The feasibility of a photovoltaic project depends on strategic decisions such as the location of the power plant. This article contributes to the literature by proposing a novel algorithm employing non-radial data envelopment analysis and a clustering method, including single-period and multi-period models, to select appropriate locations to establish photovoltaic sites. This algorithm evaluates the candidate locations’ efficiency to establish photovoltaic power plant considering defined sustainability criteria. Due to different results obtained from the presented models, the clustering method identifies the best locations. Iran is used to assess the performance of the proposed algorithm. The results show that six provinces are suitable locations to launch photovoltaic sites and the obtained locations are in good agreement with the photovoltaic potential for Iran. Furthermore, the results reveal that Iran has a high potential to generate photovoltaic energy. Besides, the locations identified for the establishment of photovoltaic sites are close to high electricity consumption provinces.