Hybrid cloud task scheduling method based on improved simulated annealing algorithm

The invention provides a hybrid cloud task scheduling method based on an improved simulated annealing algorithm. The hybrid cloud task scheduling method comprises the following steps: step 1, independently dividing and recording virtual machines of public cloud and private cloud resource pools in a hybrid cloud and tasks running in the virtual machines; 2, CPU, GPU, content and network information of the virtual machines are followed up respectively, and expected task execution time in the single virtual machine is calculated; 3, constructing a main objective function of a simulated annealing algorithm according to the total task expected execution time of the virtual machine; and step 4, calculating the average resource load condition of the hybrid cloud resource pool, and adding a random forest algorithm to obtain respective weight coefficients of the public cloud and the private cloud. According to the method, the acceptance probability formula of the simulated annealing algorithm is improved, the improved