Article: Real-time logistics route planning and energy consumption simulation modelling from a green computing perspective Journal: International Journal of Simulation and Process Modelling (IJSPM) 2026 Vol.23 No.3 pp.184 - 198 Abstract: In the context of increasingly complex global supply chains and rapid e-commerce growth, the logistics industry faces significant energy and environmental challenges. A key issue is the lack of dynamic coupling between real-time traffic and vehicle energy consumption, hindering the balance of efficiency and sustainability. This paper proposes a path optimization method from a green computing perspective. We integrate real-time traffic prediction via graph neural networks with a refined energy consumption model based on vehicle dynamics. A multi-objective function considering time, energy, and cost is constructed, and an adaptive path search algorithm based on multi-objective deep reinforcement learning is designed for real-time decision-making. Experiments show our method significantly outperforms traditional approaches, achieving 89.7% recommendation accuracy and an 18.6% reduction in energy consumption, providing an effective low-carbon solution for smart logistics. Inderscience Publishers - linking academia, business and industry through research

Title: Real-time logistics route planning and energy consumption simulation modelling from a green computing perspective

Authors: Shuo Wang

Addresses: Business School, Luoyang Normal University, Luoyang, 471934, China

Abstract: In the context of increasingly complex global supply chains and rapid e-commerce growth, the logistics industry faces significant energy and environmental challenges. A key issue is the lack of dynamic coupling between real-time traffic and vehicle energy consumption, hindering the balance of efficiency and sustainability. This paper proposes a path optimization method from a green computing perspective. We integrate real-time traffic prediction via graph neural networks with a refined energy consumption model based on vehicle dynamics. A multi-objective function considering time, energy, and cost is constructed, and an adaptive path search algorithm based on multi-objective deep reinforcement learning is designed for real-time decision-making. Experiments show our method significantly outperforms traditional approaches, achieving 89.7% recommendation accuracy and an 18.6% reduction in energy consumption, providing an effective low-carbon solution for smart logistics.

Keywords: green computing; real-time path planning; energy consumption simulation modelling; deep reinforcement learning; logistics optimisation.

DOI: 10.1504/IJSPM.2026.156735

International Journal of Simulation and Process Modelling, 2026 Vol.23 No.3, pp.184 - 198

Received: 06 Feb 2026
Accepted: 04 May 2026
Published online: 01 Oct 2026 *

Title: Real-time logistics route planning and energy consumption simulation modelling from a green computing perspective

Keep up-to-date