<link rel="stylesheet" href="styles.cf390c6bfbe7555f.css">

學術出版;;Publications

Permanent URI for this communityhdl:11536/1

收集所有交通大學研究人員與學生個人或團體所發表之各項學術著作，涵蓋期刊論文、教師專書、學位論文等項。;;Collections of Publications of NCTU Researchers and Students Like Journal Papers and Thesis.

Browse

🏛️國立陽明交通大學機構典藏

Subject: search.filters.subject.Cloud Computing

Search Results

Now showing 1 - 10 of 33
  • Thumbnail Image
    Item type:Item,
    Extending IoT/M2M Scalability by Network Slicing
    (2018-01-01)
    de la Bastida, David
    ;
    Lin, Fuchun Joseph
    ;
    資訊工程學系
    ;
    電機資訊國際碩士學位學程
    ;
    Department of Computer Science
    In this research, we have extended our initial effort in cloud-based IoT/M2M system scalability and developed a more robust solution by considering diverse QoS requirements from various IoT/M2M traffic patterns. Though our initial effort created a highly scalable architecture for IoT/M2M platforms based on OpenStack, it treated all IoT/M2M traffic without any discrepancy in the same underlying network (i.e. in the same network slice). Now, by leveraging software-defined networking in OpenStack and by using our traffic-slice optimal matching algorithm, we can direct different types of IoT traffic to feasible network slices in terms of QoS. Our experiments show that when compared with a system without network slicing, our scalability system performs better in terms of response time, power consumption, and computational cost.
  • Thumbnail Image
    Item type:Item,
    Peer-to-Peer Based Parallel Genetic Algorithm
    (2017-01-01)
    Helal, Mohammed H. S.
    ;
    Fan, Chih-Tien
    ;
    Liu, De-You
    ;
    Yuan, Shyan-Ming
    ;
    資訊科學與工程研究所
    In an attempt to reduce communication overhead while maintaining high quality Genetic Algorithm results, this paper presents a Peer-to-Peer based Genetic Algorithm that suites both Parallel and Distributed environments. In order to improve our approach's applicability on both distributed and parallel environments, we experimented a set of different individual exchange intervals when running some well-known hard optimization problems. The proposed approach has been applied in different exchange rates and benchmarked with a regular Master-Slave based PGA on result quality and executions time. Experimental results show that our approach managed to find high quality results in shorter execution time compared to Master-Slave based PGA.
  • Thumbnail Image
    Item type:Item,
    Using Google's Compute Engine Service Pricing as a Reference for Comparison Between Master-Slave and Island Model-Based Fully Distributed Genetic Algorithm
    (2017-01-01)
    Helal, Mohammed H. S.
    ;
    Liu, De-You
    ;
    Yuan, Shyan-Ming
    ;
    資訊科學與工程研究所
    ;
    Institute of Computer Science and Engineering
    Common Master-Slave based Parallel Genetic Algorithms can efficiently utilize multiple computational nodes working on a single process, which leads to finding solutions in less execution time. However, Master-Slave model causes high communication traffic between the nodes. On the other hand, Island-model based parallel implementation can reduce the amount of traffic between the nodes while reducing the efficiency in finding solutions. However it is discussed deeply in the literature, the tradeoff between execution time, traffic size and quality of result have not been estimated based on actual money cost. This paper presents a comparison between Master-Slave and Island-model based fully distributed implementations for Genetic Algorithm. The comparison is based on the actual money cost when running on Google Cloud Compute Engine Service. We implemented Genetic Algorithm in Master-Slave model and in Island model running in different migration rates in order to find a reasonable migration rate that can help find high quality results will the least possible cost.
  • Thumbnail Image
    Item type:Item,
    Pervasive brain monitoring and data sharing based on multi-tier distributed computing and linked data technology
    (2014-06-03)
    Zao, John K.
    ;
    Gan, Tchin-Tze
    ;
    You, Chun-Kai
    ;
    Chung, Cheng-En
    ;
    Wang, Yu-Te
    EEG-based Brain-computer interfaces (BCI) are facing basic challenges in real-world applications. The technical difficulties in developing truly wearable BCI systems that are capable of making reliable real-time prediction of users' cognitive states in dynamic real-life situations may seem almost insurmountable at times. Fortunately, recent advances in miniature sensors, wireless communication and distributed computing technologies offered promising ways to bridge these chasms. In this paper, we report an attempt to develop a pervasive on-line EEG-BCI system using state-of-art technologies including multi-tier Fog and Cloud Computing, semantic Linked Data search, and adaptive prediction/classification models. To verify our approach, we implement a pilot system by employing wireless dry-electrode EEG headsets and MEMS motion sensors as the front-end devices, Android mobile phones as the personal user interfaces, compact personal computers as the near-end Fog Servers and the computer clusters hosted by the Taiwan National Center for High-performance Computing (NCHC) as the far-end Cloud Servers. We succeeded in conducting synchronous multi-modal global data streaming in March and then running a multi-player on-line EEG-BCI game in September, 2013. We are currently working with the ARL Translational Neuroscience Branch to use our system in real-life personal stress monitoring and the UCSD Movement Disorder Center to conduct in-home Parkinson's disease patient monitoring experiments. We shall proceed to develop the necessary BCI ontology and introduce automatic semantic annotation and progressive model refinement capability to our system.
