Question

求助：论文翻译

Abstract-In this paper, a fuzzy model is suggested for the prediction of wind speed and the produced electrical power at a wind park. The model is trained using a genetic algorithm-based
learning scheme. The training set includes wind speed and direction data, measured at neighboring sites up to 30 km away from the wind turbine clusters. Extensive simulation results are shown for two application cases, providing wind speed forecasts from 30 min to 2 h ahead. It is demonstrated that the suggested model achieves an adequate understanding of the problem while it exhibits significant improvement compared to the persistent method.

I.INTRODUCTION
Large rapid changes in wind power may cause a serious reduction in operating economy and reliability, especially for utilities with large wind power penetration (in the Greek island of Crete it may reach 20 to 40%).Prediction of wind power, along with load forecasting, permits scheduling the connection or disconnection of wind turbines or conventional generators, thus achieving low spinning reserve and optimal operating cost. Since wind power is a function of wind speed, power fore- casts are generally derived through wind speed forecasts. For a single wind turbine, the speed is transformed to power P using manufacturers’ curves or can be approximated as follows:
Where vt ,Pt are the rated speed and power of the wind turbine, and vi vo are the cut-in and cut-out wind speeds. In the case of a large-scale application, such as a wind farm comprising a large number of wind-turbines, the lumped power output is the addition of values sampled at different points of a spatial field. The available data can be used to extract a new power curve that connects this lumped power with the wind speed as measured at one or more reference points of the farm.
In the past, efforts have been made to simulate wind power variations, mostly by analyzing the wind speed time series of a certain site. Unfortunately, typical statistical properties of wind speed such as nonstationarity, a slowly decreasing autocorrelation curve, and weak diurnal variation are not very helpful. Therefore, prediction for the next 15 min to 1 h was practically close to persistent forecast, which suggests no change from the most recent values.
In that respect, previous research often turned to spatial correlation studies of wind speeds, not always leading to a satisfactory model. A significant correlation of hourly or daily average speeds has been recognized for distances of 20 to 100 km. Note that the correlation decreases with distance and topographical elevation difference. It also decreases when the orientation of the distance vector differs from the wind direction.
One of the above studies regards spatial correlation of wind turbulence for short distances(700 m to 15 km)and short-time scales(changes of wind speed per 4,10,30 min and also 1-min deviations from 30-min averaged value).

Answer 1

Abstract-In本文提出了一种模糊模型预测的风速和所产生的电力在风公园。该模型利用遗传algorithm-based训练
学习计划。培训包括风的速度和方向的数据,以邻近的网站多达30公里,距风涡轮集群。广泛的仿真结果显示了两个的应用情况,提供风速预测,30分钟到2小时前进。结果表明,采用的数学模型获得足够的理解问题;而它也显示显著改善比持续的方法。

I.INTRODUCTION
大的迅速变化,可造成风能降低操作方案经济、可靠,尤其是对公用事业风大异能穿透(希腊克里特岛它可以达到20 ~ 40%).Prediction风力发电,随着负荷预测、许可证调度连接或断开风力涡轮机或传统发电机,从而实现低运转储备和最优营运成本。因为风力发电是一个函数的风速、电力脱颖而出-施法通常来自风速的预测。为一个单一的风力,速度转换成为电力P使用制造商曲线或者近似如下:
在v,Pt是额定转速和风力发电机的力量,和六官是切入和裁剪的风速。如果一个大规模的应用,例如风能场包括大量的wind-turbines,集中输出功率增加价值在不同时间点样本空间领域。可用的数据可提取一个新的力量曲线集中与电力连接这在测量风速的一个或多个参考点农场。
在过去,我们努力模拟风力发电的变化,主要通过分析风速时间序列的某工地。不幸的是,典型的统计特性