【摘要】 为探究气象因素对光伏组件积灰损失的影响，提出一种相似日聚类、麻雀搜索算法（SSA）和长短期记忆网络（LSTM）相结合的光伏组件积灰损失预测模型。首先，利用皮尔逊系数法选出主要气象因素；其次，利用K-均值算法将历史数据聚类为晴天、多云和阴雨天3种相似日样本集并分别建立预测模型；之后，利用SSA优化LSTM超参数，结果表明相较于其他模型，SSA-LSTM模型的预测效果最佳。最后，提出模型组合预测法，结果表明该方法具有预测精度高、泛化能力强的特点，可为光伏组件积灰损失预测研究提供参考。更多还原

【Abstract】 In order to explore the influence of meteorological factors on the dust deposition loss of photovoltaic modules, a prediction model combining similar day clustering, sparrow search algorithm(SSA) and long short-term memory(LSTM) is proposed. Firstly, the main meteorological factors are selected by the Pearson coefficient method. Secondly, the historical data is clustered into three similar day sample sets of sunny, cloudy and rainy days by using the K-means algorithm and prediction models are established respectively. Finally, the LSTM hyperparameters are optimized by SSA. The results show that compared with other models, the SSA-LSTM model has the best prediction effect. And the, a model combination prediction method is proposed. The results show that this method has the characteristics of high prediction accuracy and strong generalization ability, which can provide a reference for the prediction of photovoltaic module dust deposition loss.更多还原