In this section
@article{Tan:2026:2516-1083/ae5584,
author = {Tan, J and He, Y and Xiao, N and Zhang, F and Wang, F and Xu, J and Xie, S and Jing, R and Lin, J and Meng, C and Brandon, N and Shah, N and Zhao, Y},
doi = {2516-1083/ae5584},
journal = {Progress in Energy},
title = {A climate-driven generative scenario framework for optimizing integrated energy systems with hybrid storage solutions},
url = {http://dx.doi.org/10.1088/2516-1083/ae5584},
volume = {8},
year = {2026}
}
TY - JOUR
AB - As renewable energy sources (RESs), particularly wind and solar, become increasingly integral to the urban energy mix, optimizing integrated energy systems (IES) is essential to ensuring sustainability and resilience. The inherent variability and intermittency of RES pose significant challenges for urban energy planning, demanding robust methods to simulate local climate patterns and support reliable energy storage strategies. This study presents a climate-responsive generative model Wasserstein generative adversarial network with gradient penalty-MD based on adversarial learning to produce high-fidelity wind and solar generation scenarios. Embedded within a Monte Carlo-based decomposition optimization framework, the model balances stochastic fidelity and computational tractability for large-scale IES planning. A case study conducted in a high-RES potential region demonstrates the model’s effectiveness in supporting informed system design and operational strategies. By introducing a novel quantitative metric, results reveal the complementary roles of battery energy storage systems and hydrogen storage in addressing short-term variability and long-term balancing needs. Notably, annual renewable generation can deviate by over 40.5% under extreme climate conditions, highlighting the necessity of hybrid storage strategies. The proposed approach enhances system reliability and economic viability under diverse climate scenarios. Key contributions include: (1) the development of a climate-informed generative model for RES scenarios, (2) its integration into an computationally efficient Monte Carlo-based optimization framework for IES, and (3) a hybrid storage strategy that reinforces the resilience and sustainability of urban energy systems. These findings offer practical insights for advancing low-carbon, climate-adaptive urban infrastructure in the transition toward sustainable cities.
AU - Tan,J
AU - He,Y
AU - Xiao,N
AU - Zhang,F
AU - Wang,F
AU - Xu,J
AU - Xie,S
AU - Jing,R
AU - Lin,J
AU - Meng,C
AU - Brandon,N
AU - Shah,N
AU - Zhao,Y
DO - 2516-1083/ae5584
PY - 2026///
TI - A climate-driven generative scenario framework for optimizing integrated energy systems with hybrid storage solutions
T2 - Progress in Energy
UR - http://dx.doi.org/10.1088/2516-1083/ae5584
VL - 8
ER -