Deep-Learning-Based Adaptive Model for Solar Forecasting Using Clustering

Accurate short-term solar forecasting is challenging due to weather uncertainties associated with cloud movements. Typically, a solar station comprises a single prediction model irrespective of time and cloud condition, which often results in suboptimal performance. In the proposed model, different categories of cloud movement are discovered using K-medoid clustering. To ensure broader variation in cloud movements, neighboring stations were also used that were selected using a dynamic time warping (DTW)-based similarity score. Next, cluster-specific models were constructed. At the prediction time, the current weather condition is first matched with the different weather groups found through clustering, and a cluster-specific model is subsequently chosen. As a result, multiple models are dynamically used for a particular day and solar station, which improves performance over a single site-specific model. The proposed model achieved 19.74% and 59% less normalized root mean square error (NRMSE) and mean rank compared to the benchmarks, respectively, and was validated for nine solar stations across two regions and three climatic zones of India.

Automated summary

Accurate short-term solar forecasting is challenging due to weather uncertainties associated with cloud movements. This study proposes a method that improves prediction performance by clustering and dynamically selecting models. The validation results from nine solar stations across two regions and three climatic zones in India show that the proposed model achieves lower normalized root mean square error and mean rank compared to benchmark models.