2018 IEEE/ACM Symposium on Edge Computing (SEC)最新文献_第5页

CAVBench: A Benchmark Suite for Connected and Autonomous Vehicles CAVBench:网联和自动驾驶汽车的基准测试套件

2018 IEEE/ACM Symposium on Edge Computing (SEC) Pub Date : 2018-10-01 DOI: 10.1109/SEC.2018.00010

Yifan Wang, Shaoshan Liu, Xiaopei Wu, Weisong Shi

{"title":"CAVBench: A Benchmark Suite for Connected and Autonomous Vehicles","authors":"Yifan Wang, Shaoshan Liu, Xiaopei Wu, Weisong Shi","doi":"10.1109/SEC.2018.00010","DOIUrl":"https://doi.org/10.1109/SEC.2018.00010","url":null,"abstract":"Connected and autonomous vehicles (CAVs) have recently attracted a significant amount of attention both from researchers and industry. Numerous studies targeting algorithms, software frameworks, and applications on the CAVs scenario have emerged. Meanwhile, several pioneer efforts have focused on the edge computing system and architecture design for the CAVs scenario and provided various heterogeneous platform prototypes for CAVs. However, a standard and comprehensive application benchmark for CAVs is missing, hindering the study of these emerging computing systems. To address this challenging problem, we present CAVBench, the first benchmark suite for the edge computing system in the CAVs scenario. CAVBench is comprised of six typical applications covering four dominate CAVs scenarios and takes four datasets as standard input. CAVBench provides quantitative evaluation results via application and system perspective output metrics. We perform a series of experiments and acquire three systemic characteristics of the applications in CAVBench. First, the operation intensity of the applications is polarized, which explains why heterogeneous hardware is important for a CAVs computing system. Second, all applications in CAVBench consume high memory bandwidth, so the system should be equipped with high bandwidth memory or leverage good memory bandwidth management to avoid the performance degradation caused by memory bandwidth competition. Third, some applications have worse data/instruction locality based on the cache miss observation, so the computing system targeting these applications should optimize the cache architecture. Last, we use the CAVBench to evaluate a typical edge computing platform and present the quantitative and qualitative analysis of the benchmarking results.","PeriodicalId":376439,"journal":{"name":"2018 IEEE/ACM Symposium on Edge Computing (SEC)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121014935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 48

EdgeBox: Live Edge Video Analytics for Near Real-Time Event Detection EdgeBox:近实时事件检测的实时边缘视频分析

2018 IEEE/ACM Symposium on Edge Computing (SEC) Pub Date : 2018-10-01 DOI: 10.1109/SEC.2018.00040

Bing Luo, Sheng Tan, Zhifeng Yu, Weisong Shi

引用次数: 16

Harpocrates: Giving Out Your Secrets and Keeping Them Too 哈波克拉底:说出你的秘密，也保守秘密

2018 IEEE/ACM Symposium on Edge Computing (SEC) Pub Date : 2018-10-01 DOI: 10.1109/SEC.2018.00015

Rufaida Ahmed, Zirak Zaheer, Richard Li, R. Ricci

{"title":"Harpocrates: Giving Out Your Secrets and Keeping Them Too","authors":"Rufaida Ahmed, Zirak Zaheer, Richard Li, R. Ricci","doi":"10.1109/SEC.2018.00015","DOIUrl":"https://doi.org/10.1109/SEC.2018.00015","url":null,"abstract":"Content Distribution Networks (CDNs) offer websites and web services the ability to host content on servers that are near the edge of the network, close to users. Benefits of this arrangement include low latency, scalability, and resistance to Denial of Service attacks. Traditionally, CDNs have hosted primarily static content, but increasingly, there is an interest in pushing active computation to the edge as well. This active computation, which is similar in style to the \"server-less\" computing becoming popular in clouds, offers a wealth of new opportunities for web services to be-come faster and more scalable. With this opportunity, however, comes a much greater exposure to security threats. One is leakage of secret materials (such as keys, identities, etc.) that are accessed by these functions. Another is the possibility that sensitive calculations are not executed faithfully in the CDN; e.g. a modified version of the customer's code is run. In this paper, we present the design of Harpocrates, a framework that allows active code to be pushed from an origin webserver out to workers at the edge of a CDN. Harpocrates makes use of Intel's SGX technology to keep data private, and presents an environment similar to the JavaScript WebWorker API to simplify the process of code that can run on either origin servers or the CDN. We use Harpocrates to design a number of interesting services, including a service that generates and checks secure cookies within the CDN, and a framework that protects against denial-of-service attacks in a way that is customized to a specific website. We show that the framework performs well enough to be deployable in practice.","PeriodicalId":376439,"journal":{"name":"2018 IEEE/ACM Symposium on Edge Computing (SEC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115191220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9

