报告题目：Learning-Based Very-Short-Term Solar Prediction
报 告 人：Dongliang Duan副教授（the University of Wyoming, USA）
报告时间：2019年6月11日10:30-11:30
报告地点：南一楼311
Abstract: The high variability of solar production, especially the ramp events which refer to the sudden drop or rise of solar power, poses challenges to system stability and hence greatly limits the solar penetration into the distribution grid. To address this stability challenge, the system operator needs to acquire accurate prediction of the solar energy at very-short-term time scale in the order of minutes. However, most existing works on solar prediction are developed for medium- or short-term (days or hours) planning and scheduling. In this work, we aim to make very-short-term solar prediction in order to capture the ramp events in solar production. Given that the major factor causing the high variability in solar production is the cloud movement, we take into account the sky images provided by sky cameras. Different from the existing methods involving sky images, however, we also utilize other important meteorological data such as solar geometry, temperature, wind speed, and so on. Our proposed prediction framework incorporates all these data and is verified to capture the ramp events in solar production very well via tests and comparisons against existing alternatives. Our very-short-term solar predictor will facilitate ramp event capture and in turn effective system stability maintenance that is pivotal for high solar penetration.
Biosketch： Dr. Dongliang Duan received his M.A.Sc. and PhD degrees in Electrical Engineering from University of Florida, Gainesville, FL and Colorado State University, Fort Collins, CO, in 2009 and 2012, respectively. Since 2012, he has been with the Department of Electrical & Computer Engineering at the University of Wyoming, and he is currently an Associate Professor. He teaches courses such as Electric Circuit Analysis, Electric Power Quality, Signal Processing for Power Systems, Signal Processing for Power Systems and Power System Wide-Area Monitoring. His current research interest lies in signal processing and data analytics for smart grid and intelligent transportation systems. He has published more than 40 academic papers in the related fields, and he was the Best Paper Finalist in the IEEE PES General Meeting in 2017 and won the Best Paper Award in the 2018 IEEE International Conference on Communication Systems. Currently, he has led a US Department of Energy project (project amount: $200,000), US National Science Foundation project (project amount: $1.34 million), and has served as a reviewer for the US Natural Science Foundation and the US Department of Energy for multiple times. He has been an organizer and reviewer for many international conferences such as ICNC, ICC, and Globecom, and is now a senior editor for IET Communications. He has also served as a reviewer for the top journals in the field of smart grid, wireless communications, and signal processing, such as IEEE Trans. on Power Systems, IEEE Trans. on Smart Grid, IEEE Trans. on Wireless Communications, IEEE Trans. on Communications, IEEE Trans. on Signal Processing, and IEEE Trans. on Intelligent Transportation Systems.
报告题目：Learning-Based Very-Short-Term Solar Prediction
报 告 人：Dongliang Duan副教授（the University of Wyoming, USA）
报告时间：2019年6月11日10:30-11:30
报告地点：南一楼311
Abstract: The high variability of solar production, especially the ramp events which refer to the sudden drop or rise of solar power, poses challenges to system stability and hence greatly limits the solar penetration into the distribution grid. To address this stability challenge, the system operator needs to acquire accurate prediction of the solar energy at very-short-term time scale in the order of minutes. However, most existing works on solar prediction are developed for medium- or short-term (days or hours) planning and scheduling. In this work, we aim to make very-short-term solar prediction in order to capture the ramp events in solar production. Given that the major factor causing the high variability in solar production is the cloud movement, we take into account the sky images provided by sky cameras. Different from the existing methods involving sky images, however, we also utilize other important meteorological data such as solar geometry, temperature, wind speed, and so on. Our proposed prediction framework incorporates all these data and is verified to capture the ramp events in solar production very well via tests and comparisons against existing alternatives. Our very-short-term solar predictor will facilitate ramp event capture and in turn effective system stability maintenance that is pivotal for high solar penetration.
Biosketch： Dr. Dongliang Duan received his M.A.Sc. and PhD degrees in Electrical Engineering from University of Florida, Gainesville, FL and Colorado State University, Fort Collins, CO, in 2009 and 2012, respectively. Since 2012, he has been with the Department of Electrical & Computer Engineering at the University of Wyoming, and he is currently an Associate Professor. He teaches courses such as Electric Circuit Analysis, Electric Power Quality, Signal Processing for Power Systems, Signal Processing for Power Systems and Power System Wide-Area Monitoring. His current research interest lies in signal processing and data analytics for smart grid and intelligent transportation systems. He has published more than 40 academic papers in the related fields, and he was the Best Paper Finalist in the IEEE PES General Meeting in 2017 and won the Best Paper Award in the 2018 IEEE International Conference on Communication Systems. Currently, he has led a US Department of Energy project (project amount: $200,000), US National Science Foundation project (project amount: $1.34 million), and has served as a reviewer for the US Natural Science Foundation and the US Department of Energy for multiple times. He has been an organizer and reviewer for many international conferences such as ICNC, ICC, and Globecom, and is now a senior editor for IET Communications. He has also served as a reviewer for the top journals in the field of smart grid, wireless communications, and signal processing, such as IEEE Trans. on Power Systems, IEEE Trans. on Smart Grid, IEEE Trans. on Wireless Communications, IEEE Trans. on Communications, IEEE Trans. on Signal Processing, and IEEE Trans. on Intelligent Transportation Systems.
学院公众号二维码
