基于支持向量回归的风电场短期功率预测

发布时间：2019-01-12 20:55

【摘要】：针对风电场的短期功率预测,提出了一种考虑风电机组运行条件的用于风电场短期功率预测的新方法.首先,利用风力发电机的监控和数据采集(SCADA)系统数据计算输出功率和运行条件之间的皮尔逊相关系数,验证了SCADA监测项目对风力发电机输出功率的具有相关性;其次,建立支持向量回归(SVR)模型来预测单个风力发电机的风力与气象、运行状态的关系,发现了考虑运行条件的模型的预测结果优于仅考虑气象信息的模型的预测结果;最后,考虑到不同空间位置的风力发电机组对风电场输出功率的贡献不同,建立了各风力发电机预测功率和风电场预测功率输出之间的回归模型.试验结果表明:所提出的风场回归模型的预测误差小于风力涡轮机所有预测功率的模型的预测误差,从而验证了该方法的有效性.
[Abstract]:Based on the short-term power prediction of wind farm, a new method for short-term power prediction of wind farm considering the operating conditions of wind turbine is proposed. Firstly, the Pearson correlation coefficient between the output power and the operating conditions is calculated by using the monitoring and data acquisition (SCADA) system of the wind turbine, which verifies the relativity of the SCADA monitoring project to the output power of the wind turbine. Secondly, the support vector regression (SVR) model is established to predict the relationship between the wind force and the meteorological and operational state of a single wind turbine. It is found that the prediction results of the model considering operation conditions are better than those of the model with only meteorological information. Finally, considering the different contribution of wind turbine in different space position to the output power of wind farm, the regression model between the predicted power of wind turbine and the predicted power output of wind farm is established. The experimental results show that the prediction error of the proposed wind field regression model is smaller than that of the model with all the predicted power of the wind turbine, which verifies the validity of the proposed method.
【作者单位】：河北工业大学控制科学与工程学院;河北工业大学计算机科学与软件学院;
【基金】：河北省科技支撑计划项目(17214304D)
【分类号】：TM614

【相似文献】