Development of an integrated BLSVM-MFA method for analyzing renewable power-generation potential under climate change: A case study of Xiamen

Bingqing Wang, Yongping Li, Guohe Huang, Pangpang Gao, Jing Liu and Yizhuo Wen

Applied Energy, 2023, vol. 337, issue C, No S0306261923002520

Abstract: In order to reduce fossil-energy carbon emission and mitigate its climate change impact, developing integrated mathematical methods that are capable of predicting renewable power-generation (e.g., wind and photovoltaic power) potential are desired. This study advances an integrated Bayesian least-squares-support-vector-machine based multilevel-factorial-analysis (BLSVM-MFA) method to find out the main factors affecting wind- and photovoltaic-power generations (WPG and PPG), as well as predict WPG and PPG potentials. The BLSVM-MFA method is then applied to a case study of Xiamen (China), where various factors including climate, economic, technological and capacity are investigated and 216 scenarios are analyzed. Results disclose that the main factors affecting WPG are wind power index (contributing 54.04%) > installed capacity (41.45%) > technology (2.60%), and the main factors affecting PPG are installed capacity (60.36%) > solar radiation (19.27%) > technology (9.24%). Results also reveal that WPG and PPG potentials (in 2020–2035) decrease under most scenarios and WPG and PPG show seasonal complementarity. Ensemble predictions under 216 scenarios indicate that WPG and PPG would be 130.21 WMh and 436.51 MWh by 2035. The promotion of high-conversion and high-profit technologies can improve the competitiveness of WPG and PPG in the regional power system. Results are valuable for revealing the impacts of climate change, economic development, and technological improvement on renewable power potentials and providing support for regional energy-structure transformation and carbon-emission abatement.

Keywords: Bayesian inference; Climate change mitigation; Least squares support vector machine; Multilevel factorial analysis; Potential prediction; Renewable power generation (search for similar items in EconPapers)
Date: 2023
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/S0306261923002520
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:337:y:2023:i:c:s0306261923002520

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.2023.120888

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 ().