Adaptive optimization scheduling method for mobile terminal software based on deep reinforcement learning

Abstract

The invention relates to an adaptive optimization scheduling method for mobile terminal software based on deep reinforcement learning, which relates to a computing technology. The method comprises thesteps of: automatically optimizing the number of software processes unloaded on the mobile device, prioritizing the local task processes, and allocating CPU computing resources and memory resources to reduce the energy consumption of the mobile device and reduce the task processing delay. By measuring the scale of the real-time threading tasks of the software on the mobile device, the bandwidth of the dynamic wireless link between the mobile device and the edge device is estimated, and the feedback information such as the time delay and the energy loss of each process is evaluated by using the depth reinforcement learning algorithm, so as to obtain the optimized scheduling scheme of the software. There is no need to predict the wireless channel model from mobile device to edge device andthe CPU computing resource and memory resource occupancy model of mobile device system, which can reduce the processing delay and energy consumption of software tasks on mobile device and improve theuser experience.

Description

technical field [0001] The invention relates to computing technology, in particular to a mobile terminal software adaptive optimization scheduling method based on deep reinforcement learning. Background technique [0002] With the development and innovation of various application software, mobile devices such as smart phones need to handle larger and larger computing tasks, and the computing power requirements for mobile device CPUs are getting higher and higher. Poor CPU performance or unreasonable calculation order of mobile devices will lead to unsmooth operation of application software, such as game freezes, etc., affecting user experience. Coordinating task processes through system-level optimization schemes under fixed and mobile device hardware conditions is of great significance for reducing task processing delays and improving user experience. [0003] In this regard, A.S.Wu et al. (A.S.Wu, H.Yu, S.Jin, et al, "An incremental geneticgorithm approach to multiprocess...

AI Technical Summary

Problems solved by technology

However, mobile devices usually must be connected to the edge computing network through a wireless network. The instability of the wireless channel has a great impact on the effect of the edge computing network. When the communication channel quality is poor, the mobile device takes longer to unload, even exceeding Edge computing reduces computing delay, and at the same time, unloading data adds additional antenna transmission power loss to mobile devices