The invention discloses a cloud manufacturing multi-task scheduling optimization method based on a game theory. The method comprises the steps of establishing a CMMS game model based on time, cost andreliability in combination with the game theory; initializing to obtain habitats, and representing each habitat by adopting a matrix; adopting a fitness function based on Nash equilibrium to calculate the habitat suitability index of each habitat, and determining an initial optimal solution according to the habitat suitability index; selecting a habitat to execute migration operation according tothe immigration rate and the emigration rate, and updating the optimal solution; selecting a corresponding habitat to perform mutation operation according to the mutation rate, and updating the optimal solution; updating the population by adopting an elitist replacement strategy; if the number of iterations is reached, outputting an optimal solution, namely an optimal scheduling scheme; otherwise, continuing iteration. According to the method, a new cloud manufacturing multi-task scheduling game model is provided based on the game theory, a better scheduling scheme can be obtained, and the defects of premature convergence and poor population diversity of a basic BBO algorithm are overcome.