报告人： Lei Yang, University of Nevada, Reno

时间： 2016年12月23日 早上10点

地点：工控新楼211室

报告摘要：

With the increasing penetration of wind into bulk power systems, wind generation has posed a significant challenge to system operators due to the highly variable wind generation. Reliable system operations require accurate wind forecast, especially at the high penetration level of wind generation. In this talk, short-term forecast of wind farm generation is investigated by applying spatio-temporal analysis to extensive measurement data collected from a large wind farm. Specifically, using the data of the wind turbines power outputs recorded across two consecutive years, multiple finite-state Markov chains that take into account the diurnal non-stationarity and the seasonality of wind generation are first developed to capture the fast fluctuations of small amounts of wind generation. To capture the wind ramp dynamics, SVM is employed, based on one key observation from the measurement data that wind ramps always occur with specific patterns. Then, the forecast by the SVM is integrated into each finite-state Markov chain. Based on the SVM enhanced Markov model, short-term distributional forecasts and point forecasts are then derived. The distributional forecast can be utilized to study stochastic unit commitment and economic dispatch problems by using a Markovian approach. Numerical test results, via using realistic wind farm data provided by the National Renewable Energy Laboratory (NREL), demonstrate the significant improved accuracy of the proposed forecast approach.

报告人简介：

Lei Yang received the B.S. and M.S. degrees in electrical engineering from Southeast University, Nanjing, China, in 2005 and 2008, respectively, and the Ph.D. degree from the School of Electrical Computer and Energy Engineering at Arizona State University, Tempe, in 2012. He is currently an Assistant Professor in the Department of Computer Science and Engineering, University of Nevada, Reno, NV, USA. He was a postdoctoral scholar at Princeton University, Princeton, NJ, USA, and an Assistant Research Professor with the School of Electrical Computer and Energy Engineering at Arizona State University, Tempe. He has received the Best Paper Award Runner-up of IEEE INFOCOM 2014.