{"title":"对时空缺失数据不敏感的基于图的大规模概率光伏功率预测","authors":"Keunju Song;Minsoo Kim;Hongseok Kim","doi":"10.1109/TSTE.2024.3447023","DOIUrl":null,"url":null,"abstract":"In recent years, power systems integrated with distributed energy resources (DERs) have been considered to mitigate climate change. However, this makes power systems even more uncertain and complex, so uncertainty-aware accurate forecasting needs to be considered for the massive penetration of renewable energy. To this end, we propose a scalable and missing-insensitive framework for probabilistic multi-site photovoltaic (PV) power forecasting, specifically focused on large-scale PV sites and space-time missing data. By leveraging the graph neural network (GNN), the proposed scalable graph learning mechanism with random coarse graph attention and probabilistic spatio-temporal learning performs efficiently for large-scale PV sites in terms of forecasting accuracy and model training complexity. At the same time, our framework adaptively imputes the missing PV data in the space and time domain, respectively. Ablation study results demonstrate that our framework is effective for extracting complex spatial-temporal features across large-scale PV sites. Under extensive experiments, our framework shows 7\n<inline-formula><tex-math>$-$</tex-math></inline-formula>\n10% and 6\n<inline-formula><tex-math>$-$</tex-math></inline-formula>\n25% improvement on average for over 1600 PV sites and three types of space-time missing data, which ensures accurate and stable forecasting.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 1","pages":"160-173"},"PeriodicalIF":8.6000,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Graph-Based Large Scale Probabilistic PV Power Forecasting Insensitive to Space-Time Missing Data\",\"authors\":\"Keunju Song;Minsoo Kim;Hongseok Kim\",\"doi\":\"10.1109/TSTE.2024.3447023\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In recent years, power systems integrated with distributed energy resources (DERs) have been considered to mitigate climate change. However, this makes power systems even more uncertain and complex, so uncertainty-aware accurate forecasting needs to be considered for the massive penetration of renewable energy. To this end, we propose a scalable and missing-insensitive framework for probabilistic multi-site photovoltaic (PV) power forecasting, specifically focused on large-scale PV sites and space-time missing data. By leveraging the graph neural network (GNN), the proposed scalable graph learning mechanism with random coarse graph attention and probabilistic spatio-temporal learning performs efficiently for large-scale PV sites in terms of forecasting accuracy and model training complexity. At the same time, our framework adaptively imputes the missing PV data in the space and time domain, respectively. Ablation study results demonstrate that our framework is effective for extracting complex spatial-temporal features across large-scale PV sites. Under extensive experiments, our framework shows 7\\n<inline-formula><tex-math>$-$</tex-math></inline-formula>\\n10% and 6\\n<inline-formula><tex-math>$-$</tex-math></inline-formula>\\n25% improvement on average for over 1600 PV sites and three types of space-time missing data, which ensures accurate and stable forecasting.\",\"PeriodicalId\":452,\"journal\":{\"name\":\"IEEE Transactions on Sustainable Energy\",\"volume\":\"16 1\",\"pages\":\"160-173\"},\"PeriodicalIF\":8.6000,\"publicationDate\":\"2024-08-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Sustainable Energy\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10643410/\",\"RegionNum\":1,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENERGY & FUELS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Sustainable Energy","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10643410/","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
Graph-Based Large Scale Probabilistic PV Power Forecasting Insensitive to Space-Time Missing Data
In recent years, power systems integrated with distributed energy resources (DERs) have been considered to mitigate climate change. However, this makes power systems even more uncertain and complex, so uncertainty-aware accurate forecasting needs to be considered for the massive penetration of renewable energy. To this end, we propose a scalable and missing-insensitive framework for probabilistic multi-site photovoltaic (PV) power forecasting, specifically focused on large-scale PV sites and space-time missing data. By leveraging the graph neural network (GNN), the proposed scalable graph learning mechanism with random coarse graph attention and probabilistic spatio-temporal learning performs efficiently for large-scale PV sites in terms of forecasting accuracy and model training complexity. At the same time, our framework adaptively imputes the missing PV data in the space and time domain, respectively. Ablation study results demonstrate that our framework is effective for extracting complex spatial-temporal features across large-scale PV sites. Under extensive experiments, our framework shows 7
$-$
10% and 6
$-$
25% improvement on average for over 1600 PV sites and three types of space-time missing data, which ensures accurate and stable forecasting.
期刊介绍:
The IEEE Transactions on Sustainable Energy serves as a pivotal platform for sharing groundbreaking research findings on sustainable energy systems, with a focus on their seamless integration into power transmission and/or distribution grids. The journal showcases original research spanning the design, implementation, grid-integration, and control of sustainable energy technologies and systems. Additionally, the Transactions warmly welcomes manuscripts addressing the design, implementation, and evaluation of power systems influenced by sustainable energy systems and devices.