Ultra-short-term Interval Prediction of Wind Power Based on Graph Neural Network and Improved Bootstrap Technique
Reliable and accurate ultra-short-term prediction of wind power is vital for the operation and optimization of power systems. However, the volatility and intermittence of wind power pose uncertainties to traditional point prediction, resulting in an increased risk of power system operation. To repre...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | Journal of Modern Power Systems and Clean Energy |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10026203/ |
| _version_ | 1797770967688151040 |
|---|---|
| author | Wenlong Liao Shouxiang Wang Birgitte Bak-Jensen Jayakrishnan Radhakrishna Pillai Zhe Yang Kuangpu Liu |
| author_facet | Wenlong Liao Shouxiang Wang Birgitte Bak-Jensen Jayakrishnan Radhakrishna Pillai Zhe Yang Kuangpu Liu |
| author_sort | Wenlong Liao |
| collection | DOAJ |
| description | Reliable and accurate ultra-short-term prediction of wind power is vital for the operation and optimization of power systems. However, the volatility and intermittence of wind power pose uncertainties to traditional point prediction, resulting in an increased risk of power system operation. To represent the uncertainty of wind power, this paper proposes a new method for ultra-short-term interval prediction of wind power based on a graph neural network (GNN) and an improved Bootstrap technique. Specifically, adjacent wind farms and local meteorological factors are modeled as the new form of a graph from the graph-theoretic perspective. Then, the graph convolutional network (GCN) and bi-directional long short-term memory (Bi-LSTM) are proposed to capture spatio-temporal features between nodes in the graph. To obtain high-quality prediction intervals (PIs), an improved Bootstrap technique is designed to increase coverage percentage and narrow PIs effectively. Numerical simulations demonstrate that the proposed method can capture the spatiotemporal correlations from the graph, and the prediction results outperform popular baselines on two real-world datasets, which implies a high potential for practical applications in power systems. |
| first_indexed | 2024-03-12T21:29:41Z |
| format | Article |
| id | doaj.art-89f4f8958e3e47f0a9359e399f648712 |
| institution | Directory Open Access Journal |
| issn | 2196-5420 |
| language | English |
| last_indexed | 2024-03-12T21:29:41Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | Journal of Modern Power Systems and Clean Energy |
| spelling | doaj.art-89f4f8958e3e47f0a9359e399f6487122023-07-27T23:00:22ZengIEEEJournal of Modern Power Systems and Clean Energy2196-54202023-01-011141100111410.35833/MPCE.2022.00063210026203Ultra-short-term Interval Prediction of Wind Power Based on Graph Neural Network and Improved Bootstrap TechniqueWenlong Liao0Shouxiang Wang1Birgitte Bak-Jensen2Jayakrishnan Radhakrishna Pillai3Zhe Yang4Kuangpu Liu5Aalborg University,AAU Energy,Aalborg,Denmark,9220Tianjin University,Key Laboratory of Smart Grid of Ministry of Education, School of Electrical and Information Engineering,Tianjin,China,300072Aalborg University,AAU Energy,Aalborg,Denmark,9220Aalborg University,AAU Energy,Aalborg,Denmark,9220Aalborg University,AAU Energy,Aalborg,Denmark,9220Aalborg University,AAU Energy,Aalborg,Denmark,9220Reliable and accurate ultra-short-term prediction of wind power is vital for the operation and optimization of power systems. However, the volatility and intermittence of wind power pose uncertainties to traditional point prediction, resulting in an increased risk of power system operation. To represent the uncertainty of wind power, this paper proposes a new method for ultra-short-term interval prediction of wind power based on a graph neural network (GNN) and an improved Bootstrap technique. Specifically, adjacent wind farms and local meteorological factors are modeled as the new form of a graph from the graph-theoretic perspective. Then, the graph convolutional network (GCN) and bi-directional long short-term memory (Bi-LSTM) are proposed to capture spatio-temporal features between nodes in the graph. To obtain high-quality prediction intervals (PIs), an improved Bootstrap technique is designed to increase coverage percentage and narrow PIs effectively. Numerical simulations demonstrate that the proposed method can capture the spatiotemporal correlations from the graph, and the prediction results outperform popular baselines on two real-world datasets, which implies a high potential for practical applications in power systems.https://ieeexplore.ieee.org/document/10026203/Wind powergraph neural network (GNN)bidirectional long short-term memory (Bi-LSTM)prediction intervalBootstrap technique |
| spellingShingle | Wenlong Liao Shouxiang Wang Birgitte Bak-Jensen Jayakrishnan Radhakrishna Pillai Zhe Yang Kuangpu Liu Ultra-short-term Interval Prediction of Wind Power Based on Graph Neural Network and Improved Bootstrap Technique Journal of Modern Power Systems and Clean Energy Wind power graph neural network (GNN) bidirectional long short-term memory (Bi-LSTM) prediction interval Bootstrap technique |
| title | Ultra-short-term Interval Prediction of Wind Power Based on Graph Neural Network and Improved Bootstrap Technique |
| title_full | Ultra-short-term Interval Prediction of Wind Power Based on Graph Neural Network and Improved Bootstrap Technique |
| title_fullStr | Ultra-short-term Interval Prediction of Wind Power Based on Graph Neural Network and Improved Bootstrap Technique |
| title_full_unstemmed | Ultra-short-term Interval Prediction of Wind Power Based on Graph Neural Network and Improved Bootstrap Technique |
| title_short | Ultra-short-term Interval Prediction of Wind Power Based on Graph Neural Network and Improved Bootstrap Technique |
| title_sort | ultra short term interval prediction of wind power based on graph neural network and improved bootstrap technique |
| topic | Wind power graph neural network (GNN) bidirectional long short-term memory (Bi-LSTM) prediction interval Bootstrap technique |
| url | https://ieeexplore.ieee.org/document/10026203/ |
| work_keys_str_mv | AT wenlongliao ultrashorttermintervalpredictionofwindpowerbasedongraphneuralnetworkandimprovedbootstraptechnique AT shouxiangwang ultrashorttermintervalpredictionofwindpowerbasedongraphneuralnetworkandimprovedbootstraptechnique AT birgittebakjensen ultrashorttermintervalpredictionofwindpowerbasedongraphneuralnetworkandimprovedbootstraptechnique AT jayakrishnanradhakrishnapillai ultrashorttermintervalpredictionofwindpowerbasedongraphneuralnetworkandimprovedbootstraptechnique AT zheyang ultrashorttermintervalpredictionofwindpowerbasedongraphneuralnetworkandimprovedbootstraptechnique AT kuangpuliu ultrashorttermintervalpredictionofwindpowerbasedongraphneuralnetworkandimprovedbootstraptechnique |