A SOC service quality assurance system and method based on actor-critic deep reinforcement learning

Abstract

The invention discloses a SOC service quality assurance system based on Actor-Critic deep reinforcement learning, including a user task generator, multiple resource pools, multiple resource pool task optimal allocation modules, a business task scheduler, and a business load evaluation module , QoE evaluation module; input the task list of all users, resource pool occupancy, each user's business load and the current idle resource pool number, use QoE as the feedback basis for effect evaluation, run the Actor-Critic deep reinforcement learning algorithm, and get the following The allocation plan of the tasks to be executed by the user on the resource pool at one moment; according to the task allocation plan, the task scheduling is completed through the task scheduling interface of the SOC platform, and the corresponding resources are assigned to execute the specific tasks of the specific users. The tasks listed in the task list of all users Find an optimal resource allocation scheme, arrange the user's tasks in the optimal order to complete the service to the resources in the resource pool, and maximize the user's subjective quality experience QoE.

Description

technical field [0001] The invention relates to the technical field of electrical digital data processing, in particular to an SOC service quality assurance system and method based on Actor-Critic deep reinforcement learning. Background technique [0002] Security Operations Center (SOC) provides users with security services through cloud security resources, reduces the cost of security services through a large group model, and makes security services easy to obtain. The advantages of this cloud service model are reflected in the effective scheduling of cloud shared service resources. For users, cloud resources are statistically shared, so the available service quality cannot be completely determined, but in a certain fluctuate within the range. Therefore, for the SOC security operation mode, how to provide users with a pre-agreed service quality (SLA, Service Level Agreement) under the limitation of limited cloud resources has become one of the key technologies. [0003] ...

AI Technical Summary

Problems solved by technology

[0007] 2. Users are grouped according to the quality of service (QoS), and the cloud platform also reserves and schedules resources according to the objective indicators of service quality QoS, such as service response time and service completion time. Although these objective QoS indicators are different from user It is related to the subjective feelings of QoS, but there are still differences, and this difference will further amplify the waste of resources caused by scheduling resources based on purely objective QoS indicators

[0012] Finally, the existing algorithms directly use the collected objective indicators as the optimization target, which cannot reflect the subjective feelings of users on service quality.

Images