基于案例推理的极端天气下风功率预测系统研究

Case-based Reasoning Method for Predicting Wind Power Under Extreme Weather

提高风功率预测精度是保障风电并网安全运行的关键,同时也是电力市场现货交易决策制定的支撑,而间歇性、波动性风速是影响风功率预测精度的重要因素。提出了一种基于案例推理的极端天气下风功率预测方法,首先利用混沌理论建立间歇性风速模型,进而确定极端天气预测案例库,其次建立基于案例推理的风功率预测模型,最后结合山西省大同市某风电场的实际运行数据进行验证,并与广义回归神经网络(GRNN)、最小二乘支持向量机(LSSVM)和遗传BP神经网络(GABP)三种方法的预测结果进行对比。仿真结果表明,该方法能够有效提升风电功率预测精度,或可为极端天气时的风功率预测研究提供借鉴。

Improving wind power prediction accuracy is the key to ensure wind power grid connection and also the support for the decision making of spot trade in power market.The intermittent wind speed is an important factor affecting the accuracy of wind power prediction.This paper presents a case-based reasoning(CBR)method for predicting wind power under extreme weather.Firstly,the chaos theory is used to establish the intermittent wind speed model,and then the case base of extreme weather prediction is determined.Secondly,the wind power prediction model is established using case-based reasoning.Finally,the actual operation data of a wind farm in Datong,Shanxi Province is used for verification,of which the prediction results are compared with those of generalized regression neural network(GRNN),least squares support vector machine(LSSVM)and genetic BP neural network(GABP).The simulation results show that this method can effectively improve the wind power prediction accuracy and may provide a useful example for relevant researches.