With large passenger and battery capacity, electric buses can play dual roles – commuting tools in transportation networks and mobile energy storage units in power networks. To promote the beneficial synergy between power-transportation coupled networks, it is necessary to properly optimize the operation of electric buses in both networks. This paper proposes a spatial-temporal scheduling framework for the electric bus fleet in a power-transportation coupled network. By scheduling the plug-in locations and charging/discharging profiles of the electric buses, the model not only minimizes the total operational costs of the fleet (i.e., the electricity consumption and battery degradation costs), but also maximizes the revenue by providing flexibility to the power network. The coupled power and transportation constraints are explicitly described in the model. To address the uncertainty from fleet’s energy consumption, the chance-constrained programming is adopted that can be reformulated into second-order cones and efficiently solved by off-the-shelf solvers. Numerical experiments are conducted to validate the superiority of the proposed method based on the IEEE 33-bus distribution network and the Sioux Falls transportation network.