An Explainable KAN–Shapley Framework for Many-to-Many Electric Vehicle Charging Dispatch in Intelligent Transportation Systems
Top Cited Papers
- 6 May 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. PP (15249050) , 1-17
Abstract
Mobile Charging Services (MCS) can alleviate the shortage of fixed charging infrastructure, but real-world dispatching in dense cities must jointly handle time-varying traffic and grid-price signals, hard feasibility constraints such as SOC safety, service time windows, and service regions, and the need for auditable decisions. Existing optimization-based schedulers rely on hand-crafted costs and provide limited decision transparency, whereas end-to-end learning-based dispatchers are often opaque and may violate constraints at inference time. This paper proposes an Explainable KAN–Shapley Dispatch Network (XKSDN) for many-to-many dispatch between EV charging request clusters and multiple Mobile Charging Vehicles (MCVs). XKSDN first abstracts massive requests via spatiotemporal–energy clustering, and then learns a structured utility function with a Kolmogorov–Arnold Network (KAN), whose edge-wise one-dimensional spline functions expose nonlinear effects such as distance decay and SOC-urgency transitions. To turn learned utilities into executable schedules, a constraint-aware matching layer integrates feasibility masking (Big- $M$ ), virtual nodes for partial matching, and node replication for limited MCV capacity, and solves the resulting assignment with an improved Hungarian algorithm. For accountability, XKSDN computes local Shapley-value attributions within clusters, quantifying the marginal contributions of distance, SOC, congestion, and price to each dispatch command. Experiments on New York City trip data with SUMO simulations show that XKSDN improves service success rate and response delay while reducing operational cost against representative optimization and deep learning baselines, and provides consistent, auditable explanations for safety-critical deployments.Keywords
Funding Information
- National Science and Technology Council
- NSTC (113-2221-E-032 -033 -MY2)
This publication has 34 references indexed in Scilit:
- System-level integration of electric transportation in smart grids: An aggregator-centric review of control architectures, optimization algorithms, and business modelseTransportation, 2025
- An integrated multi-regional cooperative strategy for real-time electric taxi dispatching and chargingControl Engineering Practice, 2025
- Planning of a multi-agent mobile robot-based adaptive charging network for enhancing power system resilience under extreme conditionsApplied Energy, 2025
- A review of machine learning approaches for electric vehicle energy consumption modelling in urban transportationRenewable Energy, 2024
- A data-driven approach to urban charging facility expansion based on bi-level optimization: A case study in a Chinese cityEnergy, 2024
- Leveraging explainable artificial intelligence in understanding public transportation usage rates for sustainable developmentOmega, 2024
- Toward efficient smart management: A review of modeling and optimization approaches in electric vehicle-transportation network-grid integrationGreen Energy and Intelligent Transportation, 2024
- Barriers and motivators to the adoption of electric vehicles: A global reviewGreen Energy and Intelligent Transportation, 2024
- Electric vehicle behavior modeling and applications in vehicle-grid integration: An overviewEnergy, 2023
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955