With the rapid development of electrified railroads

the issues related to power consumption and carbon emissions are becoming increasingly severe. Integrating photovoltaic and energy storage devices into the traction power supply system and recycling the regenerative braking energy of trains is an effective measure to save energy and reduce consumption. However

the uncertainty of regenerative braking energy poses severe challenges to the energy scheduling of the traction power supply system. This paper addresses the uncertainty of train regenerative braking energy by developing an accurate probabilistic model based on measured regenerative braking data. A typical scenario of train regenerative braking is then generated and reduced. The optimization goal is to minimize the daily operating cost of the traction power supply system connected by photovoltaic and energy storage and to minimize the interaction between the system and the external power grid. Stochastic scenario constraints are formulated to ensure that the system operates safely and stably. A stochastic optimal scheduling model is constructed

and a multi-objective particle swarm optimization algorithm is used to solve the model. The results show that

compared to the method of recycling photovoltaic energy and train regenerative braking through a hybrid energy storage system

the proposed approach reduces the daily operating cost of the system by 1.82% and the interaction power with the external grid by 18.74%.