基于改进灰狼算法优化LSTM的光伏发电功率短期预测OA
Short Term Forecasting of Photovoltaic Power Generation Based on LSTM Optimized by Improved Grey Wolf Algorithm
为了提高光伏发电功率短期预测结果的准确性,提出了一种基于改进灰狼(improved grey wolf optimiza-tion,IG WO)算法优化长短时记忆(long short term memory,LSTM)神经网络的光伏发电功率短期预测方法.利用余弦相似度寻找相似日,确定光伏发电功率预测的特征量和训练集.采用非线性收敛因子和差分进化策略对GWO算法进行改进,得到收敛性能更好的IGWO算法,采用IGWO算法对LSTM的超参数进行优化,…查看全部>>
In order to improve the accuracy of short-term prediction results for photovoltaic power generation,a photovoltaic power generation short-term prediction method based on the long short term memory(LSTM)neural network optimized by improved grey wolf optimization(IGWO)algorithm is proposed.The similar days are searched for by using cosine similarity and the feature quantity and training set for photovoltaic power genera-tion prediction are determined.The…查看全部>>
袁建华;谈顺;刘闯
三峡大学电气与新能源学院,湖北宜昌 443000三峡大学电气与新能源学院,湖北宜昌 443000国网湖北省电力有限公司荆门供电公司,湖北荆门 448000
动力与电气工程
光伏发电功率短期预测改进灰狼算法长短时记忆神经网络
photovoltaic power generationshort term forecastingimproved grey wolf optimization algorithmlong short term memory neural network
《电力学报》 2024 (2)
111-118,8
煤燃烧国家重点实验室开放基金资助项目(FSKLCCA1607).
评论