Fog Computing. Группа авторов

3 Deep Learning in the Era of Edge Computing: Challenges and Opportunities

       Mi Zhang1, Faen Zhang2, Nicholas D. Lane3, Yuanchao Shu4, Xiao Zeng1, Biyi Fang1, Shen Yan1, and Hui Xu2

       1Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA, 48824

       2AInnovation, Beijing, China, 100080

       3Department of Computer Science, Oxford University, Oxford, United Kingdom, OX1 3PR

       4Microsoft Research, Redmond, WA, USA, 98052

3.1 Introduction

      Of all the technology trends that are taking place right now, perhaps the biggest one is edge computing [1, 2]. It is the one that is going to bring the most disruption and the most opportunity over the next decade. Broadly speaking, edge computing is a new computing paradigm that aims to leverage devices that are deployed at the Internet's edge to collect information from individuals and the physical world as well as to process the collected information in a distributed manner [3]. These devices, referred to as edge devices, are physical devices equipped with sensing, computing, and communication capabilities. Today, we are already surrounded by a variety of such edge devices: our mobile phones and wearables are edge devices; home intelligence devices such as Google Nest and Amazon Echo are edge devices; autonomous systems such as drones, self-driving vehicles, and robots that vacuum the carpet are also edge devices. These edge devices continuously collect a variety of data, including images, videos, audios, texts, user logs, and many others with the ultimate goal to provide a wide range of services to improve the quality of people's everyday lives.

Although the Internet is the backbone of edge computing, the true value of edge computing lies at the intersection of gathering data from sensors and extracting meaningful information from the collected sensor data. Over the past few years, deep learning (i.e. deep neural networks [DNNs]) [4] has become the dominant data analytics approach due to its capability to achieve impressively high accuracies on a variety of important computing tasks, such as speech recognition [5], machine translation [6], object recognition [7], face detection [8], sign language translation [9], and scene understanding [10]. Driven by deep learning's splendid capability, companies such as Google, Facebook, Microsoft, and Amazon are embracing this technological breakthrough and using deep learning as the core technique to power many of their services.

      Deep learning models are known to be expensive in terms of computation, memory, and power consumption [11, 12]. As such, given the resource constraints of edge devices, the status quo approach is based on the cloud computing paradigm in which the collected sensor data are directly uploaded to the cloud; and the data processing tasks are performed on the cloud servers, where abundant computing and storage resources are available to execute the deep learning models. Unfortunately, cloud computing suffers from three key drawbacks that make it less favorable to applications and services enabled by edge devices. First, data transmission to the cloud becomes impossible if the Internet connection is unstable or even lost. Second, data collected at edge devices may contain very sensitive and private information about individuals. Directly uploading those raw data onto the cloud constitutes a great danger to individuals' privacy. Most important, as the number of edge devices continues to grow exponentially, the bandwidth of the Internet becomes the bottleneck of cloud computing, making it no longer feasible or cost-effective to transmit the gigantic amount of data collected by those devices to the cloud.

      In this book chapter, we aim to provide our insights for answering the following question: can edge computing leverage the amazing capability of deep learning? As computing resources in edge devices become increasingly powerful, especially with the emergence of artificial intelligence (AI) chipsets, we envision that in the near future, the majority of the edge devices will be equipped with machine intelligence powered by deep learning. The realization of this vision requires considerable innovation at the intersection of computer systems, networking, and machine learning. In the following, we describe eight research challenges followed by opportunities that have high promise to address those challenges. We hope this book chapter act as an enabler of inspiring new research that will eventually lead to the realization of the envisioned intelligent edge.

3.2 Challenges and Opportunities

      3.2.1 Memory and Computational Expensiveness of DNN Models

Memory and computational abilities are expensive for DNN models that achieve state-of-the-art performance. To illustrate this, Table 3.1 lists the details of some of the most commonly used DNN models. As shown, these models normally contain millions of model parameters and consume billions of floating-point operations (FLOPs). This is because these DNN models are designed for achieving high accuracy without taking resources consumption into consideration. Although computing resources in edge devices are expected to become increasingly powerful, their resources are way more constrained than cloud servers. Therefore, filling the gap between high computational demand of DNN models and the limited computing resources of edge devices represents a significant challenge.

Table 3.1 Memory and computational expensiveness of some of the most commonly used DNN models.

DNN	Top-5 error (%)	Latency (ms)	Layers	FLOPs (billion)	Parameters (million)
AlexNet	19.8	14.56	8	0.7	61
GoogleNet	10.07	39.14	22	1.6	6.9
VGG-16	8.8	128.62	16	15.3	Скачать книгу В начало < 27 28 29 30 31 32 33 34 35 36 > В конец e-mail: [email protected]