考虑风速变化模式的风速预报方法分析-analysis of wind speed forecasting method considering wind speed change pattern.docxVIP

AbstractWind power producers play a more and more important role in electricity market. However, the uncertainty of wind is considered as a major barrier against further wind power penetration. The uncertainty increases the level of regulation and reserves required to maintain stability of the grid. Short term wind speed prediction plays an important role in large scale wind power penetration. In this paper, we focus on the study of wind speed prediction in wind farm.Firstly, we propose a pattern based approach for short-term wind speed prediction based on GPCA. It is well accepted that wind varies in different patterns in different weather conditions. Thus, we should use different models to describe these patterns, while most current works build wind speed prediction on a single model. Based on this observation, we introduce GPCA method to discover the patterns hidden in data of wind speed. Then we train a model for each pattern. Finally we use a weighted combination of these models as the final outputs. Experiment results show that our approach outperforms some classical techniques.Secondly, we introduce Deep Learning theory to find patterns automatically. Deep multi-layer neural networks have a strong ability to represent highly non- linear functions. A deep neural network can extract simple and abstract features on the top hidden layer. Thus we use this approach to find patterns in wind speed time series and build a multi-step prediction. The experiment results show that deep architectures are very efficient.Thirdly, we propose an approach to search for patterns and important characteristics in frequency domain. We use Wavelet Analysis to decompose raw wind speed series into a set of sub-series. Sub-series with different frequency can be seen ones with different patterns in frequency domain. A set of prediction models are built for each sub-series and the prediction steps are determined according to the self-relevance character. Then a multi-scale ensemble strat