An Agent-Based Digital Twin for Energy Management in Ski Resorts: Integrating Skier Behavior Modeling with Lift Energy Consumption Optimization
Abstract
Ski resorts face mounting pressure to reduce energy consumption while maintaining skier satisfaction, with energy costs repre- senting up to 69% of operational expenses. This paper presents a novel agent-based digital twin framework that integrates human behavior modeling with energy consumption analysis to address this critical challenge. The framework uniquely combines: (1) a validated physics-based energy model for ski-lifts achieving less than 12% mean error on real operational data, (2) an agent- based simulation of individual skier decision-making that captures heterogeneous preferences, skill levels, and dynamic responses to queue conditions, and (3) a graph-based representation of resort infrastructure enabling scalable scenario analysis. The system is validated using real ski-pass data from a major European resort, demonstrating accurate reproduction of skier flows and lift occupancy patterns. Through multi-objective analysis, we demonstrate the trade-offs between energy consumption and skier satis- faction under different operational strategies, revealing that adaptive speed control can reduce energy by up to 40% on low-traffic days with minimal impact on satisfaction. This work contributes to the growing field of digital twins for sustainable infrastructure management, providing a validated methodology that bridges human behavior modeling, energy systems analysis, and operational optimization. The framework enables resort managers to evaluate energy-saving strategies and infrastructure modifications with- out costly physical experimentation, with broader applicability to other energy-intensive service systems with human-in-the-loop dynamics.
Related
- Integrating adaptive human behavior into epidemic models with large language models
- A novel deep learning prediction method for PM2.5 integrating improved MSTL decomposition and FATA optimization algorithm
- A model of grain growth in UN integrating molecular dynamics, phase-field modeling, and uncertainty quantification
- Multiscale modeling of thermo-hydromechanical behavior of clayey rocks and application to geological disposal of radioactive waste
- An LLM-powered Agent Framework for Heterogeneous Evacuation Behavior Modeling under a Moving Threat in a Public Plaza
BibTeX
@article{simoiu2026agentbased,
title = {{An Agent-Based Digital Twin for Energy Management in Ski Resorts: Integrating Skier Behavior Modeling with Lift Energy Consumption Optimization}},
author = {Mircea Simoiu and Stéphane Ploix and Fateh Boulmaiz and Siao-Leu Phouratsamay},
journal = {Energy Conversion and Management: X},
year = {2026},
month = jul,
url = {https://hal.science/hal-05793209v1},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - An Agent-Based Digital Twin for Energy Management in Ski Resorts: Integrating Skier Behavior Modeling with Lift Energy Consumption Optimization
AU - Mircea Simoiu
AU - Stéphane Ploix
AU - Fateh Boulmaiz
AU - Siao-Leu Phouratsamay
PY - 2026
DA - 2026/07/11
JO - Energy Conversion and Management: X
UR - https://hal.science/hal-05793209v1
AB - Ski resorts face mounting pressure to reduce energy consumption while maintaining skier satisfaction, with energy costs repre- senting up to 69% of operational expenses. This paper presents a novel agent-based digital twin framework that integrates human behavior modeling with energy consumption analysis to address this critical challenge. The framework uniquely combines: (1) a validated physics-based energy model for ski-lifts achieving less than 12% mean error on real operational data, (2) an agent- based simulation of individual skier decision-making that captures heterogeneous preferences, skill levels, and dynamic responses to queue conditions, and (3) a graph-based representation of resort infrastructure enabling scalable scenario analysis. The system is validated using real ski-pass data from a major European resort, demonstrating accurate reproduction of skier flows and lift occupancy patterns. Through multi-objective analysis, we demonstrate the trade-offs between energy consumption and skier satis- faction under different operational strategies, revealing that adaptive speed control can reduce energy by up to 40% on low-traffic days with minimal impact on satisfaction. This work contributes to the growing field of digital twins for sustainable infrastructure management, providing a validated methodology that bridges human behavior modeling, energy systems analysis, and operational optimization. The framework enables resort managers to evaluate energy-saving strategies and infrastructure modifications with- out costly physical experimentation, with broader applicability to other energy-intensive service systems with human-in-the-loop dynamics.
SN - 2590-1745
ER -