A Novel Data-Driven Method to Estimate Invisible Solar Power Generation: A Case Study in Taiwan

Abstract

As the penetration of photovoltaic (PV) solar generation increases, numerous residential and commercial solar PV systems without meters are being installed. The majority of these systems, however, are not monitored by power system operators. Therefore, the uncertainty of net load owing to these invisible solar power generation will raise additional challenges for power system operation. To reduce the above-mentioned impact, this work proposes a novel method to estimate the total solar power generation in a large region from a small representative subset. The proposed method is capable of capturing all relevant information that assists in the identification of representative subsets. Moreover, different optimization algorithms are utilized and evaluated to select the optimal number of clusters and representative subsets. As a case study, the power generation of 166 PV sites in Taiwan was collected and analyzed. The proposed method demonstrates a significant improvement in estimating the aggregated power generation compared to other existing studies.