Robust Short-Term Wind Power Forecasting using a Multivariate Input and Hybrid Architecture

被引：0

作者：

Truc Thi Kim Nguyen ^{[1
]}

Duy Nhu Nhat Do ^{[1
]}

Hoang Nhu Thanh Vo ^{[1
]}

Hung Ho Si Nguyen ^{[1
]}

Minh Thi Tinh Le ^{[2
]}

Viet Thanh Dinh ^{[1
]}

机构：

[1] Univ Da Nang, Univ Sci & Technol, Fac Elect Engn, Da Nang, Vietnam

[2] VNU HCM, Ho Chi Minh City Univ Technol, Fac Elect & Elect Engn, Ho Chi Minh, Vietnam

来源：

2023 ASIA MEETING ON ENVIRONMENT AND ELECTRICAL ENGINEERING, EEE-AM | 2023年

关键词：

Time series forecasting; artificial neural networks; wind power; wind power forecasting; deep learning; LSTM; CNN-LSTM;

D O I：

10.1109/EEE-AM58328.2023.10394758

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

Wind power is a clean, efficient and sustainable source of electricity that is highly regarded in the renewable energy industry. However, wind power is significantly dependent on weather, especially wind speed. Therefore, making an accurate forecast of the generating capacity of a wind power plant is very important to help manage and optimize the operation of the power generation system. This paper proposed wind power forecasting models using time series forecasting methods such as LSTM, CNN and the combination of CNN-LSTM with multivariable and univariate input. These models are evaluated with a dataset collected from wind power plant BT2 - Quang Binh. The results show that the combined model of CNN-LSTM with multivariable input gives more accurate predictive results than other proposed models in the Turbine 27 dataset in term of Root Mean Square Error and Mean Absolute Percentage Error.

引用

页数：6

共 15 条

[1]

[Anonymous], 2021, Nang luong Viet Nam

[2]

Chollet F., 2015, About us

[3] Models for Short-Term Wind Power Forecasting Based on Improved Artificial Neural Network Using Particle Swarm Optimization and Genetic Algorithms [J].

Dinh Thanh Viet ;

Vo Van Phuong ;

Minh Quan Duong ;

Quoc Tuan Tran .

ENERGIES, 2020, 13 (11)

[4]

Viet DT, 2018, PROCEEDINGS OF 2018 4TH INTERNATIONAL CONFERENCE ON GREEN TECHNOLOGY AND SUSTAINABLE DEVELOPMENT (GTSD), P130, DOI 10.1109/GTSD.2018.8595557

[5]

Doan L. T. D, 2018, Nghien cuu du bao cong suat phat cua nha may dien gio

[6] Power Forecasting of Regional Wind Farms via Variational Auto-Encoder and Deep Hybrid Transfer Learning [J].

Khan, Mansoor ;

Naeem, Muhammad Rashid ;

Al-Ammar, Essam A. ;

Ko, Wonsuk ;

Vettikalladi, Hamsakutty ;

Ahmad, Irfan .

ELECTRONICS, 2022, 11 (02)

[7] Wind Power Forecasting with Deep Learning Networks: Time-Series Forecasting [J].

Lin, Wen-Hui ;

Wang, Ping ;

Chao, Kuo-Ming ;

Lin, Hsiao-Chung ;

Yang, Zong-Yu ;

Lai, Yu-Huang .

APPLIED SCIENCES-BASEL, 2021, 11 (21)

[8] A Hybrid GA-PSO-CNN Model for Ultra-Short-Term Wind Power Forecasting [J].

Liu, Jie ;

Shi, Quan ;

Han, Ruilian ;

Yang, Juan .

ENERGIES, 2021, 14 (20)

[9] Short-term forecasting for multiple wind farms based on transformer model [J].

Qu, Kai ;

Si, Gangquan ;

Shan, Zihan ;

Kong, XiangGuang ;

Yang, Xin .

ENERGY REPORTS, 2022, 8 :483-490

[10] Short-term multi-step wind power forecasting based on spatio-temporal correlations and transformer neural networks [J].

Sun, Shilin ;

Liu, Yuekai ;

Li, Qi ;

Wang, Tianyang ;

Chu, Fulei .

ENERGY CONVERSION AND MANAGEMENT, 2023, 283

← 1 2 →