Off-line task hybrid deployment method and device

The invention relates to the technical field of cloud computing, and provides an offline task hybrid deployment method and device, and the method comprises the steps: predicting an expected resource quota of a target online task at a next moment through a resource quota prediction model obtained through the training of a reinforcement learning method; adjusting the actual resource quota of the target online task in the target server at the next moment according to the actual resource quota, comparing the total resource allocation amount of all tasks in the target server with the resource allocation limitation of the target server to obtain a comparison result, and performing offline task arrangement according to the comparison result. On the premise that the task execution effect is guaranteed, online and offline tasks are deployed on the same server in a mixed mode, and the resource utilization rate of the server is increased. 本申请涉及云计算技术领域，提供了一种在离线任务混合部署方法与设备，该在离线任务混合部署方法利用通过强化学习方法训练得到的资源配额预测模型预测目标在线任务在下一时刻的