A review on the forecasting of wind speed and generated power

Abstract

In the world, wind power is rapidly becoming a generation technology of significance. Unpredictability and variability of wind power generation is one of the fundamental difficulties faced by power system operators. Good forecasting tools are urgent needed under the relevant issues associated with the integration of wind energy into the power system. This paper gives a bibliographical survey on the general background of research and developments in the fields of wind speed and wind power forecasting. Based on the assessment of wind power forecasting models, further direction for additional research and application is proposed.

Introduction

With the deterioration of the environment and depletion of conventional resources, renewable energy has attracted people's attention. As a kind of non-pollution renewable energy, wind power has been growing rapidly in many areas, especially in Europe countries. For example in Spain, wind power generation account for 4% of its electricity consumption [1].

Wind power generation depends on wind speed. Wind speed could be easily influenced by obstacle and terrain. It also varies with height, so the random character of wind is significant. The reliability of wind power is not satisfactory because it cannot supply steady electricity to power system. So when the wind power penetration (i.e. proportion of wind power in a power system) grows, the power system operation will be affected [2]. As a result, the power system regulators must make detailed schedule plans and set reserve capacity for it. To reduce the reserve capacity and increase the wind power penetration, the accurate forecasting of wind speed is needed.

To handle wind speed prediction, many methods have been developed. These methods can be divided into two categories. The first is the physical method, which use a lot of physical considerations to reach the best prediction precision. The second is the statistical method, like ARMA model, which aims at finding the relationship of the on-line measured power data [3]. Physical method has advantages in long-term prediction while statistical method does well in short-term prediction. However, this classification is not absolute. Few practical forecasting uses physical or statistical method only. Both physical and statistical models are utilized simultaneously in typical forecasting method. In which, to train the system on the local conditions, NWP results are regarded as input variables together with historical data and statistical theories. In the recent years, some new methods are catching researcher's attention. New methods based on artificial intelligence like artificial neural network (ANN) and fuzzy logic models are widely used [4]. Also, hybrid models, which come out nowadays, of cause are advanced ones and have less error than others.

Wind power generated by wind turbines has intimate relationship with wind speed. Wind speed is converted into power through characteristic curve of a wind turbine. And the forecasting of wind speed and wind power has the same principle. Thus wind speed and wind power are reviewed together and the emphasis is the forecasting method or model. The forecasting method is not classified conventionally as physical and statistical, for most of methods include both of them. This paper divides the forecasting methods into four categories: the physical model, the conventional statistical model, the spatial correlation model, and the artificial intelligence and other new methods.

This paper is organized as follows. Section 2 presents model input and describes various kinds of forecasting models in detail. In Section 3, these forecasting models are compared and evaluated. Finally, Section 4 presents the main conclusion of the paper.