Quantifying the climate and human-system-driven uncertainties in energy planning by using GANs

A.T.D. Perera, F. Khayatian, S. Eggimann, K. Orehounig and Saman Halgamuge

Applied Energy, 2022, vol. 328, issue C, No S030626192201426X

Abstract: Combining uncertainties of climate and energy models are challenging as they have different resolutions. The inclusion of building and transportation sectors into modelling prompted by the desire to decarbonize those sectors increases the complexity even further, as the uncertainties added by the operation of these sectors can easily amplify the uncertainties already introduced by climate change. Therefore, energy planners need to face many challenges during the design phase. This study introduced a computational platform that combines climate models (24 climate models covering representative concentration pathways [RCPs] 2.6, 4.5, and 8.5), building simulations, machine learning (i.e., generative adversarial networks [GAN]), and energy system models to mitigate these problems of modelling uncertainties during energy system optimization. This approach enables the joint consideration of climate-induced and building operation-related uncertainties, harmonizing bottom-up and machine learning techniques. The study reveals that the uncertainties brought by climate significantly influence building cooling and heating demand. Although uncertainties brought by the building operation do not influence the peak load, a significant change in the demand profile was observed during standard operation, significantly influencing the distribution of the heating and cooling demand profile. The assessment also reveals that the compound impacts brought about by climate and human systems (building operation) increases the net present value of the energy system by 28% and the levelized costs up to 12%. Neglecting these uncertainties can lead to adverse consequences, such as a loss of energy supply.

Keywords: Energy system optimization; Future climate data; Climate change; Generative adversarial networks; Machine learning (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S030626192201426X
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:328:y:2022:i:c:s030626192201426x

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2022.120169

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().