An Optimization-Guided Prediction-Free Two-Stage Real-Time Energy Management Strategy for Novel Co-Phase Traction Power Supply System With PV and Energy Storage

To overcome the challenge of large compensation capacity requirements in distributed continuous co-phase traction power supply system (TPSS), a novel co-phase TPSS (NCTPSS) is proposed. This system simultaneously tackles the problems of three-phase voltage unbalance and neutral sections commonly found in conventional electrified railways, while also providing interfaces for the integration of distributed renewable energy sources. When NCTPSS is integrated with photovoltaics (PV) and energy storage (ES), it enables the effective utilization of both regenerative braking energy (RBE) and renewable energy. However, due to the uncertainties associated with traction load (TL) and photovoltaics (PV), conventional prediction-optimization-based frameworks for real-time energy management strategy (EMS) face challenges such as high computational complexity and modeling difficulties. To address these issues, this paper proposes an optimization-guided prediction-free two-stage real-time EMS, consisting of an offline stage and a real-time stage. In the offline stage, an optimized dispatch library is generated based on historical TL and PV data to provide reference guidance and avoid myopic decision-making. In the real-time stage, a coordinated control strategy that combined optimization-guided EMS and rule-based EMS is proposed to ensure effective dispatch under various load scenarios. Finally, simulations and hardware-in-the-loop experiments are conducted to validate the performance of the proposed NCTPSS and EMS.