A Study on the Prediction of Program Complexity Section for Offloading Execution Decision
Jae‐Hyun Kim, Yang Sun Lee · International Journal of Control and Automation · 2019
The IoT-Cloud fusion virtual machine system is a platform for lowperformance IoT(Internet of Things) devices, and uses offloading technology, one of the cloud computing technologies that delegate tasks requiring high-performance computing power to the cloud server.Although the offloading technique has solved the problem that the performance of the virtual machine is dependent on the performance of the IoT device being operated, there is a network cost due to the communication between the cloud and the local device.Therefore, depending on the program complexity, the offloading performance may be lower than the performance of the local device.In this paper, we predicted a program area complexity based on deep learning to solve this problem.The program complexity area prediction predicts the execution complexity of the program by learning the program complexity estimate and actual execution complexity analyzed by the static profiler.Since the complexity area can be used as an index for determining the offloading execution, the offloading can be performed only when the offloading performance is advantageous, and efficient offloading can be performed.