2016 IEEE CCNC大会：Fog Computing的实时资源估计与边缘数据处理

需积分: 9 77 浏览量更新于2024-09-10 收藏 952KB PDF 举报

在2016年的IEEE Cloud and Computing Networking Conference (CCNC)上，会议论文"PRE-Fog: IoTTraceBasedProbabilistic ResourceEstimationatFog"探讨了在物联网(IoT)边缘即雾计算(Micro Datacenter, MDC)环境下，如何实现高效和有效的资源管理。随着物联网设备的普及，这些设备产生了各种类型的数据，频率各异，对实时响应、紧急服务、医疗保健和低延迟应用的需求日益增长。在这种背景下，边缘云计算成为关键，它位于IoT设备与大型数据中心云之间，承担着数据处理、过滤、预处理以及安全措施等职责。论文的作者，来自卡尔顿大学系统与计算机工程系的Mohammad Aazam、Marc St-Hilaire、Chung-Horng Lung和Ioannis Lambadaris，提出了PRE-Fog模型。该模型利用基于物联网 traces 的概率资源估计方法，旨在解决在Fog中智能分配和优化资源的问题。通过分析实际的IoT操作数据， PRE-Fog能够动态地评估和预测不同服务对资源的需求，如存储、计算和网络带宽，从而避免过度依赖核心网络和云端，减轻其负担。为了实现这一目标，研究者们关注了以下几个关键点： 1. **实时性和敏感性服务**：针对那些对实时响应有严格要求的服务，如紧急救援和远程医疗，Fog必须能够在短时间内处理和转发数据。 2. **数据分类与上传策略**：决定哪些数据应该上传到云端，而哪些可以在本地处理或在Fog层进行初步处理，以平衡性能和成本。 3. **资源管理算法**：设计高效的算法来动态调整Fog中的硬件资源，如CPU、内存和存储，以适应不断变化的负载需求。 4. **数据处理效率**：优化数据预处理步骤，减少传输至云端的数据量，提高整体系统的响应速度和能源效率。 5. **安全性**：在Fog层实施安全措施，保护用户隐私和数据安全，防止数据泄露或恶意攻击。这篇论文为理解并优化Fog计算架构中的资源管理提供了理论基础和实践指导，对于推进IoT时代的边缘计算技术发展具有重要意义。它强调了在快速发展的IoT环境中，对Fog计算的智能管理和优化是确保服务质量、降低能耗和保护用户隐私的关键。

PRE-Fog: IoT Trace Based Probabilistic

Resource Estimation at Fog

Mohammad Aazam, Marc St-Hilaire, Chung-Horng Lung, Ioannis Lambadaris

Department of Systems and Computer Engineering

Carleton University, Ottawa, Canada

aazam@ieee.org, marc_st_hilaire@carleton.ca, chlung@sce.carleton.ca, ioannis@sce.carleton.ca

Abstract— Lately, pervasive and ubiquitous computing services

have been under focus of not only the research community, but

developers as well. Different devices generate different types of

data with different frequencies. Emergency, healthcare, and latency

sensitive services require real-time responses. Also, it is necessary

to decide what type of data has to be uploaded to the cloud, without

burdening the core network and the cloud. For this purpose, the

cloud on the edge of the network, known as Fog or Micro

Datacenter (MDC), plays an important role. Fog resides between

the underlying Internet of Things (IoTs) and the mega datacenter

cloud. Its purpose is to manage resources, perform data filtration,

preprocessing, and security measures. To achieve this, Fog requires

an effective and efficient resource management framework, which

we propose in this paper. Fog has to deal with mobile nodes and

IoTs, which involves objects and devices of different types having a

fluctuating connectivity behavior. All such types of service

customers have an unpredictable relinquish probability, since any

object or device can stop using resources at any moment. In our

proposed methodology for resource estimation and management

through Fog computing, we take into account these factors and

formulate resource management on the basis of fluctuating

relinquish probability of the customer, service type, service price,

and variance of the relinquish probability. With the intent of

showing practical implications of our method, we implemented it

on Crawdad real trace and Amazon EC2 pricing. Based on various

services, differentiated through Amazon's price plans and historical

record of Cloud Service Customers (CSCs), the model determines

the amount of resources to be allocated. More loyal CSCs get better

services, while for the contrary case, the provider reserves

resources cautiously.

