基于自适应模糊时间序列法的光伏发电短期功率预测

Photovoltaic Power Generation Short-Term Power Forecasting Based on Adaptive Fuzzy Time Sequence Method

针对并网光伏发电系统功率预测问题,提出一种基于自适应模糊时间序列法的并网光伏发电短期功率预测模型.根据光伏发电系统的历史发电数据,进行自适应算法处理,使数据结构与预测模型相适应,确定聚类数目、划分论域并定义论域区间.通过对历史数据进行模糊化处理,确定各模糊关系组,再计算各类模糊关系组的权重向量.按照模糊时间序列的方法进行光伏发电功率预测,并去模糊化得到实际预测结果.结果表明,对比时间序列预测法ARIMA模型,本文预测模型结果误差由13.66%减小到11.34%,并且在处理突变数据上有较大改进.

To forecast the power of grid connected photovoltaic power generation system this paper proposes a short - term power forecasting model based on adaptive fuzzy time series method. Based on the historical generation data of photovohaic power generation system, the adaptive algorithm is adopted to match the data structure with the forecasting model, and determine the number of clustering and domain interval Historical data is fuzzified to determine each fuzzy relation set. The weight vector of fuzzy relation groups is accordingly calculated. Photovohaic power is forecast by making use of fuzzy time series method, and the real forecast result is obtained after it is defuzzified. The results show that compared with ARIMA model, this forecasting model can reduce the error rate from 13.66 % to 11.34 %, and that dramatic advances in handling mutation data are made.