安徽大学学报（自然科学版）2025，Vol.49Issue(2)：39-48,10.DOI:10.3969/j.issn.1000-2162.2025.02.005
基于TCN的双向LSTM光伏功率概率预测
Probabilistic prediction of photovoltaic power based on bidirectional LSTM with TCN
摘要
Abstract
To better describe the uncertainty of photovoltaic output,this paper proposes a photovoltaic power probability prediction model based on temporal convolutional network(TCN)and bidirectional long short term memory(BiLSTM).Firstly,historical data sets are divided into three weather scenarios:sunny,partly cloudy,and cloudy/rainy based on cloud cover and rainfall from numerical weather predictions.This segmentation generates training and testing datasets with similar weather conditions.Then,TCN is applied for integrated feature dimension extraction,and BiLSTM neural network is used for bidirectional fitting of output power and weather data time series.In response to the non-differentiability issue of traditional interval prediction quantile loss functions,we introduce the Huber norm approximation as a substitute for the original loss function and apply gradient descent for optimization,forming an improved differentiable quantile regression(QR)model to generate confidence intervals.Finally,kernel density estimation is used to give probability density predictions.Taking a distributed photovoltaic power station in East China as the research object,compared with existing probability prediction methods,the proposed ultra-short-term estimation algorithm shows improvements in various evaluation metrics of power intervals,validating the reliability of the proposed approach.关键词
光伏/概率预测/TCN/分位数回归/BiLSTMKey words
photovoltaic/probability prediction/TCN/quantile regression/BiLSTM分类
动力与电气工程引用本文复制引用
盛万兴,李蕊,赵阳,李鹏丽,张倩..基于TCN的双向LSTM光伏功率概率预测[J].安徽大学学报（自然科学版）,2025,49(2):39-48,10.基金项目
国家电网有限公司总部科技项目(5400-202355207A-1-1-ZN) （5400-202355207A-1-1-ZN）
