To avoid possible conflicts between the maintenance scheduling and the unit commitment for hydro-thermal power systems under the traditional non-collaborative optimization mode,a collaborative maintenance scheduling and unit commitment model for hydro-thermal systems is proposed,in which the total cost of the system and the adjustment cost of maintenance scheduling as an objective are minimized with considering the coupling characteristics of cascade hydropower. Furthermore,the model is transformed into a mixed integer linear programming (MILP) model. To improve the solution of the MILP model,the objective scaling ensemble approach is proposed,including two stages. In the first stage,the coefficients of integer variables in the objective are scaled and the integer variables that may take 0 are probed. In the second stage,the reduced MILP model is solved after determining and fixing the integer variables with a value of 0. Finally,a 6-unit hydro-thermal power system and an actual provincial 86-unit hydro-thermal power system are taken as test systems. The results show that the proposed model can obtain a more economical and reasonable maintenance scheduling and unit commitment scheme compared with the non-collaborative optimization mode,thus effectively improving the solution speed by the objective scaling ensemble approach.