Wind Generation Capacity Forecasting to Improve the Unit Commitment Scheduling
|
|
Wind energy has gained extensive interest and become one of the most mature renewable energy alternatives to the conventional fuel-based resources. The development of wind power generation has rapidly progressed over the last decade. The record shows that wind power generation has expanded with an annual rate of 25 percent since 1990 and demonstrates a great potential in many regions of the US [1]. According to the record from National Renewable Energy Laboratory, Texas becomes the No. 1 in US regarding the installation capacity of wind generation facilities. Despite various benefits of the wind power, an integration of wind energy into the electric grid is difficult to manage. The main challenge associates with its unpredictability. The power generated from the wind rapidly fluctuates, which imposes difficulties both in terms of operation and planning. Because of intermittent nature of the wind, the utilities traditionally ignore the capacity of wind resources in their unit commitment (UC) scheduling. However, a saving can be realized from the reduction of thermal plant commitment if part of wind capacity can be counted towards ‘firm’ energy resource. Besides, neglecting wind capacity totally in generation planning can be harmful for the system with increasing wind generation penetration level. To efficiently utilize the resources, at least part of the capacity of the wind generation should be taken into account in the UC scheduling. An accurate wind power forecast would allow the utility to harvest the wind capacity and improve the system operation. However, there must be balance between these savings and the potential impact on the system reliability. The dependable capacity of the wind resources depends on the accuracy of the forecasting model. In this regard, the concept of confidence interval comes into play in the wind generation dispatch. This presentation describes the development of an Artificial Neural Networks (ANN) short-term wind power generation forecast for a wind farm. The wind forecast model with a 10-minute forecasting time step and lead-time up to three days ahead has been developed. A new concept of wind capacity dispatch is proposed. |
|
MetroCon 2007 |
|
“Innovating for Society” |
|
Power Engineering |
|
Wei-Jen Lee received the B.S. and M.S. degrees from National Taiwan University, Taipei, Taiwan, R.O.C., and the Ph.D. degree from the University of Texas, Arlington, in 1978, 1980, and 1985, respectively, all in Electrical Engineering. In 1985, he joined the University of Texas, Arlington, where he is currently a professor of the Electrical Engineering Department and the director of the Energy Systems Research Center. He has been involved in research on power flow, transient and dynamic stability, voltage stability, short circuits, relay coordination, power quality analysis, and deregulation for utility companies. He has published more than thirty (30) papers with refereed transaction status and more than ninety five (95) papers presented at conferences and symposia. He has provided on-site training courses for power engineers in Panama, China, Taiwan, Korea, Saudi Arabia, Thailand, and Singapore. He has also served as the primary investigator (PI) or Co-PI of over sixty (60) funded research projects totaling over 6.0 million dollars. Prof. Lee is a Fellow of IEEE and registered Professional Engineering in the State of Texas. |
|
About the Speaker: |
