计及CCM和改进GRA的PSO-BiLSTM光伏出力预测模型  

PSO-BiLSTMPV output prediction model with CCMand improved GRA

作　　者：高胜强[1] 张琳 王海鹏 宋煜 燕灏 刘紫凝 周维维 卜帅羽 GAO Shengqiang;ZHANG Lin;WANG Haipeng;SONG Yu;YAN Hao;LIU Zining;ZHOU Weiwei;BU Shuaiyu(State Grid Beijing Electric Power Company,Beijing 100031,China;College of Environmental Science and Engineering,North China Electric Power University,Beijing 102206,China)

机构地区：[1]国网北京市电力公司,北京100031 [2]华北电力大学环境科学与工程学院,北京102206

出　　处：《电源技术》2025年第4期869-882,共14页Chinese Journal of Power Sources

基　　金：国网北京市电力公司科技项目资助(520206240001)。

摘　　要：为了显著提高光伏电站输出功率的预测精度,提出了一种基于CCM-IGRA-PSO-BiLSTM的光伏出力智能预测模型。首先,采用收敛交叉映射(convergent cross mapping,CCM)算法提取影响光伏出力的关键气象要素,并将其作为相似日选取的重要评判指标和后续搭建的预测模型的重要输入变量;其次,运用基于熵权法的改进灰色关联分析法(improved grey relation analysis,IGRA)筛选与待预测日气象特征相近的历史相似日;接下来,分别将选定相似日的关键气象参数和光伏发电序列作为训练样本集的输入和输出变量,使用粒子群优化算法(particle swarm optimization,PSO)确定双向长短期记忆网络(bidirectional long short-term memory,Bi-LSTM)的最优超参数组合,建立待预测日的高精度光伏出力预测模型;最后,以云南省某光伏电站为研究对象,建立四个季节的典型日的日前光伏出力组合预测模型,采用平均绝对误差(mean absolute error,MAE)、平均绝对百分比误差(mean absolute percentage error,MAPE)和均方根误差(root mean square error,RMSE)作为模型性能的评价指标。结果显示,以夏季的晴天天气为例,所提模型的MAPE、MAE和RMSE分别达到了0.38%、0.06和0.07 MW,均优于基准模型,可为电站制定合理的生产计划和电力市场参与策略提供科学的指导和支持。To significantly enhance the prediction accuracy of the output power of photovoltaic(PV)power station,this paper developed an intelligent prediction model for PV output through incorporating CCM,IGRA,PSO and BiLSTMinto a general framework.Firstly,the convergent cross mapping(CCM)algorithm was employed to extract key meteorological elements affecting PV output,where they are considered as major evaluation criteria of similar day selection and critical input variables of subsequently established prediction model;secondly,an improved grey relational analysis method(IGRA)based on entropy weight method was utilized to select historical similar days that closely match meteorological characteristics of the day to be predicted.And then,selecting the critical weather parameters and PV power generation sequence of similar days as the training samples,the particle swarm optimization(PSO)algorithm was used to determine optimal hyperparameters combi‐nation for the bidirectional long short-term memory(Bi-LSTM)network.A high-precision PV output prediction model based on CCM-IGRA-PSO-BiLSTM for the predicted days was established.Three criteria,including mean absolute error(MAE),mean absolute percentage error(MAPE)and root mean square error(RMSE),were selected as the evaluation metrics for model performance.The ob‐tained results indicate that,taking the sunny weather in spring as an example,the proposed com‐bined model achieved MAPE,MAE and RMSE of 0.38%,0.06 and 0.07 MW,respectively,all of which surpass those of several baseline models.This way provides scientific guidance and support for the station to formulate reasonable production plan and electricity market participation strategy.

关 键 词：光伏出力预测 粒子群优化 收敛交叉映射 改进的灰色关联分析法 双向长短期记忆网络 

分 类 号：TM914[电气工程—电力电子与电力传动]