Аңдатпа
Energy efficiency is one of the most critical aspects of the modern computing paradigm, such as edge and cloud computing, due to minimizing carbon footprint and lowering operational costs. In order to achieve efficiency, it is essential to address the energy consumption problem of the computing nodes. Conventionally, power in the edge/cloud paradigm could be conserved by diminishing under-utilized resources through various virtual machine consolidation techniques. This operation can be performed more effectively if the resource management component acquires some knowledge of the system workload. In this paper, we would like to present our research on developing an energy-efficient framework to optimize and offload computationally intensive tasks to the edge/cloud system. This objective was achieved based on a two-fold effort. Firstly, an adaptation and modification were introduced to an offloading framework to make it work with heterogeneous edge/cloud systems. This modification consists of the functionalities of resource allocation and control. Subsequently, a lightweight resource scheduling algorithm, namely the Minimal Margin-Based Scheduling Algorithm, was developed to orchestrate the deployment of offloaded tasks to the best-suited container. After that, an extensive evaluation of real equipment was conducted to confirm the proposal's effectiveness. In fact, the results of practical experiments showed that the developed framework and algorithm could efficiently manage computing nodes in response to the change in the workload and reduce energy consumption.