The present disclosure relates to management of virtual machines and, more specifically, using machine learning for virtual machine migration plan generation. The computer readable instructions includes determining an initial mapping of a plurality of virtual machines to a plurality of hosts as an origin state and determining a final mapping of the virtual machines to the hosts as a goal state. The virtual machine migration plan is generated based on the heuristic state transition cost of the candidate paths in combination with the heuristic goal cost of a sequence of transitions from the origin state to the goal state having a lowest total cost. One or more candidate parallel migration plans are generated based on the parallelism gates in combination with serial migrations from the virtual machine migration plan.
Aug-12-2017, 20:51:17 GMT