Answers are grounded in this paper and cite their sources.
Charge-route planning (CRP) optimizes the route with charging schedules for electric vehicles (EVs) in order to minimize time and expense, thereby enhancing the overall user experience, especially considering the prolonged charging durations of EVs. Efficiently solving CRP is challenging due to dynamic traffic conditions and complex constraints associated with EV driving and charging. To address this challenge, we propose data-driven traffic-aware ant colony optimization (DDTA-ACO), a framework that tightly integrates predictive and reactive strategies for superior charge-route optimization. First, we propose a high-fidelity, data-driven charge-route time estimation (CRTE) model to accurately predict travel times under dynamic conditions. Then, we design a synergistic search mechanism based on 2 complementary operators: repair-and-proactive avoidance (RPA) and elite adaptive search (EAS). RPA proactively avoids unpromising regions, while EAS intensifies the search in elite regions. Together, they learn from failures and successes to efficiently explore the complex search space. Experiments conducted on 2 real-world datasets demonstrate that DDTA-ACO outperforms state-of-the-art algorithms, showcasing its superior effectiveness for practical, large-scale CRP problems.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: