Automatic test resource scheduling method for power information communication equipment

Abstract

The invention discloses an automatic test resource scheduling method for electric power information communication equipment based on deep reinforcement learning A3C (Actor-Critic Algorithm). Accordingto the method, a deep reinforcement learning A3C related theory is adopted for the first time; automatic test resource requirements in communication equipment based on cloud computing are analyzed, resource scheduling time and test execution time are comprehensively considered, an A3C algorithm framework is adopted, an automatic test cloud computing resource dynamic scheduling method for electricpower information communication equipment is designed, and the utilization rate of test resources is increased.

Description

technical field [0001] The invention belongs to the field of automatic testing, and in particular relates to a resource scheduling method for automatic testing of electric power information communication equipment. Background technique [0002] With the development of smart grids, power information and communication services have continuously increased requirements on the reliability of data transmission networks. As the key node of the data network, the power information communication equipment has a direct impact on the communication quality by its functions and performance indicators, so it needs to be strictly tested before deployment. Traditional manual testing consumes huge human and material resources, and some testing tasks cannot be completed. Subsequently, the traditional automated testing technology was adopted to make up for the lack of manual testing that was too labor-intensive, but the physical testing environment needed to be built on demand during testing, ...

AI Technical Summary

Problems solved by technology

However, arranging multi-task work on a cloud computing distributed platform is an NP-hard problem. It is very time-consuming to generate the best strategy through traditional traversal-based algorithms, and the execution of the algorithm itself consumes more resources.

Images