Real-time data analytics is essential since more and more applications require online decision making in a timely manner. However, efficient analysis of geo-distributed data streams is challenging. This is because data needs to be collected from all edge data centers, which aggregate data from local sources, in order to process most of the analytic tasks. Thus, most of the time edge data centers need to transfer data to a central data center over a wide area network, which is expensive. In this paper, we advocate for a coordinated approach of edge data centers in order to handle these analytic tasks efficiently and hence, reducing the communication cost among data centers. We focus on the windowed aggregation of data streams, which has been widely used in stream analytics. In general, aggregation of data streams among edge data centers in the same region reduces the amount of data that needs to be sent over cross-region communication links. Based on state-of-the-art research, we leverage intra-region links and design a low-overhead coordination algorithm that optimizes communication cost for data aggregation. Our algorithm has been evaluated using synthetic and Big Data Benchmark datasets. The evaluation results show that our algorithm reduces the bandwidth cost up to ~6x, as compared to the state-of-the-art solution.
{"title":"Optimizing Windowed Aggregation over Geo-Distributed Data Streams","authors":"Hooman Peiro Sajjad, Y. Liu, Vladimir Vlassov","doi":"10.1109/EDGE.2018.00012","DOIUrl":"https://doi.org/10.1109/EDGE.2018.00012","url":null,"abstract":"Real-time data analytics is essential since more and more applications require online decision making in a timely manner. However, efficient analysis of geo-distributed data streams is challenging. This is because data needs to be collected from all edge data centers, which aggregate data from local sources, in order to process most of the analytic tasks. Thus, most of the time edge data centers need to transfer data to a central data center over a wide area network, which is expensive. In this paper, we advocate for a coordinated approach of edge data centers in order to handle these analytic tasks efficiently and hence, reducing the communication cost among data centers. We focus on the windowed aggregation of data streams, which has been widely used in stream analytics. In general, aggregation of data streams among edge data centers in the same region reduces the amount of data that needs to be sent over cross-region communication links. Based on state-of-the-art research, we leverage intra-region links and design a low-overhead coordination algorithm that optimizes communication cost for data aggregation. Our algorithm has been evaluated using synthetic and Big Data Benchmark datasets. The evaluation results show that our algorithm reduces the bandwidth cost up to ~6x, as compared to the state-of-the-art solution.","PeriodicalId":396887,"journal":{"name":"2018 IEEE International Conference on Edge Computing (EDGE)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127293950","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}
Shichao Zhu, Lin Gui, Jiacheng Chen, Qi Zhang, Ning Zhang
Research and applications of unmanned aerial vehicles (UAVs) are becoming increasingly prosperous in these years due to the maturity of the aircraft technology and regulations. A large amount of UAVs are to be deployed in cities to undertake tasks such as environment monitoring and security surveillance. For those computation-intensive tasks, on-board execution can lead to inefficiency and unsustainability due to the limited battery life and computing resources of UAVs. To this end, this paper adopts cooperative mobile edge computing such that energy consumption and task execution latency can both be reduced. The computation offloading for UAVs aims to optimize the energy and latency jointly with the help of cooperative edge servers. We obtain the most energy efficient offloading data rate by convex optimization and obtain the optimal data allocation scheme to meet the latency constraint by simulated annealing based particle swarm optimization (SAPSO). Simulation results validate the efficiency of the proposed UAV computation offloading strategy.
{"title":"Cooperative Computation Offloading for UAVs: A Joint Radio and Computing Resource Allocation Approach","authors":"Shichao Zhu, Lin Gui, Jiacheng Chen, Qi Zhang, Ning Zhang","doi":"10.1109/EDGE.2018.00017","DOIUrl":"https://doi.org/10.1109/EDGE.2018.00017","url":null,"abstract":"Research and applications of unmanned aerial vehicles (UAVs) are becoming increasingly prosperous in these years due to the maturity of the aircraft technology and regulations. A large amount of UAVs are to be deployed in cities to undertake tasks such as environment monitoring and security surveillance. For those computation-intensive tasks, on-board execution can lead to inefficiency and unsustainability due to the limited battery life and computing resources of UAVs. To this end, this paper adopts cooperative mobile edge computing such that energy consumption and task execution latency can both be reduced. The computation offloading for UAVs aims to optimize the energy and latency jointly with the help of cooperative edge servers. We obtain the most energy efficient offloading data rate by convex optimization and obtain the optimal data allocation scheme to meet the latency constraint by simulated annealing based particle swarm optimization (SAPSO). Simulation results validate the efficiency of the proposed UAV computation offloading strategy.","PeriodicalId":396887,"journal":{"name":"2018 IEEE International Conference on Edge Computing (EDGE)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126218679","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}
We introduce an edge-centric parametric predictive analytics methodology, which contributes to real-time regression model caching and selective forwarding in the network edge where communication overhead is significantly reduced as only model's parameters and sufficient statistics are disseminated instead of raw data obtaining high analytics quality. Moreover, sophisticated model selection algorithms are introduced to combine diverse local models for predictive modeling without transferring and processing data at edge gateways. We provide mathematical modeling, performance and comparative assessment over real data showing its benefits in edge computing environments.
