[Poster Presentation]Optimization of BiLSTM for PV Output Prediction Based on Hybrid Bat Algorithm

Optimization of BiLSTM for PV Output Prediction Based on Hybrid Bat Algorithm
ID:164 Submission ID:157 View Protection:ATTENDEE Updated Time:2023-11-20 13:53:24 Hits:174 Poster Presentation

Start Time:Pending (Asia/Shanghai)

Duration:Pending

Session:[No Session] » [No Session Block]

Presentation File

Tips: The file permissions under this presentation are only for participants. You have not logged in yet and cannot view it temporarily.

Abstract
摘要 -- 光伏发电受气候环境影响较大,具有较大的不确定性。准确的光伏出力预测可以降低其不确定性,提高电力系统的可靠性。该文提出一种基于混合蝙蝠算法(HBA)优化的双向长短期记忆神经网络(Bi-directionallongshorttermmemory,BiLSTM)的光伏输出预测模型。首先,采用灰色相关分析方法进行环境因子与光伏出力数据的相关性分析,将相关系数较高的环境因子作为预测网络的输入特征;其次,利用HBA优化BiLSTM网络中的最优参数,建立HBA⁃LSTM预测模型;最后,利用某一区域的实际数据进行预测分析,结果表明,与BiLSTM预测方法相比,本文所提方法的预测精度更高。
 
Keywords
BiLSTM; Hybrid Bat Algorithm; PV Output Forecast; Gray Correlation Analysis
Speaker
Mengxiang Ding
a current graduate s Southwest Jiaotong University;the School of Electrical Engineering

Submission Author
Mengxiang Ding Southwest Jiaotong University;the School of Electrical Engineering
Wenli Fan Southwest Jiaotong University
Zixuan Liu Southwest Jiaotong University
Yang Shengyuan 西南交通大学
Shengyong Ye State Grid Sichuan Economic Research Institute
Selamawit Mesfin 西南交通大学
Comment submit
Verification code Change another
All comments

Contact us

Southwest Jiaotong University

(SWJTU)

Add: No.999, Xi'an Road, Pidu

District, Chengdu City, Sichuan

Province,611756 China

Email: ciycee2023@163.com

 

Aconf Staff:Lu Wei

Tel:+86 18971567453
Email:luwei@chytey.com

WeChat public account: 

IEEE IAS SWJTU Student Branch