Short-Term Wind and Photovoltaic Power Prediction Based on Optimized LSTM Model

Yuhui Li; Jiandong Duan; Pengfei Zhang; Bo Shao; Luxiao Wang; Yiming Xu

doi:10.1007/978-981-96-1856-9_11

Short-Term Wind and Photovoltaic Power Prediction Based on Optimized LSTM Model

Yuhui Li
, Jiandong Duan^*
, Pengfei Zhang
, Bo Shao
, Luxiao Wang
, Yiming Xu

^*Corresponding author for this work

School of Electrical Engineering and Automation, Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Volatility and randomness of wind speed and solar irradiance can make it difficult to predict the power of wind and photovoltaic in short time, which reduces power grid’s scheduling ability and affects the stability of grid-connected operation of new energy power generation. In order to address this problem, the Quantum Particle Swarm Optimization (QPSO) algorithm is adopted to optimize the network structure and parameters of Long-Short Term Memory (LSTM) net-work. Through theoretical analysis of working principle and process of LSTM network and optimization algorithm, an optimized LSTM for predicting wind and photovoltaic power in short time is established. The accuracy of the proposed model is proved by using actual data, then compared with unoptimized model and particle swarm optimization (PSO) optimized model. The results of experimental indicate that the LSTM model optimized by QPSO has better prediction precision and demonstrates good prediction results in both wind and photovoltaic power generation in short time, with a wider applicability.

Original language	English
Title of host publication	The Proceedings of 2024 International Conference of Electrical, Electronic and Networked Energy Systems
Editors	Aimin Sha, Jishen Peng, Cancan Rong, Li Zhang, XIaoheng Yan, Zheming Jin
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	96-106
Number of pages	11
ISBN (Print)	9789819618552
DOIs	https://doi.org/10.1007/978-981-96-1856-9_11
State	Published - 2025
Externally published	Yes
Event	International Conference of Electrical, Electronic and Networked Energy Systems, EENES 2024 - Xi'an, China Duration: 18 Oct 2024 → 20 Oct 2024

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	1330 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	International Conference of Electrical, Electronic and Networked Energy Systems, EENES 2024
Country/Territory	China
City	Xi'an
Period	18/10/24 → 20/10/24

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

LSTM network
PSO
QPSO
Short-term power prediction of wind and photovoltaic

Access to Document

10.1007/978-981-96-1856-9_11

Cite this

Li, Y., Duan, J., Zhang, P., Shao, B., Wang, L., & Xu, Y. (2025). Short-Term Wind and Photovoltaic Power Prediction Based on Optimized LSTM Model. In A. Sha, J. Peng, C. Rong, L. Zhang, XI. Yan, & Z. Jin (Eds.), The Proceedings of 2024 International Conference of Electrical, Electronic and Networked Energy Systems (pp. 96-106). (Lecture Notes in Electrical Engineering; Vol. 1330 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-96-1856-9_11

Li, Yuhui ; Duan, Jiandong ; Zhang, Pengfei et al. / Short-Term Wind and Photovoltaic Power Prediction Based on Optimized LSTM Model. The Proceedings of 2024 International Conference of Electrical, Electronic and Networked Energy Systems. editor / Aimin Sha ; Jishen Peng ; Cancan Rong ; Li Zhang ; XIaoheng Yan ; Zheming Jin. Springer Science and Business Media Deutschland GmbH, 2025. pp. 96-106 (Lecture Notes in Electrical Engineering).

@inproceedings{e0465b252d4b489197e3bf59a9180b3e,

title = "Short-Term Wind and Photovoltaic Power Prediction Based on Optimized LSTM Model",

abstract = "Volatility and randomness of wind speed and solar irradiance can make it difficult to predict the power of wind and photovoltaic in short time, which reduces power grid{\textquoteright}s scheduling ability and affects the stability of grid-connected operation of new energy power generation. In order to address this problem, the Quantum Particle Swarm Optimization (QPSO) algorithm is adopted to optimize the network structure and parameters of Long-Short Term Memory (LSTM) net-work. Through theoretical analysis of working principle and process of LSTM network and optimization algorithm, an optimized LSTM for predicting wind and photovoltaic power in short time is established. The accuracy of the proposed model is proved by using actual data, then compared with unoptimized model and particle swarm optimization (PSO) optimized model. The results of experimental indicate that the LSTM model optimized by QPSO has better prediction precision and demonstrates good prediction results in both wind and photovoltaic power generation in short time, with a wider applicability.",

keywords = "LSTM network, PSO, QPSO, Short-term power prediction of wind and photovoltaic",

author = "Yuhui Li and Jiandong Duan and Pengfei Zhang and Bo Shao and Luxiao Wang and Yiming Xu",

note = "Publisher Copyright: {\textcopyright} Beijing Paike Culture Commu. Co., Ltd. 2025.; International Conference of Electrical, Electronic and Networked Energy Systems, EENES 2024 ; Conference date: 18-10-2024 Through 20-10-2024",

year = "2025",

doi = "10.1007/978-981-96-1856-9\_11",

language = "英语",

isbn = "9789819618552",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "96--106",

