Optimizing wireless dynamic charging infrastructure for electric vehicles: A predictive and adaptive framework leveraging decision-dependent uncertainties and renewable energy utilization

The rapid adoption of electric vehicles (EVs) is transforming modern transportation systems while presenting challenges related to charging infrastructure, grid integration, and renewable energy utilization. This paper proposes a novel multi-stage distributionally robust optimization (DRO) framework tailored for wireless dynamic charging lanes, addressing critical challenges such as traffic density fluctuations, renewable energy variability, and grid capacity constraints. By leveraging predictive analytics and decision-dependent uncertainty modeling, the proposed framework dynamically optimizes lane deployment, energy resource allocation, and operational strategies. The mathematical modeling captures multi-objective optimization goals, including cost minimization, renewable energy integration, carbon emission reduction, and system resilience under uncertainties. Predictive models for traffic flow and renewable energy availability are integrated with a primal–dual algorithm to ensure computational scalability. The framework also incorporates gamification-inspired user engagement metrics to align EV user behavior with system objectives, enhancing efficiency and user satisfaction. A comprehensive case study is conducted on a hypothetical urban highway network spanning 50 km, featuring 10 candidate lane locations and diverse energy resources, including solar, wind, and grid energy. Results demonstrate the framework’s ability to achieve up to 30% cost savings, 25% carbon emission reductions, and a 20% increase in renewable energy utilization, compared to traditional static charging strategies. The findings emphasize the importance of synchronized traffic and energy system optimization in enhancing the sustainability and efficiency of EV charging infrastructure. This study provides a robust, adaptive framework for designing and operating wireless dynamic charging systems, offering valuable insights for policymakers, researchers, and practitioners in advancing EV adoption and achieving sustainable mobility goals. The proposed framework paves the way for future innovations in integrating renewable energy and smart mobility systems under dynamic and uncertain conditions. • Proposed a multi-stage distributionally robust optimization framework for wireless dynamic charging lanes. • Integrated predictive analytics to optimize lane deployment, energy allocation, and operational strategies in real-time. • Introduced a gamification-inspired user engagement mechanism.