SC-OPTIM: A Stochastic Constrained Optimization Framework for Energy-Efficient Model Selection in AI-Supply Chains

Authors:
  • YLYunting Lin
    Yunting Lin
  • JGJiayi Gu
    Jiayi Gu
  • JLJing Luo
    Jing Luo
  • ZNZiyi Ni
    Ziyi Ni
  • YZYichao Zhang
    Yichao Zhang
  • JSJunhao Song
    Junhao Song
  • ZYZhenyu Yu
    Zhenyu Yu
  • RBRiyang Bao
    Riyang Bao
  • XSXinyuan Song
    Xinyuan Song
  • ZHZhimo Han
    Zhimo Han
Preprint
Publisher website
Google Scholar
Abstract
The orchestration of heterogeneous AI models is critical for intelligent supply chain decisionmaking, yet existing LLM-based orchestrators rely on qualitative heuristics or popularity signals, ignoring fundamental trade-offs between operational performance and multidimensional resource costs such as energy, latency, and carbon footprint. We propose SC-OPTIM, an energy-aware, data-driven inference framework that formulates model selection as a constrained optimization problem. SC-OPTIM integrates a Constrained Markov Decision Process with an online Adaptive Efficiency Frontier learned via Gaussian Process Regression, and solves a chance-constrained Mixed-Integer Quadratic Program to balance cost, lead time, service level, and resource constraints under uncertainty. Experiments on real-world supply chain tasks demonstrate that SC-OPTIM consistently improves decision accuracy across tasks, substantially increases accuracy-per-joule efficiency, reduces orchestration latency from seconds to milliseconds, and significantly lowers inference-related energy consumption, enabling efficient, scalable, and sustainable AI-driven supply chain optimization.