
【分类号】：TM614

【相似文献】