Abstract: The co-phase traction power supply system of electrified railways can effectively address power quality problems dominated by negative sequence and phase separation issues in traditional traction power supply systems. It also provides a flexible interface for the integration of photovoltaics, energy storage systems, and electric vehicles. However, the system faces multiple uncertainties from photovoltaic output, electric vehicles, and traction loads, which brings new challenges to the optimal operation of the system. Based on this, this paper proposes a distributed collaborative optimal scheduling model considering system uncertainties. Firstly, aiming to minimize the daily operation cost of the traction power supply system, and considering constraints such as system power balance and energy storage operation, a multi-scenario stochastic programming approach is adopted to handle the uncertainties of photovoltaic output, traction loads, and electric vehicles. Secondly, the alternating direction method of multipliers is introduced to decouple the centralized problem into sub-problems for each substation, achieving a distributed and efficient solution for the system. Case studies show that the system effectively mitigates grid power fluctuations, and the comprehensive daily operation cost is reduced by 23.06%, which verifies the effectiveness of the proposed method in improving the economic efficiency and robustness of the system.