Multivariate computing power comprehensive management scheduling method and system for intelligent computing center

The invention relates to the technical field of computing power scheduling, in particular to a multivariate computing power comprehensive nano-management scheduling method and system for an intelligent computing center, and the method comprises the steps: monitoring the resource utilization condition of each computing unit based on the current resource configuration state of the intelligent computing center by adopting a support vector machine and a neural network, and recognizing idle resources in combination with a decision tree analysis method; and a genetic algorithm is used for dynamic adjustment and resource redistribution to generate a resource use efficiency analysis result and a resource redistribution plan. According to the method and the device, by combining technologies such as the support vector machine, the neural network and the decision tree, the resource utilization condition of each computing unit can be monitored in real time, and the idle resources can be identified more accurately, so tha