基于自适应神经模糊推理系统的风功率缺失数据补齐

Data Completing of Missing Wind Power Data Based on Adaptive Neuro-fuzzy Inference System

风电场风电输出功率数据的完整性在风能利用中具有重要意义。利用相邻风机法、持续法、平均插值法、标准功率曲线对应法均可以对风电缺失功率数据进行补齐,但都有各自的优缺点及适用范围;在单一补齐数据方法的基础上,文中采用自适应神经模糊推理系统(ANFIS)模型对丢失数据进行补齐和优化。对实测数据的仿真计算结果表明,用所提出的方法进行数据补齐后风电输出功率的计算结果平均相对误差降低,准确率提高。

The integrity of wind power output data is very important to the utilization of wind energy.Using any one of the adj acent turbine data,persistence strategy,average interpolation strategy and standard power curve strategy,one is enabled to complete the missing wind power data,but each strategy has its own advantages and disadvantages.On the basis of multiple single data completing strategies,the adaptive neuro-fuzzy inference system （ANFIS） model is proposed,and the fuzzy inference algorithm is adopted to complete the missing data,till optimization of the final results.It is shown by simulation calculation of the wind data measured that the average relative error is reduced and the accuracy of data completing is improved.