基于GA-BP和小波-SVM算法的风电场短期功率预测

Short-term Power Forecasting of Wind Farms Based on GA-BP and Wavelet-SVM Algorithm

风力发电过程中的功率预测问题是制约风力发电发展的重要因素。针对单一传统神经网络易陷入局部最优的问题,提出了利用信息熵原理把遗传算法优化的BP网络和小波-支持向量机2种算法进行组合预测,结合华北某风电场提供的历史功率数据和数值天气预报数据对未来48 h功率进行预测,仿真结果表明,该组合预测方法的预测精度比单一预测模型的预测精度高,效率高,具有一定实用价值。

The power prediction problem in wind power generation is an important factor that restricts the development of wind power generation.Aiming at the problem that a single traditional neural network is easy to fall into local optimum,this paper proposes a combination of BP neural network optimized by genetic algorithm and wavelet-SVM algorithm based on information entropy principle,to predict the future 48 h power combining with historical power data and numerical weather forecast data provided by a wind farm in North China.The simulation results show that the combined forecasting method has higher forecasting accuracy and higher efficiency than the single forecasting model,and has certain practical value.