editor = "Aimin Sha and Jishen Peng and Cancan Rong and Li Zhang and XIaoheng Yan and Zheming Jin",

booktitle = "The Proceedings of 2024 International Conference of Electrical, Electronic and Networked Energy Systems",

address = "德国",

}

Li, Y, Duan, J, Zhang, P, Shao, B, Wang, L & Xu, Y 2025, Short-Term Wind and Photovoltaic Power Prediction Based on Optimized LSTM Model. in A Sha, J Peng, C Rong, L Zhang, XI Yan & Z Jin (eds), The Proceedings of 2024 International Conference of Electrical, Electronic and Networked Energy Systems. Lecture Notes in Electrical Engineering, vol. 1330 LNEE, Springer Science and Business Media Deutschland GmbH, pp. 96-106, International Conference of Electrical, Electronic and Networked Energy Systems, EENES 2024, Xi'an, China, 18/10/24. https://doi.org/10.1007/978-981-96-1856-9_11

Short-Term Wind and Photovoltaic Power Prediction Based on Optimized LSTM Model. / Li, Yuhui; Duan, Jiandong; Zhang, Pengfei et al.
The Proceedings of 2024 International Conference of Electrical, Electronic and Networked Energy Systems. ed. / Aimin Sha; Jishen Peng; Cancan Rong; Li Zhang; XIaoheng Yan; Zheming Jin. Springer Science and Business Media Deutschland GmbH, 2025. p. 96-106 (Lecture Notes in Electrical Engineering; Vol. 1330 LNEE).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Short-Term Wind and Photovoltaic Power Prediction Based on Optimized LSTM Model

AU - Li, Yuhui

AU - Duan, Jiandong

AU - Zhang, Pengfei

AU - Shao, Bo

AU - Wang, Luxiao

AU - Xu, Yiming

N1 - Publisher Copyright: © Beijing Paike Culture Commu. Co., Ltd. 2025.

PY - 2025

Y1 - 2025

N2 - Volatility and randomness of wind speed and solar irradiance can make it difficult to predict the power of wind and photovoltaic in short time, which reduces power grid’s scheduling ability and affects the stability of grid-connected operation of new energy power generation. In order to address this problem, the Quantum Particle Swarm Optimization (QPSO) algorithm is adopted to optimize the network structure and parameters of Long-Short Term Memory (LSTM) net-work. Through theoretical analysis of working principle and process of LSTM network and optimization algorithm, an optimized LSTM for predicting wind and photovoltaic power in short time is established. The accuracy of the proposed model is proved by using actual data, then compared with unoptimized model and particle swarm optimization (PSO) optimized model. The results of experimental indicate that the LSTM model optimized by QPSO has better prediction precision and demonstrates good prediction results in both wind and photovoltaic power generation in short time, with a wider applicability.

AB - Volatility and randomness of wind speed and solar irradiance can make it difficult to predict the power of wind and photovoltaic in short time, which reduces power grid’s scheduling ability and affects the stability of grid-connected operation of new energy power generation. In order to address this problem, the Quantum Particle Swarm Optimization (QPSO) algorithm is adopted to optimize the network structure and parameters of Long-Short Term Memory (LSTM) net-work. Through theoretical analysis of working principle and process of LSTM network and optimization algorithm, an optimized LSTM for predicting wind and photovoltaic power in short time is established. The accuracy of the proposed model is proved by using actual data, then compared with unoptimized model and particle swarm optimization (PSO) optimized model. The results of experimental indicate that the LSTM model optimized by QPSO has better prediction precision and demonstrates good prediction results in both wind and photovoltaic power generation in short time, with a wider applicability.

KW - LSTM network

KW - PSO

KW - QPSO

KW - Short-term power prediction of wind and photovoltaic

UR - https://www.scopus.com/pages/publications/105000434211

U2 - 10.1007/978-981-96-1856-9_11

DO - 10.1007/978-981-96-1856-9_11

M3 - 会议稿件

AN - SCOPUS:105000434211

SN - 9789819618552

T3 - Lecture Notes in Electrical Engineering

SP - 96

EP - 106

BT - The Proceedings of 2024 International Conference of Electrical, Electronic and Networked Energy Systems

A2 - Sha, Aimin

A2 - Peng, Jishen

A2 - Rong, Cancan

A2 - Zhang, Li

A2 - Yan, XIaoheng

A2 - Jin, Zheming

PB - Springer Science and Business Media Deutschland GmbH

T2 - International Conference of Electrical, Electronic and Networked Energy Systems, EENES 2024

Y2 - 18 October 2024 through 20 October 2024

ER -

Li Y, Duan J, Zhang P, Shao B, Wang L, Xu Y. Short-Term Wind and Photovoltaic Power Prediction Based on Optimized LSTM Model. In Sha A, Peng J, Rong C, Zhang L, Yan XI, Jin Z, editors, The Proceedings of 2024 International Conference of Electrical, Electronic and Networked Energy Systems. Springer Science and Business Media Deutschland GmbH. 2025. p. 96-106. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-96-1856-9_11

Short-Term Wind and Photovoltaic Power Prediction Based on Optimized LSTM Model

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this