Systems and methods described herein provide an intelligent MEC resource scheduling service. A network device in a MEC network stores, in a memory, threshold values indicating overload conditions for resource usage by a first MEC cluster; monitors resource usage in the first MEC cluster; determines, based on the monitoring, when one of the threshold values is reached; identifies available resources in a second MEC cluster; and re-directs, based on the identifying, at least some of the resource usage from the first MEC cluster to the second MEC cluster.