An Energy-efficient Computation Offloading Approach based on Optimization Theory for Cyber Foraging in Mobile Clouds

[[abstract]]運算委派為雲端運算裡重要的課題,以目前網路無所不在的連接,行動裝置可利 用此一趨勢將運算委派至資源豐富的資料中心裡運算並獲得最後結果,從中也為電源受限的行動裝置節省部分電力。然而,傳統的運算委派方法多假設行動裝置 具有連網能力。因此,本論文提出一混合式運算委派方法為低階行動裝置將運算量較複雜且龐大的程式將運算傳送到周遭運算能力較強或具有閒置資源的裝置協 助運算。此一方法可依據各行動裝置的運算、電源、網路頻寬及裝置與路由器的 距離來選擇是否需要委派運算至資料中心以達到最佳化能源效益之目的。根據模 擬試驗的結果,混合式運算委派在不同的環境下提昇 7%至 61%的能源效益。 Computation offloading is a hot topic to minimize the energy consumption in cloud- assisted mobile computing. However, the assumption is that the mobile devices must have network connectivity to cloud. In this thesis, we propose an ad hoc computation offloading approach, which allows that the resource-poor mobile devices could offload its computation to nearby devices that have idle resources. Because there are different computation-offloading scenarios, the total energy consumption is influenced by the factors, such as the energy-efficiency of computation and communication of these devices and the transmission distances among these devices. Therefore, the approach is proposed to solve the optimization problem with objective of minimizing the total energy consumption under such ad hoc computation offloading. According to the simulation results, it shows that our method could improve the energy efficiency from 7% to 61% in different simulation cases