From Cell Towers to Smart Street Lamps: Placing Cloudlets on Existing Urban Infrastructures 从手机信号塔到智能路灯:在现有的城市基础设施上放置云

2018 IEEE/ACM Symposium on Edge Computing (SEC) Pub Date : 2018-10-01 DOI: 10.1109/SEC.2018.00021

Julien Gedeon, Michael Stein, Jeff Krisztinkovics, Patrick Felka, Katharina Keller, Christian Meurisch, Lin Wang, M. Mühlhäuser

{"title":"From Cell Towers to Smart Street Lamps: Placing Cloudlets on Existing Urban Infrastructures","authors":"Julien Gedeon, Michael Stein, Jeff Krisztinkovics, Patrick Felka, Katharina Keller, Christian Meurisch, Lin Wang, M. Mühlhäuser","doi":"10.1109/SEC.2018.00021","DOIUrl":"https://doi.org/10.1109/SEC.2018.00021","url":null,"abstract":"Cloudlets are small-scale offloading units for low-latency demands, offering a unique opportunity for emerging smart city applications such as autonomous driving or augmented reality. While previous works have investigated the general concept of cloudlets, little attention has been directed to the question of where to actually place cloudlets on existing infrastructure in a city. Due to cloudlets' heterogeneity in this context, their placement remains challenging. In this paper, we first provide a thorough analysis of a city-wide cloudlet infrastructure deployed on three types of existing infrastructures that act as wireless access points: cellular base stations, commercial off-the-shelf routers, and smart lamp posts. Based on real-world data for the access point locations in a major city and movement traces of two mobile applications, we analyze multiple coverage metrics to gain insights on the practicability of leveraging these infrastructures for a city-scale deployment of cloudlets. As a second major contribution, we propose a novel placement strategy that takes into account the heterogeneity in terms of communication ranges, resources, and costs associated with each type of cloudlet. Our strategy enables the tradeoff between deployment cost and quality of service as required for different deployment scenarios. The effectiveness of our strategy is confirmed through real-world-trace-based evaluation.","PeriodicalId":376439,"journal":{"name":"2018 IEEE/ACM Symposium on Edge Computing (SEC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122180122","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 15

A Novel Architecture for Automatic Document Classification for Effective Security in Edge Computing Environments 一种边缘计算环境下有效安全的文档自动分类新体系结构

2018 IEEE/ACM Symposium on Edge Computing (SEC) Pub Date : 2018-10-01 DOI: 10.1109/SEC.2018.00056

Lei Ding, M. B. Salem

引用次数: 4

Enabling Semantics in oneM2M Service Delivery Platform oneM2M业务交付平台使能语义

2018 IEEE/ACM Symposium on Edge Computing (SEC) Pub Date : 2018-10-01 DOI: 10.1109/SEC.2018.00054

Jie Cao, Lanyu Xu, Weisong Shi

引用次数: 0

A Heuristic Algorithm Based on Resource Requirements Forecasting for Server Placement in Edge Computing 基于资源需求预测的边缘计算服务器布局启发式算法

2018 IEEE/ACM Symposium on Edge Computing (SEC) Pub Date : 2018-10-01 DOI: 10.1109/SEC.2018.00043

Kaile Xiao, Zhipeng Gao, Qian Wang, Yang Yang

引用次数: 17

Embedded Deep Learning for Vehicular Edge Computing 车载边缘计算的嵌入式深度学习

2018 IEEE/ACM Symposium on Edge Computing (SEC) Pub Date : 2018-10-01 DOI: 10.1109/SEC.2018.00038

J. Hochstetler, Rahul Padidela, Qi Chen, Qing Yang, Song Fu

引用次数: 51

Risk-Based Optimization of Resource Provisioning in Mobile Edge Computing 移动边缘计算中基于风险的资源配置优化

2018 IEEE/ACM Symposium on Edge Computing (SEC) Pub Date : 2018-10-01 DOI: 10.1109/SEC.2018.00033

H. Badri, Tayebeh Bahreini, Daniel Grosu, Kai Yang

引用次数: 6

Bandwidth-Efficient Live Video Analytics for Drones Via Edge Computing 基于边缘计算的无人机带宽高效实时视频分析

2018 IEEE/ACM Symposium on Edge Computing (SEC) Pub Date : 2018-10-01 DOI: 10.1109/SEC.2018.00019

Junjue Wang, Ziqiang Feng, Zhuo Chen, S. George, Mihir Bala, P. Pillai, Shao-Wen Yang, M. Satyanarayanan

引用次数: 158