A Distributionally Robust Bi-Level Multi-Objective Decision Making Method Under Hybrid Uncertainty

This paper introduces a novel bi-level multi-objective optimization framework designed for decision-making under hybrid uncertainty, where system constraints account for both intuitionistic fuzzy sets and stochastic uncertainties. By combining interval programming and chance-constrained optimization...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE access Ročník 13; s. 155399 - 155410
Hlavní autori: Wang, Xindi, Ma, Jing, Qin, Yong
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Piscataway IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
bi-level decision making
chance constraint
convex optimization
Decision making
Decision support systems
Fuzzy sets
Fuzzy-stochastic hybrid programming
Indexes
Multiple objective analysis
Optimization
Probabilistic logic
Probability distribution
Programming
Random variables
Robustness (mathematics)
Stochastic processes
Uncertainty
Water resources
ISSN:2169-3536, 2169-3536
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This paper introduces a novel bi-level multi-objective optimization framework designed for decision-making under hybrid uncertainty, where system constraints account for both intuitionistic fuzzy sets and stochastic uncertainties. By combining interval programming and chance-constrained optimization, the proposed method relaxes the commonly adopted assumption of Gaussian distributions for stochastic uncertainties, thereby making it applicable to a wider range of distributional forms, including non-Gaussian scenarios. To effectively handle the interplay between fuzziness and stochasticity, we propose an acceptability index that quantifies uncertainty propagation, ensuring robust solutions that balance both sources of uncertainty. The approach provides a computationally efficient and theoretically sound decision-support tool for complex bi-level optimization problems. Numerical case studies demonstrate its ability to generate high-confidence solutions while offering flexibility in preference modeling.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2025.3605948