基于小波-神经网络的太阳辐射强度预测.docVIP

基于小波包-神经网络的太阳逐时辐射预测* 陈杰1,2，张新燕1,2，吕光建1,2 新疆大学 电气工程学院，乌鲁木齐 830047；2. 教育部可再生能源发电与并网控制工程技术研究中心,?乌鲁木齐830047； ） 摘要：太阳辐射量受到季节、大气状况、云况、温度、湿度甚至沙尘等气象因素的影响，表现为强烈的时变性和随机性。对于非线性的辐射量预测，目前已提出了许多方法，但依然存在智能算法的选取不合理、网络结构泛化能力差、预测精度不理想等不足。针对光伏电站太阳逐时辐射强度数据特征不明显、普通BP网络难以完全映射其特征的缺点，提出了一种基于小波包-神经网络的预测模型（WPNN），利用小波包变换将辐射强度序列进行多尺度分解，并创建多个BP模型对各分量预测，最后通过重构得到最终的预测结果。结果表明，预测精度明显提高，满足预期效果，证明该模型的有效性和实际意义。 关键词：太阳辐射；预测；小波包变换；神经网络 中图分类号：TM615 文献标识码：A 文章编号：1001-1390（2015）00-0000-00 Study on prediction of solar radiation intensity based on wavelet decomposition and BP neural network Chen Jie1,2, ,Zhang Xinyan1,2, Lv Guangjian1,2 (1.College of Electrical Engineering, Xin jiang University, Urumqi , 830047, Xinjiang, China. 2. Engineering?Research?Center?of?Education?Ministry?for?Renewable?Energy?Power?Generation?and?Grid?Technology,?Urumqi?830047,?Xinjiang *基金项目：国家自然科学基金资助项目；新疆维吾尔自治区科技支疆项目(201491112)；国网新疆电网项目(SGXJ0000DKJS1440234)Abstract：The amount of solar radiation is affected by the season, atmospheric conditions, cloud conditions, temperature, humidity and even dust and other weather factors with a strong time variability and randomness. For the prediction method?of for nonlinear?radiation, at present, someone put forward many?methods are put forward currently. However, there is still?lack of?selecting the following problems are still presented, such as the?unreasonable intelligent algorithm?selecting is?unreasonable，network structure?generalization ability is? poor generalization ability?and prediction accuracy?is not ideal. Aiming atIn view of the deficiency?of that a?photovoltaic power station?solar radiation intensity?of?the original hourly data?is not obvious and the normal BP neural network?can not be completely?mapped its features,?this paperit puts forward a forecasting prediction model?based on Wavelet Packet Neural Network . Network (WPNN). It used wavelet packet to transform the radiation intensity sequence multi-scale decomposition and established?several B