In the present study, a classification system of four meteorological indices were introduced to classify the sky types from sunny to cloudy. These meteorological indices are; cloud cover (Cc), sunshine hour (S), clearness index (Kt) and diffuse fraction (K). Frequency of occurrence and cumulative frequency distribution of each sky indices were established to interpret the prevailing sky conditions in eight cases, each case investigates one day, these days were chosen according to the type of clouds that were overwhelming that day at a subtropical location in Turkey (Izmir). The impact of Cc, on measured global solar radiation (GSR) intensity were also analyzed. In order to predict GSR in each selected case and to making it more and more precise, NARX, FFNN and GRNN weather parameters-based models were evaluated and compared. To achieve accuracy of estimation, ten different input configurations were used to train the models. In addition global solar radiation in a cloudless skies (GSR’) is evaluated as a new input parameter. NARX models had the best performance for estimation of GSR in the first case, with GPI of 0.936 (NARX-C1M1). Results are also indicating that all NARX artificial neural network models provided better estimations than GRNN and FFNN models in case 2 with GPI value of 0.872 (NARX-C2M1). As for case 3, NARX was considered as the best models (NARX-C3M1, GPI = 0.957), followed by NARX (NARX-C3M6, GPI = 0.956) and then FFNN (FF-C3M1, GPI = 0.949). In case 4, NARX models had the highest GPI value (NARX-C4M1, GPI = 0.957) compared with FFNN and GRNN indicated models. Regarding case 5, NARX was considered as the best network (NARX-C5M4, GPI = 0.748), followed by NARX-C5M9 (GPI = 0.549), while FFNN and GRNN model couldn't provide positive results. Likewise, the NARX models did provide better results in case 6 with best GPI value up to 0.64. Furthermore, only NARX and FFNN models provided the better estimation in case 7 (best model, NARX-C7M1 with GPI = 0.826), whereas, GRNN models did not give such acceptable results. Similar to the mentioned above and in comparison with FFNN and GRNN, we have deducated that NARX models offered a better accuracy results compared with the other models (best model, NARX-C8M4 with GIP = 0.364) in case8.

在本研究中，引入了四个气象指标的分类系统来对从晴天到多云的天空类型进行分类。这些气象指标是：云量（Cc），日照小时（S），净度指数（Kt）和扩散分数（K）。建立了每个天空指数的发生频率和累积频率分布，以解释8种情况下的主要天空状况，每种情况下调查一天，这些天是根据当天在土耳其亚热带地区压倒性的云的类型选择的（伊兹密尔）。还分析了Cc对测得的全球太阳辐射（GSR）强度的影响。为了预测每种情况下的GSR并使其越来越精确，对NARX，FFNN和GRNN基于天气参数的模型进行了评估和比较。为了实现估计的准确性，使用了十种不同的输入配置来训练模型。另外，将无云天空（GSR'）中的全球太阳辐射评估为新的输入参数。在第一种情况下，NARX模型具有最佳的GSR估计性能，GPI为0.936（NARX-C1M1）。结果还表明，在情况2中GPI值为0.872（NARX-C2M1）的情况下，所有NARX人工神经网络模型都比GRNN和FFNN模型提供了更好的估计。至于情况3，NARX被认为是最佳模型（NARX-C3M1，GPI = 0.957），其次是NARX（NARX-C3M6，GPI = 0.956），然后是FFNN（FF-C3M1，GPI = 0.949）。在情况4中，与FFNN和GRNN指示的模型相比，NARX模型具有最高的GPI值（NARX-C4M1，GPI = 0.957）。对于情况5，NARX被认为是最佳网络（NARX-C5M4，GPI = 0.748），其次是NARX-C5M9（GPI = 0.549），而FFNN和GRNN模型无法提供正面结果。同样，在情况6中，NARX模型确实提供了更好的结果，最佳GPI值高达0.64。此外，在情况7中，只有NARX和FFNN模型提供了更好的估计（最佳模型，GPI = 0.826的NARX-C7M1），而GRNN模型没有给出这种可接受的结果。与上述类似，并且与FFNN和GRNN相比，我们推断出在情况8中，NARX模型与其他模型（最佳模型，GIP = 0.364的NARX-C8M4）相比，提供了更好的精度结果。在案例7中，只有NARX和FFNN模型提供了更好的估计（最佳模型，GPI = 0.826的NARX-C7M1），而GRNN模型没有给出这样的可接受结果。与上述类似，并且与FFNN和GRNN相比，我们推断出在情况8中，NARX模型与其他模型（最佳模型，GIP = 0.364的NARX-C8M4）相比，提供了更好的精度结果。在案例7中，只有NARX和FFNN模型提供了更好的估计（最佳模型，GPI = 0.826的NARX-C7M1），而GRNN模型没有给出这样的可接受结果。与上述类似，并且与FFNN和GRNN相比，我们推断出在情况8中，NARX模型与其他模型（最佳模型，GIP = 0.364的NARX-C8M4）相比，提供了更好的精度结果。