期刊
IEEE ACCESS
卷 9, 期 -, 页码 45377-45398出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3066559
关键词
Delays; Task analysis; Servers; Resource management; Reliability; Heuristic algorithms; Machine learning; Edge machine learning; multi-access edge computing; computation offloading; stochastic optimization; resource allocation; energy-latency-accuracy trade-off
资金
- Ministero dell'Istruzione, dell'Universita e della Ricerca (MIUR) through the Progetti di Rilevante Interesse Nazionale (PRIN) Liquid Edge contract [861459]
This paper proposes a resource allocation strategy for dynamic training and inference of machine learning tasks at the edge of wireless network to explore the trade-off between energy, delay, and learning accuracy. Two dynamic strategies are introduced to minimize system energy consumption under constraints on service delay and accuracy, as well as to optimize learning accuracy while guaranteeing bounded energy consumption. The proposed approach aims to strike a balance between energy consumption and quality of service in Edge Machine Learning (EML) tasks.
The aim of this paper is to propose a resource allocation strategy for dynamic training and inference of machine learning tasks at the edge of the wireless network, with the goal of exploring the trade-off between energy, delay and learning accuracy. The scenario of interest is composed of a set of devices sending a continuous flow of data to an edge server that extracts relevant information running online learning algorithms, within the emerging framework known as Edge Machine Learning (EML). Taking into account the limitations of the edge servers, with respect to a cloud, and the scarcity of resources of mobile devices, we focus on the efficient allocation of radio (e.g., data rate, quantization) and computation (e.g., CPU scheduling) resources, to strike the best trade-off between energy consumption and quality of the EML service, including service end-to-end (E2E) delay and accuracy of the learning task. To this aim, we propose two different dynamic strategies: (i) The first method aims to minimize the system energy consumption, under constraints on E2E service delay and accuracy; (ii) the second method aims to optimize the learning accuracy, while guaranteeing an E2E delay and a bounded average energy consumption. Then, we present a dynamic resource allocation framework for EML based on stochastic Lyapunov optimization. Our low-complexity algorithms do not require any prior knowledge on the statistics of wireless channels, data arrivals, and data probability distributions. Furthermore, our strategies can incorporate prior knowledge regarding the model underlying the observed data, or can work in a totally data-driven fashion. Several numerical results on synthetic and real data assess the performance of the proposed approach.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据