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. INDEX TERMS Edge machine learning, multi-access edge computing, computation offloading, stochastic optimization, resource allocation, energy-latency-accuracy trade-off.
The evolution of communication networks shows a clear shift of focus from just improving the communications aspects to enabling new important services, from Industry 4.0 to automated driving, virtual/augmented reality, Internet of Things (IoT), and so on. This trend is evident in the roadmap planned for the deployment of the fifth generation (5G) communication networks. This ambitious goal requires a paradigm shift towards a vision that looks at communication, computation and caching (3C) resources as three components of a single holistic system. The further step is to bring these 3C resources closer to the mobile user, at the edge of the network, to enable very low latency and high reliability services. The scope of this chapter is to show that signal processing techniques can play a key role in this new vision. In particular, we motivate the joint optimization of 3C resources. Then we show how graph-based representations can play a key role in building effective learning methods and devising innovative resource allocation techniques.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.