Abstract
The quality of decisions in the renewable energy sector is as good as the quality of available data. This makes data quality a cornerstone in renewable energy system planning, designing, operation, and assessment. Unfortunately, such data is not always available and usually is cost-prohibitive. One solution for this issue is using the data of few representative days (RDs) instead of the full year for reduced costs of the data itself and the system simulations. A new framework is proposed in this study to distinguish these RDs based on meteorological features. The new framework represents an end-to-end pipeline, starting with measurements, data curing, feature extraction, clustering, and representative year construction. The analysis showed that increasing the number of RDs indeed improves the representativeness of the reconstructed year with disagreement indices as low as 1.041. Including system-irrelevant meteorological parameters was found to increase the disagreement index between original data and reconstructed year from 0.206 to 0.989. The proposed autoencoder feature extraction approach outperformed the conventional statistical one, especially for shallow autoencoders, where the disagreement index was reduced from 1.564 to 1.001. Finally, a brief case study of a standard solar water heating system was performed using TRNSYS v18 software to verify the proposed approach, where the absolute percentage deviation in the annual solar fraction was found to be only 0.278%. This study takes the first steps towards offering decision-makers, designers, and modelers a framework that provides high-quality and high-resolution data compatible with the elevating measurements and simulation cost.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have