A Hierarchical Stochastic Model Predictive Control Framework for Integrated Request-aware Charge Scheduling and Service Allocation

Coordinated Scheduling of Distribution Network and Transportation System for EVs with Aggregated Flexibility and Endogenous Dynamic Pricing

With the large-scale integration of Electric Vehicles (EVs) into distribution systems, the spatiotemporal uncertainty of charging loads and the interplay between user charging behavior and network operational constraints present new challenges to the safe and economical operation of the power system. To address the insufficient coordination among flexibility characterization, distributed optimization, and user-side responses, this paper proposes a closed-loop collaborative dispatch strategy. The strategy integrates flexibility aggregation, endogenous dynamic pricing, and user charging-station selection behavior. Firstly, a three-tier collaborative architecture comprising the Distribution System Operator (DSO), Electric Vehicle Aggregators (EVAs), and EV users is established, with rolling updates implemented using Model Predictive Control (MPC). A flexible aggregation model is developed based on set operations of vehicle-level constraints, dynamically calculating power boundaries and energy feasibility domains. Furthermore, a distributed coordinated optimization model between the DSO and multiple EVAs is established and solved via the Alternating Direction Method of Multipliers (ADMM) under privacy-preserving conditions. By analyzing the correlation between ADMM dual variables and the marginal value of network constraints, a Distribution Locational Marginal Pricing (DLMP) -inspired dynamic price signal—endogenous to the optimization—is constructed to guide spatial reallocation of charging loads. Joint simulations based on an IEEE 33-node distribution network and the Sioux Falls transport network demonstrate that the proposed strategy reduces 24 h network losses from 9.05 MWh (uncoordinated) to 8.41 MWh, lowers user total costs from 22,200 yuan to 7100 yuan, and eliminates voltage limit violations (duration reduced from 1.50 h to 0), while exhibiting good distributed solution performance and closed-loop control capability.

Coordinated Optimization of Orderly Charging and Grid Interaction at Electric Vehicle Charging Stations Based on Multi-Agent Reinforcement Learning

A collaborative optimization framework based on multi-agent reinforcement learning is proposed for orderly charging at electric vehicle charging stations and coordinated interaction with the power grid, providing a technical reference for intelligent charging coordination under grid interaction and electromagnetic compatibility constraints.

Correlation-Aware Dynamic-Price-Feedback Ordered Charging for Vehicle–Grid Coordination

: Random vehicle arrivals, heterogeneous charging demands, and the station-level limit on aggregate electric vehicle (EV) charging power pose simultaneous challenges to event-driven ordered charging in terms of causal information constraints, charging economics, and aggregate-load coordination. Existing full-information multiobjective methods generally rely on the complete daily EV set and iterative solution procedures, whereas fixed time-of-use pricing or single-objective load-smoothing strategies cannot continuously adapt to vehicle arrival events. Moreover, preserving only the marginal distributions of charging-behavior variables may neglect their joint dependence, thereby affecting consistency between scenario generation and scheduling evaluation. To address these issues, this paper proposes Correlation-Aware Dynamic-Price-Feedback Ordered Charging for Vehicle–Grid Coordination (CDPFOC). CDPFOC uses a Gaussian Copula to generate representative scenarios that preserve the joint dependence structure of charging behaviors. It forms event-level economic feedback through a Dynamic Feedback Module (DFM), implements load balancing through an Adaptive Load-Envelope Module (ALM), and updates only the unexecuted future charging plans of vehicles that have arrived and remain online. Monte Carlo experiments in four representative scenarios show that, under a unified real-time dynamic settlement price and a 9 MW station-level EV aggregate charging-power hard limit, CDPFOC records either the lowest dynamic settlement cost or a tie for the lowest in all scenarios. Relative to uncontrolled charging, it reduces the dynamic settlement cost by 0.36%–18.68% and the peak-to-valley difference (PV) by 1.73%–17.55%, while attaining a 100.00% schedulable energy delivery rate and zero station-level capacity violations. Ablation results further indicate that the DFM primarily provides economic guidance, whereas the ALM primarily suppresses charging-power concentration; together, they coordinate charging economics and load smoothing without using individual information from vehicles that have not yet arrived.

A Stochastic Dual Dynamic Programming Approach for Fixed-Route Electric Vehicle Charging under Congestion Uncertainty

Deploying heavy-duty electric trucks under real-world uncertainty is operationally challenging, particularly when multiple vehicles compete for limited public charging resources and face uncertain wait times. This research studies the Fixed-Route Vehicle Charging Problem and formulates it as a multistage stochastic program under charging congestion uncertainty. The delivery system is modeled as a discrete-event process triggered by physical route milestones, and charging congestion uncertainty is represented by a Markovian transition. To address the resulting mixed-integer structure, we apply stochastic dual dynamic programming (SDDP) as a tactical planning approach, while accommodating discrete vehicle dynamics within the convexity requirements. Computational experiments on a California logistics network showed that the proposed approach performed effectively across multiple geographically diverse delivery routes. Compared to a multistage stochastic integer programming benchmark, SDDP achieved a competitive solution quality while reducing training time as the number of route instances increased. Out-of-sample simulations further demonstrated that policies derived from SDDP remained robust under distributional shifts toward more congested scenarios. Overall, this study establishes SDDP as a tractable and scalable framework for generating high-quality operational policies for heavy-duty electric fleets under congestion uncertainty.

Dynamic Programming-Based Non-Anticipative Approach for Multi-Stage Coordinated Optimal Dispatch of Electricity and Transportation Nexus

Application of Multi-objective Differential Evolution Algorithm in Electric Vehicle Charging and Discharging Coordination Strategy

Experimental results demonstrate that the proposed MODE approach achieves a grid load standard deviation of 6.95 and a peak-to-valley ratio of 1.63 while maintaining an average battery depth of discharge and a user satisfaction level of 0.92 for commuting scenarios.