科研速览 · Science Skim继续刷下去 · Keep skimming →
◆ Energy Reports2025-12-16· Computer science

Optimization of electric vehicle routing: A multi-criteria intelligent decision framework for efficient and scalable mobility

Anandha Prakash P., Radha R.

原始摘要(英文原文)· Original abstract
Electric vehicle adoption is seriously hindered by the short battery range, uneven distribution of charging infrastructure and inconsistent waiting time at charging stations, which cannot be met by regular navigation systems that have no multi-dimensional processing capacity. The acute necessity to have intelligent routing systems to optimize the electric vehicle pathfinding minimizing the use of energy and delay in travel encourages the in-depth research about the advanced computational methods. The hypothesis that real-time geospatial data trends used in conjunction with stochastic queuing theory and fuzzy logic can significantly enhance the efficiency of electric vehicle routing and reduce the amount of time and energy spent on travel is comprehended in this study. A six-phase model is a unified system that integrates Google Maps and OpenChargeMap data, Haversine based spherical distance calculations of graph Pruning, Poisson arrival models of demand forecasting, multi-server queue analysis of congestion forecasting, dynamic assessment of stations by fuzzy inference systems, and an improved pathfinding algorithm of multi-critera route optimization. Experimental validation in a variety of routing scenarios shows significant performance improvements: 31.5% reduction of the charging station waiting time, 6.2% reduction of energy consumption, 5.8% improvement of travel time efficiency, 28% reduction of the route deviation, 20%–33% of charging stops required compared to classical algorithms, 43% fewer charging stops are required compared to DDQN. 29% fewer charging stops compared to MPC. Computational efficiency is improved by 10.3X and 7.7X respectively. The accuracy of the routes increases by 91.7% compared to DDQN and 78.8% compared to MPC whereas memory efficiency verifies decreases of 82% and 67% accordingly. The framework is a scalable, infrastructure-conscious and computationally effective deployment of electric vehicles in the urban transit systems that is practical in complex and staged urban transportation systems, moving transportation systems to sustainability in terms of mobility.
读原文 · Read the paper ↗

AI 追问PRO

登录后使用 AI 追问

讨论区

登录后参与讨论

相关论文 · Related

Optimization of electric vehicle routing: A multi-criteria intelligent decision framework for efficient and scalable mobility — 科研速览 Science Skim