计算机科学
生成语法
工具箱
忠诚
能源消耗
渲染(计算机图形)
能量转换
桥接(联网)
高效能源利用
能量(信号处理)
植绒(纹理)
人工智能
桥(图论)
骨料(复合)
机器学习
风险分析(工程)
数据聚合器
Lift(数据挖掘)
复杂系统
持续性
模拟
行为建模
系统动力学
稀缺
个人流动性
作者
Yongjian Chen,Zhi Yang,Shiqi Shawn Ou
摘要
The transition to sustainable mobility and energy systems represents a complex socio-technical challenge, with the success of new technologies and policies critically dependent on their interaction with human behavior. Traditional models frequently struggle to capture the nuanced, heterogeneous, and adaptive characteristics of individual decision-making in mobility choices and energy usage, thereby introducing significant uncertainties into system design and policy evaluation. This paper presents a novel paradigm to bridge this gap: the Hierarchical Generative Agent-based Simulation Framework (HGA-Sim). The framework's core innovations are twofold: 1) It utilizes Large Language Models to generate agents endowed with intrinsic personality traits autonomously, enabling a realistic simulation of diverse, human-like responses to environmental stimuli and personal experiences. 2) It employs a hierarchical "Archetype -Individual" architecture, rendering large-scale community simulations computationally feasible. Validated through a case study of a 495-agent community, the HGA-Sim framework accurately reproduces aggregate mobility and energy consumption patterns, including critical peak loads and temporal dynamics. It demonstrates remarkable fidelity to real-world data with a Root Mean Square Error of 0.1983. By establishing a human-in-the-loop virtual testing environment, this research provides a foundational tool for evaluating the real-world viability of sustainable mobility designs, assessing the potential socioeconomic impacts of new transportation and energy policies, and mitigating risks associated with investments in future sustainable infrastructure.
科研通智能强力驱动
Strongly Powered by AbleSci AI