High resolution irradiance forecasts based on sky imagers are valuable for applications that require short term decisions based on ramps of solar irradiance. Here, we present our sky imager based forecasting algorithm, using images of a low cost surveillance camera. Model development and evaluation is done separately for the different steps in sky imager forecasting, starting with cloud detection, followed by estimation and extrapolation of cloud movement, and finally deriving irradiance forecasts from the predicted cloud images. We distinguish between clear and cloudy conditions and especially evaluate the effect of cirrus situations on the different forecasting steps. To create binary cloud masks, we adapted a pixel value based cloud algorithm using a set of manually classified pixels. In an independent validation dataset 90.3 % of the pixels are classified correctly. For the circumsolar region, where cloud decision is known to be especially challenging and crucial for the forecasting of the direct component of the solar radiation, we introduce a correction procedure using real-time irradiance measurements and object recognition methods. Applying this method we can significantly improve the cloud detection in the circumsolar region and increase the forecast skill of the cloud decision forecast. The development of the irradiance algorithm is a special focus of this paper. Real-time irradiance measurements and cloud decision information are used as input to our irradiance model. The algorithm is developed using cloud decision information derived from measurements instead of sky imager cloud decision forecasts to exclude the influence of errors in cloud decision and cloud motion methods for model development. Afterwards, the irradiance algorithm is applied to sky imager based cloud decision forecasts. Even though we start with binary cloud information, the distribution of the clear sky index from our forecasts is in very good agreement with the distribution of the measurements. In a validation dataset of 46 days, we receive a positive forecast skill for all forecast horizons larger than 1 min. We also apply our forecast chain to a dataset of two month from an independent measurement station resulting in a comparable forecasting performance.

中文翻译：

---

一种新的基于天象仪的全球辐照度预测模型，并分析了卷云情况

基于天空成像仪的高分辨率辐照度预测对于需要基于太阳辐照度的坡度做出短期决策的应用非常有价值。在这里，我们使用低成本监控摄像头的图像介绍了基于天空成像器的预测算法。针对天空成像器预测的不同步骤，分别进行模型开发和评估，从云检测开始，然后进行云运动的估计和外推，最后从预测的云图像得出辐照度预测。我们区分晴天和阴天，特别是评估卷云情况对不同预测步骤的影响。为了创建二进制云掩码，我们使用一组手动分类的像素调整了基于像素值的云算法。在独立的验证数据集中90。正确分类了3％的像素。对于已知的云决定对于太阳辐射的直接成分的预测特别具有挑战性和至关重要的外围地区，我们采用实时辐照度测量和物体识别方法介绍了一种校正程序。应用该方法可以显着改善周边地区的云检测，提高云决策预报的预测能力。辐照度算法的发展是本文的重点。实时辐照度测量和云决策信息被用作我们辐照度模型的输入。该算法是使用从测量得出的云决策信息而不是Sky Imager云决策预测来开发的，以排除云决策中的误差影响和云运动方法对模型开发的影响。之后，将辐照度算法应用于基于天空成像器的云决策预测。即使我们从二进制云信息开始，但我们的预报中晴朗天空指数的分布与测量值的分布非常吻合。在46天的验证数据集中，对于大于1分钟的所有预测范围，我们都会获得积极的预测技能。我们还将预测链应用于来自独立测量站的两个月的数据集，从而获得可比的预测性能。辐照度算法应用于基于天空成像仪的云决策预测。即使我们从二进制云信息开始，但我们的预报中晴朗天空指数的分布与测量值的分布非常吻合。在46天的验证数据集中，对于大于1分钟的所有预测范围，我们都会获得积极的预测技能。我们还将预测链应用于来自独立测量站的两个月的数据集，从而获得可比的预测性能。辐照度算法应用于基于天空成像仪的云决策预测。即使我们从二进制云信息开始，但我们的预报中晴朗天空指数的分布与测量值的分布非常吻合。在46天的验证数据集中，对于大于1分钟的所有预测范围，我们都会获得积极的预测技能。我们还将预测链应用于来自独立测量站的两个月的数据集，从而获得可比的预测性能。对于大于1分钟的所有预测范围，我们都会获得积极的预测技能。我们还将预测链应用于来自独立测量站的两个月的数据集，从而获得可比的预测性能。对于大于1分钟的所有预测范围，我们都会获得积极的预测技能。我们还将预测链应用于来自独立测量站的两个月的数据集，从而获得可比的预测性能。