基于CEEMDAN-GSA-LSTM和SVR的光伏功率短期区间预测  

Short-Term Interval Forecasting of Photovoltaic Power Based on CEEMDAN-GSA-LSTM and SVR

作　　者：李芬 孙凌 王亚维 屈爱芳 梅念 赵晋斌 LI Fen;SUN Ling;WANG Yawei;QU Aifang;MEI Nian;ZHAO Jinbin(College of Electric Power Engineering,Shanghai University of Electric Power,Shanghai 200090,China;Laboratory of Low Frequency Electromagnetic Communication Technology,the 722 Research Institute,CSSC,Wuhan 430205,China;Mathematics and Science College,Shanghai Normal University,Shanghai 200234,China;State Grid Economic and Technological Research Institute Co.,Ltd.,Beijing 102209,China)

机构地区：[1]上海电力大学电气工程学院,上海200090 [2]中国船舶集团有限公司第七二二研究所低频电磁通信技术实验室,武汉430205 [3]上海师范大学数理学院,上海200234 [4]国网经济技术研究院有限公司,北京102209

出　　处：《上海交通大学学报》2024年第6期806-818,共13页Journal of Shanghai Jiaotong University

基　　金：国家自然科学基金面上项目(52177184);上海绿色能源并网工程技术研究中心(13DZ2251900)。

摘　　要：针对光伏输出功率存在间歇性和波动性的问题,提出一种光伏功率短期区间预测模型.首先,该模型采用自适应噪声完备集合经验模态分解将历史光伏出力数据分解为不同的分量并按照其与赤纬角、时角等时序特征量的相关性定义为时序分量和随机分量.其次,分别使用经过引力搜索算法优化的长短期记忆神经网络和支持向量回归模型对时序分量和随机分量进行预测.再次,叠加时序分量和随机分量的预测结果得到点预测结果.然后,对误差进行Johnson变换及正态分布建模后得到光伏功率区间预测结果.最后,利用算例验证该模型的有效性.结果表明:在不同天气情况下,上述模型比现有预测模型精度更高,具有较好的鲁棒性,能够基于预测值提供较为精准的置信区间.Aimed at the intermittency and fluctuation of photovoltaic output power,a short-term interval prediction model of photovoltaic power is proposed.First,the model uses the complete ensemble empirical mode decomposition of adaptive noise(CEEMDAN)to decompose the historical photovoltaic output data into different components and define them as time-series components and random components according to their correlation with time-series features such as declination and time angles.Then,the long short-term memory(LSTM)neural network and the support vector regression(SVR)model optimized by the gravitational search algorithm(GSA)are used to predict the time series components and the random components respectively,and the prediction results of the time series components and the random components are superimposed to obtain the point prediction result.After the error is subjected to Johnson transformation and normal distribution modeling,the photovoltaic power interval prediction result is obtained.Finally,the effectiveness of the method is verified by an example.The comparison of the proposed model with other existing prediction models under different weather conditions suggests that the proposed model has a higher accuracy and a better robustness,which can provide precise confidence intervals based on point prediction values.

关 键 词：光伏功率预测 区间预测 自适应噪声完备集合经验模态分解 引力搜索算法 长短期记忆 支持向量回归 Johnson变换 

分 类 号：TM615[电气工程—电力系统及自动化] P49[天文地球—大气科学及气象学]