{"title":"Edge-Centric Efficient Regression Analytics","authors":"Natascha Harth, C. Anagnostopoulos","doi":"10.1109/EDGE.2018.00020","DOIUrl":"https://doi.org/10.1109/EDGE.2018.00020","url":null,"abstract":"We introduce an edge-centric parametric predictive analytics methodology, which contributes to real-time regression model caching and selective forwarding in the network edge where communication overhead is significantly reduced as only model's parameters and sufficient statistics are disseminated instead of raw data obtaining high analytics quality. Moreover, sophisticated model selection algorithms are introduced to combine diverse local models for predictive modeling without transferring and processing data at edge gateways. We provide mathematical modeling, performance and comparative assessment over real data showing its benefits in edge computing environments.","PeriodicalId":396887,"journal":{"name":"2018 IEEE International Conference on Edge Computing (EDGE)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129639761","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}
N. Giang, R. Lea, Michael Blackstock, Victor C. M. Leung
Technology advancement has pushed computation to the network edge, paving the way for a class of IoT applications that leverage CPU, storage and communications in edge devices. Building these new IoT applications is not an easy task however. Two key challenges are supporting the dynamic nature of the edge network and the context-dependent characteristics of application logic. In this paper we report our experience in building an edge computing platform called Distributed Node-RED (DNR) that uses a distributed data flow programming model based on the popular open source Node-RED tool. We describe some of the challenges we faced as well as some novel solutions that were implemented in our platform. A new approach in applying the concept of exogenous coordination is also presented and shown to be necessary in building large-scale IoT applications across the edge, fog and cloud.
{"title":"Fog at the Edge: Experiences Building an Edge Computing Platform","authors":"N. Giang, R. Lea, Michael Blackstock, Victor C. M. Leung","doi":"10.1109/EDGE.2018.00009","DOIUrl":"https://doi.org/10.1109/EDGE.2018.00009","url":null,"abstract":"Technology advancement has pushed computation to the network edge, paving the way for a class of IoT applications that leverage CPU, storage and communications in edge devices. Building these new IoT applications is not an easy task however. Two key challenges are supporting the dynamic nature of the edge network and the context-dependent characteristics of application logic. In this paper we report our experience in building an edge computing platform called Distributed Node-RED (DNR) that uses a distributed data flow programming model based on the popular open source Node-RED tool. We describe some of the challenges we faced as well as some novel solutions that were implemented in our platform. A new approach in applying the concept of exogenous coordination is also presented and shown to be necessary in building large-scale IoT applications across the edge, fog and cloud.","PeriodicalId":396887,"journal":{"name":"2018 IEEE International Conference on Edge Computing (EDGE)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132567651","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}
Abderrahmen Mtibaa, R. Tourani, S. Misra, J. Burke, Lixia Zhang
This paper discusses leveraging the Named Data Networking (NDN) architecture and Named Function Networking (NFN) to facilitate in-network edge computing. In the NDN context, we consider a the Augmented Reality (AR) use-case–a challenging application–to discuss how NDN functionalities can be leveraged for addressing inherent edge computing challenges, such as efficient resource discovery, compute re-use, mobility management, and security. We present several options to tackle the highlighted challenges and where possible provide solutions.
