An increasing number of mobile applications rely on Machine Learning (ML) routines for analyzing data. Executing such tasks at the user devices saves the energy spent on transmitting and processing large data volumes at distant cloud-deployed servers. However, due to memory and computing limitations, the devices often cannot support the required resource-intensive routines and fail to accurately execute the tasks. In this work, we address the problem of edge-assisted analytics in resource-constrained systems by proposing and evaluating a rigorous selective offloading framework. The devices execute their tasks locally and outsource them to cloudlet servers only when they predict a significant performance improvement. We consider the practical scenario where the offloading gain and resource costs are time-varying; and propose an online optimization algorithm that maximizes the service performance without requiring to know this information. Our approach relies on an approximate dual subgradient method combined with a primal-averaging scheme, and works under minimal assumptions about the system stochasticity. We fully implement the proposed algorithm in a wireless testbed and evaluate its performance using a state-of-the-art image recognition application, finding significant performance gains and cost savings.
翻译:越来越多的移动应用程序依赖于机器学习(ML)常规来分析数据。 在用户设备上执行这种任务可以节省传输和处理远程云端服务器大量数据量的能量。 但是,由于记忆和计算的限制,这些设备往往无法支持所需要的资源密集型常规,无法准确执行任务。在这项工作中,我们通过提议和评价一个严格的选择性卸载框架来解决资源受限制系统中的边缘辅助分析问题。这些装置在当地执行任务,只有在预测显著的性能改进时,才将其外包给云式服务器。我们考虑了卸载收益和资源成本是时间变化的实用情景;我们提出了一种在线优化算法,在不需要了解这一信息的情况下最大限度地提高服务性能。我们的方法依靠一种近乎的双分位法,结合一种初等节能计划,并在对系统是否精确性进行最起码的假设下进行工作。我们完全应用了无线测试床的拟议算法,并使用状态图像识别应用程序来评估其性能,从而找到显著的业绩收益和成本节约。