Distributed Photovoltaic Power Interval Prediction Based on Spatio-Temporal Correlation Feature and B-LSTM Model

A distributed photovoltaic (PV) power interval prediction method based on spatio-temporal correlation features and bayesian long short-term memory (B-LSTM) model is proposed. The approximate Bayesian neural network is constructed by adding a Dropout layer based on the LSTM neural network to establis...

Full description

Saved in:
Bibliographic Details
Main Authors: Haijun WANG, Rongrong JU, Yinghua DONG
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2024-07-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202310049
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850037835726323712
author Haijun WANG
Rongrong JU
Yinghua DONG
author_facet Haijun WANG
Rongrong JU
Yinghua DONG
author_sort Haijun WANG
collection DOAJ
description A distributed photovoltaic (PV) power interval prediction method based on spatio-temporal correlation features and bayesian long short-term memory (B-LSTM) model is proposed. The approximate Bayesian neural network is constructed by adding a Dropout layer based on the LSTM neural network to establish a B-LSTM model considering spatio-temporal correlation features, and its powerful memory and feature extraction capabilities are used to extract deep features for distributed PV power interval prediction for intrinsic mode function components with different feature scales. An arithmetic example is analysed with an actual distributed PV dataset in a region to verify the superiority of the proposed method.
format Article
id doaj-art-85e73f01a7984e7d8b4d313d295de835
institution DOAJ
issn 1004-9649
language zho
publishDate 2024-07-01
publisher State Grid Energy Research Institute
record_format Article
series Zhongguo dianli
spelling doaj-art-85e73f01a7984e7d8b4d313d295de8352025-08-20T02:56:45ZzhoState Grid Energy Research InstituteZhongguo dianli1004-96492024-07-01577748010.11930/j.issn.1004-9649.202310049zgdl-57-04-wanghaijunDistributed Photovoltaic Power Interval Prediction Based on Spatio-Temporal Correlation Feature and B-LSTM ModelHaijun WANG0Rongrong JU1Yinghua DONG2Nanjing Vocational Institute of Railway Technology, Nanjing 210031, ChinaChina Electric Power Research Institute, Nanjing 210003, ChinaChina Electric Power Research Institute, Nanjing 210003, ChinaA distributed photovoltaic (PV) power interval prediction method based on spatio-temporal correlation features and bayesian long short-term memory (B-LSTM) model is proposed. The approximate Bayesian neural network is constructed by adding a Dropout layer based on the LSTM neural network to establish a B-LSTM model considering spatio-temporal correlation features, and its powerful memory and feature extraction capabilities are used to extract deep features for distributed PV power interval prediction for intrinsic mode function components with different feature scales. An arithmetic example is analysed with an actual distributed PV dataset in a region to verify the superiority of the proposed method.https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202310049distributed photovoltaicsspatio-temporal correlationinterval prediction
spellingShingle Haijun WANG
Rongrong JU
Yinghua DONG
Distributed Photovoltaic Power Interval Prediction Based on Spatio-Temporal Correlation Feature and B-LSTM Model
Zhongguo dianli
distributed photovoltaics
spatio-temporal correlation
interval prediction
title Distributed Photovoltaic Power Interval Prediction Based on Spatio-Temporal Correlation Feature and B-LSTM Model
title_full Distributed Photovoltaic Power Interval Prediction Based on Spatio-Temporal Correlation Feature and B-LSTM Model
title_fullStr Distributed Photovoltaic Power Interval Prediction Based on Spatio-Temporal Correlation Feature and B-LSTM Model
title_full_unstemmed Distributed Photovoltaic Power Interval Prediction Based on Spatio-Temporal Correlation Feature and B-LSTM Model
title_short Distributed Photovoltaic Power Interval Prediction Based on Spatio-Temporal Correlation Feature and B-LSTM Model
title_sort distributed photovoltaic power interval prediction based on spatio temporal correlation feature and b lstm model
topic distributed photovoltaics
spatio-temporal correlation
interval prediction
url https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202310049
work_keys_str_mv AT haijunwang distributedphotovoltaicpowerintervalpredictionbasedonspatiotemporalcorrelationfeatureandblstmmodel
AT rongrongju distributedphotovoltaicpowerintervalpredictionbasedonspatiotemporalcorrelationfeatureandblstmmodel
AT yinghuadong distributedphotovoltaicpowerintervalpredictionbasedonspatiotemporalcorrelationfeatureandblstmmodel