{"title":"Towards Edge Computing over Named Data Networking","authors":"Abderrahmen Mtibaa, R. Tourani, S. Misra, J. Burke, Lixia Zhang","doi":"10.1109/EDGE.2018.00023","DOIUrl":"https://doi.org/10.1109/EDGE.2018.00023","url":null,"abstract":"This paper discusses leveraging the Named Data Networking (NDN) architecture and Named Function Networking (NFN) to facilitate in-network edge computing. In the NDN context, we consider a the Augmented Reality (AR) use-case–a challenging application–to discuss how NDN functionalities can be leveraged for addressing inherent edge computing challenges, such as efficient resource discovery, compute re-use, mobility management, and security. We present several options to tackle the highlighted challenges and where possible provide solutions.","PeriodicalId":396887,"journal":{"name":"2018 IEEE International Conference on Edge Computing (EDGE)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126134383","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}
K. Fan, Q. Pan, Junxiong Wang, Tingting Liu, Hui Li, Yintang Yang
With the development of Internet technology, the demand for openness and sharing of information in the network grows rapidly. Data sharing in one domain can not satisfy users' requirement. What a user needs may be the data in another management domain, so there is an urgent need for a secure way to share data among different domains. At present, some web technology (JSONP, server proxy, cross frame and so on) and attribute-based encryption (ABE) are main methods to solve cross-domain sharing. The main problem cross-domain sharing face is security of data and authentication among different domains. In edge computing model, the cloud service provider is a trust root which links all the edge computing nodes together. Edge computing node is the administrator of one domain, and responsible for data transmission and processing. In this paper, we propose a secure way to share data among different domains by edge computing model, we regard the edge computing node and managed edge equipment as a domain, and all the domains are linked together by the cloud, it is easy to solve the problem of authentication among different domains in this way. Meanwhile, RSA algorithm and ciphertext-policy attribute-based encryption (CP-ABE) are used to ensure the confidentiality of the information and one-to-many sharing of data. Finally, analysis shows that our scheme is secure.
{"title":"Cross-Domain Based Data Sharing Scheme in Cooperative Edge Computing","authors":"K. Fan, Q. Pan, Junxiong Wang, Tingting Liu, Hui Li, Yintang Yang","doi":"10.1109/EDGE.2018.00019","DOIUrl":"https://doi.org/10.1109/EDGE.2018.00019","url":null,"abstract":"With the development of Internet technology, the demand for openness and sharing of information in the network grows rapidly. Data sharing in one domain can not satisfy users' requirement. What a user needs may be the data in another management domain, so there is an urgent need for a secure way to share data among different domains. At present, some web technology (JSONP, server proxy, cross frame and so on) and attribute-based encryption (ABE) are main methods to solve cross-domain sharing. The main problem cross-domain sharing face is security of data and authentication among different domains. In edge computing model, the cloud service provider is a trust root which links all the edge computing nodes together. Edge computing node is the administrator of one domain, and responsible for data transmission and processing. In this paper, we propose a secure way to share data among different domains by edge computing model, we regard the edge computing node and managed edge equipment as a domain, and all the domains are linked together by the cloud, it is easy to solve the problem of authentication among different domains in this way. Meanwhile, RSA algorithm and ciphertext-policy attribute-based encryption (CP-ABE) are used to ensure the confidentiality of the information and one-to-many sharing of data. Finally, analysis shows that our scheme is secure.","PeriodicalId":396887,"journal":{"name":"2018 IEEE International Conference on Edge Computing (EDGE)","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123061240","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}
As the overwhelming growth of smart devices and massive arrival of new application, network traffic volume has been growing rapidly. The traditional centralized network architecture, such as locating services at core cloud, causes a heavy burden on the backhaul link and long latency. Edge Cloud Computing has been introduced to reduce traffic bottlenecks in the core, backhaul network and service delay by pushing data intensive tasks towards the edge and locally processing data in proximity to the users. This paper introduces a new simulation framework, so-called ECSim++, based on the OMNeT++ simulator [15] and INET framework [2] to enable exploration of computing, caching, communication or energy efficiency related issues in Edge Cloud Computing. ECSim++ is designed not only to allow researchers to customize caching protocols, edge services, but also to analyze, debug and evaluate easily for Edge Cloud Computing environment. In addition, ECSim++ also provides an energy consumption model so that researchers could deploy and evaluate their energy strategies.
{"title":"ECSim++: An INET-Based Simulation Tool for Modeling and Control in Edge Cloud Computing","authors":"Tien-Dung Nguyen, E. Huh","doi":"10.1109/EDGE.2018.00018","DOIUrl":"https://doi.org/10.1109/EDGE.2018.00018","url":null,"abstract":"As the overwhelming growth of smart devices and massive arrival of new application, network traffic volume has been growing rapidly. The traditional centralized network architecture, such as locating services at core cloud, causes a heavy burden on the backhaul link and long latency. Edge Cloud Computing has been introduced to reduce traffic bottlenecks in the core, backhaul network and service delay by pushing data intensive tasks towards the edge and locally processing data in proximity to the users. This paper introduces a new simulation framework, so-called ECSim++, based on the OMNeT++ simulator [15] and INET framework [2] to enable exploration of computing, caching, communication or energy efficiency related issues in Edge Cloud Computing. ECSim++ is designed not only to allow researchers to customize caching protocols, edge services, but also to analyze, debug and evaluate easily for Edge Cloud Computing environment. In addition, ECSim++ also provides an energy consumption model so that researchers could deploy and evaluate their energy strategies.","PeriodicalId":396887,"journal":{"name":"2018 IEEE International Conference on Edge Computing (EDGE)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124667887","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：