Statistical Machine Learning for Uncertainty Modeling of Renewable Energy
In the context of the rapid development of renewable energy power generation, photovoltaic (PV) and wind power (WP) outputs fluctuate greatly and have strong randomness. This brings a series of problems in controlling, scheduling and planning. To address the randomness of distributed renewable energy (DRE), artificial intelligence (AI) has moved to the mainstream of renewable energy forecasting and prediction, while energy storage can also address the uncertainty of renewable energy systems. Machine learning gives computers the ability of autonomous learning and pattern recognition. The effective combination of mathematical statistics and machine learning makes statistical machine learning an effective solution to deal with uncertainty modeling.
Developing optimization methods suitable for large-scale grid-connected renewable energy has important engineering significance. However, the main theoretical problem of uncertainty optimization is how to deal with uncertainty as the uncertainty of the source side leads to complex and changeable operating scenarios of energy networks. This brings challenges to the optimization of DRE.
In this session, we bring together research that discusses and highlights the statistical machine learning technologies for uncertainty modeling of renewable energy, which enables the functions of planning, operation, and control of uncertainty scenarios.
Topics of interest
include but are not limited to:
energy forecasting 概率可再生能源预测
Probabilistic modeling of
renewable energy systems 可再生能源系统的概率建模
Planning of distributed
renewable energy 分布式可再生能源规划
and scenario generation of renewable energy 可再生能源的不确定性量化和场景模拟可再生能源的不确定性量化和场景模拟
Probabilistic power flow
calculation considering uncertainty 考虑不确定性的概率潮流计算
Probabilistic scheduling of
renewable energy systems 可再生能源系统的概率调度
Probabilistic modeling for
planning distributed renewable energy 分布式可再生能源规划的概率建模
Stochastic weather simulation
and climate models 随机天气模拟和气候模型
Deep learning for renewable
energy system data analysis 可再生能源系统数据分析的深度学习
Applications of reinforcement
learning in renewable energy systems 强化学习在可再生能源系统中的应用
Machine learning in
agriculture and rural microgrid 农业和农村微电网中的机器学习
Prof. Xueqian Fu, China Agricultural University, China
Xueqian Fu (Member, IEEE) received his B.S.
and M.S. degrees from North China Electric
Power University in 2008 and 2011,
respectively. He received his Ph.D. degree
from South China University of Technology in
2015. From 2011 to 2015, he was an
electrical engineer with Guangzhou Power
Supply Co. Ltd.. From 2015 to 2017, he was a
Post-Doctoral Researcher with Tsinghua
University. He is currently an Associate
Professor at China Agricultural University.
His current research interests include
statistical machine learning, Agricultural
Energy Internet, and PV system integration.
He is an associate Editor-in-Chief of
“Information Processing in Agriculture", an
editorial member of “Journal of Solar Energy
Research Updates", an associate editor of
“Protection and Control of Modern Power
Systems”, Lead guest editor of
“International Transactions on Electrical
Energy Systems", Guest Associate Editor of
“Frontiers in Energy Research", and Guest
Editor of “Applied Sciences". In 2020 and
2022, he served as the Session chair of the
2020 and 2022 Asia Energy and Electrical
Engineering Symposium (IEEE AEEES 2020, IEEE
AEEES 2022). In 2022, he served as a
committee member of the 2nd International
Conference on Intelligent Power and Systems
付学谦，副教授/博士生导师，中国农业大学“优秀人才” 、“青年新星”。发表/录用第一/通信作者SCI论文33篇，出版国际英文著作1章，担任国际英文期刊《Information Processing in Agriculture》副主编、《Journal of Solar Energy Research Updates》编委、《Protection and Control of Modern Power Systems》助理编辑、《International Transactions on Electrical Energy Systems》Lead Editor、《Frontiers in Energy Research》客座助理编辑、《Applied Sciences》客座编辑，中文期刊《电力需求侧管理》编委会委员、《中国电力》青年编辑委员会委员，全国研究生教育评估监测专家库专家，北京物联网学会荣誉会员。主持国家自然科学基金青年科学基金项目1项、中国博士后科学基金(面上一等资助) 1项。
encouraged to submit their full papers/abstract to
the special sessions. Please submit electronically
article in PDF format before the submission
submission system is opened here:
choose session 9.
is needed. If you don't have, you can register first.
Any questions, please mail the conference secretary.