March 3, 2026Open Access

Optimization of E-commerce supply chain based on model predictive control

Key Points

Model predictive control achieved high accuracy, with MAE of 0.21 and RMSE of 0.27, under fluctuating demand conditions.
The 'rolling optimization + dynamic learning' mechanism resulted in a reduction of MAE by 28.6% and RMSE by 31.2% compared to other methods.
Adaptation to random pulse demand demonstrated the advantages of model predictive control over traditional strategies.
Understanding these optimizations could significantly enhance practices in inventory and logistics within e-commerce.

Abstract

This article proposes a model predictive control (MPC) method for complex dynamic e-commerce closed-loop supply chains, considering time delay and dual channel mixed recycling. It was found that MPC achieved high accuracy (MAE 0.21, RMSE 0.27, MAPE 1.12%) for sine function requirements with obvious fluctuation patterns, demonstrating stability and low error. In the scenario of random pulse demand, using the “rolling optimization + dynamic learning” mechanism, compared with reinforcement learning and collaborative planning prediction and replenishment methods, MAE decreased by 28.6% and 35.1%, and RMSE decreased by 31.2% and 38.7%, respectively, verifying the adaptive advantage of MPC under dynamic demand. This study elucidates how MPC optimizes inventory management, logistics scheduling, and recycling strategies in e-commerce supply chains, providing theoretical insights and practical guidance to improve operational efficiency and overall supply chain performance.

Optimization of E-commerce supply chain based on model predictive control

Key Points

Abstract

Cite This Study