Index Terms—IoT; Cloud of Things; Fog computing; Edge

computing; Micro Datacenter (MDC); resource management.

I. INTRODUCTION

Connectivity has been revolutionized with the rapid

development of Wireless Sensor Networks (WSNs), healthcare

related services, smart phones, and other pervasive means. With

the advent of IoT; devices, services, and people are ubiquitously

connected almost all the time, generating a tremendous amount

of data. The objective of IoT is to provide a network

infrastructure with interoperable communication protocols and

softwares to allow interaction and integration of physical/virtual

sensors, computers, smart devices, vehicles, and dumb objects

like fridge, dishwasher, microwave oven, food items, medicines,

etc. [1].

The backbone of IoT communications is Machine-to-

Machine (M2M), although, not limited to it. In M2M

communications, two or more machines communicate with each

other directly, without human interventions. IoT enables non-

communicating devices to become part of the Internet and

communicate through data communications means such as bar-

code readers, RFID, etc. With the advancements in smartphone

technology, many objects would be able to be part of IoT through

various smartphone sensors. This way, non-intelligent nodes,

known as "things", become communicating and data generating

objects of IoT.

IoT-based services are gaining importance rapidly. Since

2011, the number of connected devices has already exceeded the

number of people on Earth. Already, the number of connected

devices have reached 9 billion and is expected to grow more

rapidly and reach 24 billion by 2020 [2]. With the increasing

number of heterogeneous devices connected to IoT and

generating data, it is no more possible for a standalone IoT to

perform power and bandwidth constrained tasks efficiently. IoT

and cloud computing amalgamation is becoming very important

[3]. There comes a situation when the cloud is connected with

IoT that generates multimedia data. Visual Sensor Network or

CCTV connected to cloud are examples of such a scenario. Since

multimedia content consumes more processing power, storage

space, and scheduling resources, it becomes important to manage

them effectively to perform efficient resource management in the

cloud. Specially, with mobile devices and other IoT nodes which

do not have a reliable connectivity behavior cost considerably

when it comes to resource allocation. Since resources are

reserved but due to mobility or fluctuating behavior, if resources

are given up, the datacenter has to manage the underutilization

scenarios. In addition, mission critical and latency sensitive IoT

services require very quick responses and processing. In that

case, it is not feasible to communicate through the distant cloud,

over the Internet. Fog computing plays a very vital role in this

regard [3]. Fog computing refers to bringing networking

resources close to the underlying networks. It is a network

between the underlying network(s) and the cloud(s). Fog

computing extends the traditional cloud computing paradigm to

2016 13th IEEE Annual Consumer Communications & Networking Conference (CCNC)

下载后可阅读完整内容，剩余5页未读，立即下载

ArthurWooyun

粉丝: 0
资源: 4

2016 IEEE CCNC大会：Fog Computing的实时资源估计与边缘数据处理

基于穿戴设备的驾驶员识别：提升车辆安全

西门子EWSD系统详解：接口、应用与功能特点

IEEE CCNC 2016 年 大会资料（1）

IEEE CCNC 2016 年 大会资料（2）

ccnc2016:IEEE CCNC 2016论文代码

西门子EWSD基础学习资料.pdf

cairo-devel-1.15.12-4.el7.x86_64.rpm.zip

abrt-devel-2.1.11-60.el7.centos.i686.rpm.zip

baobab-3.28.0-2.el7.x86_64.rpm.zip

anaconda-21.48.22.159-1.el7.centos.x86_64.rpm.zip

最新资源

IEEE CCNC 2016 年大会资料（1）

IEEE CCNC 2016 年大会资料（2）