Author

Haifeng Li

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access 2026

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.

Li-Xiao Wang, Jia-Qi Li, Hai-Feng Li et al. · Energy Engineering · 0 citations

Open access Jul 2026

Intelligent power flow control of AC/DC hybrid transmission corridors using safe reinforcement learning agents.

As renewable generation progressively displaces conventional generators, power flow through geographically constrained transmission corridors increasingly approaches or violates thermal and stability limits, exposing the grid to congestion-induced renewable curtailment and cascading-failure risks. Traditional real-time dispatch practices, which rely on precomputed look-up tables and operator heuristics, prove inadequate when faced with rapidly growing uncertainties arising from high penetrations of wind and photovoltaic generation. This paper presents a safe reinforcement learning (SRL)-driven coordinated control framework that simultaneously regulates embedded HVDC links and dispatchable generators to enhance the transfer capability of AC/DC hybrid transmission corridors. A perturbation-based sensitivity approach distills the generator fleet into a compact subset whose output variations most strongly affect the transmission corridor power flow, effectively compressing the decision dimensionality. The sequential decision task is formulated as a Markov Decision Process model, where SRL agents are trained to govern HVDC flow and generator redispatch, under a maximum-entropy actor-critic framework, yielding policies that are simultaneously exploratory, reward-seeking, and constraint-respecting. Extensive simulation experiments and commissioning on the Yangtze River-crossing transmission corridor confirm that the SRL agent's policies elevate the mean aggregate transfer by 629 MW and raise the delivery ceiling by 807 MW, peaking at 2761 MW in heavily stressed scenarios.

Haifeng Li, Zhiwei Wang, Tao Jin et al. · Scientific Reports · 0 citations