  • Thumbnail Image
    Item type:Item,
    Implementing NFV System with OpenStack
    (2017-01-01)
    Chen, Jinlin
    ;
    Chen, Yiren
    ;
    Tsai, Shi-Chun
    ;
    Lin, Yi-Bing
    ;
    交大名義發表
    Network Function Virtualization (NFV) is a promising approach for service providers to reduce CAPEX and OPEX and has drawn a lot of attention from vendors. Service Function Chaining (SFC) provides the ability to define a sequence of network services. This paper identifies two important issues (placement and scaling) on deploying reliably and efficiently SFC with a cloud platform. Based on the OpenStack Tacker architecture, we explore possible solutions and implement the missing features in Tacker for SFC. We propose two algorithms for finding service location and policy of scaling. The experiments show the efficiency of our approach compared with the default deployment methods provided in OpenStack. We also discuss and highlight future work to improve utilization of cloud platform for deploying service function chaining.
  • Thumbnail Image
    Item type:Item,
    An IoT-Based Cloud-Fog Computing Platform for Creative Service Process
    (2017-01-01)
    Hsu, Tse-Chuan
    ;
    Hsu, Terng-Yin
    ;
    Yang, Hongji
    ;
    Chung, Yeh-Ching
    ;
    資訊工程學系
    The creative service process is an innovative process that uses newly developed technologies to improve the service models currently used. In this paper, we proposed an IoT-based Cloud-Fog computing platform for the creative service process. The proposed Cloud-Fog computing platform is a distributed computing platform where compute, storage, and network systems of Cloud and Fog are working independently or collaboratively depending on the services performed by the platform. If a service requires resources either from Cloud or Fog, then only the designated Cloud or Fog will be involved. Otherwise, both Cloud and Fog will be collaborated to each other for the service. During the collaboration, the required data may be back and forth in between Cloud and Fog. To demonstrate the usage of the proposed platform for the creative service process, two service examples, smart classroom and city surveillance, are discussed
  • Thumbnail Image
    Item type:Item,
    A Cloud Based Dynamic Content Delivery Network
    (2015-01-01)
    Fan, Chih-Tien
    ;
    Piboonudompornkul, Pawat
    ;
    Wu, Zong-You
    ;
    交大名義發表
    ;
    National Chiao Tung University
    In this paper, proposed Cloud based Content delivery network system to serve a dynamic web content delivery service. We used MongoDB as a NoSQL database, deploy inside each HDFS nodes server and connect database together as a replication set of database. This system ensures web content provider will receive a high performance, high availability and fault tolerance from power of NoSQL database technology. From the problem when web content provider want to move their web content in MySQL database environment to work in NoSQL database environment. User require a lot of time change their web content to work with new database environment and think about different schema of each database. So, we also study about Relational database management system (RDBMS) compare with NoSQL database, MongoDB. This work find out differentiation of this two type of database in different aspect: characteristic of each database, feature, database scheme and how to mapping this database query language together. The result of this work we done to develop simple and useful helper tools: PHP MySQL connector and MySQL database migrate tool. This tool is make web content provide easy and fast for migrate their web content from MySQL database web server environment to use our Cloud Based Dynamic Content Delivery Network without any special knowledge with NoSQL database.
  • Thumbnail Image
    Item type:Item,
    OpenStack-based Highly Scalable IoT/M2M Platforms
    (2017-01-01)
    de la Bastida, David
    ;
    Lin, Fuchun Joseph
    ;
    資訊工程學系
    ;
    電機資訊國際碩士學位學程
    ;
    Department of Computer Science
    The IoT/M2M platforms are emerging to provide a common service layer for various types of new IoT applications. It is foreseen billions of IoT/M2M devices will soon be connected to those IoT/M2M platforms hosted in the cloud. In this research we propose a highly scalable OpenStack-based architecture for IoT/M2M platforms. Our unique contribution consists of leveraging the advanced functionalities of OpenStack to introduce a master node specifically designed for IoT/M2M scalability in the cloud and a load balancing queue node cooperating with the master node for fair distribution of incoming traffic among platform nodes. Using four different types of IoT/M2M applications: smart meter, Bluetooth tags, eHealth, and video, we show that compared to LBAAS and Heat that are OpenStack native load balancing and scalability functions, in most cases our proposed system is capable of achieving the fastest response time and the lowest computational cost with acceptable tradeoff of more energy consumption.
  • Thumbnail Image
    Item type:Item,
    Web Resource Cacheable Edge Device in Fog Computing
    (2016-01-01)
    Fan, Chih-Tien
    ;
    Wu, Zong-You
    ;
    Chang, Che-Pin
    ;
    Yuan, Shyan Ming
    ;
    資訊科學與工程研究所
    The bandwidth of the network is precious. As cloud computing provides powerful computation power and more and more devices are connected to the Internet there is a need to seek for methods to reduce the traffic. Fog computing was proposed to adding the computation and storage ability to the edge devices. The requests from the end device can be preprocessed or even responded at the edge device. In this work, the ability of Web Resource Caching is added to the edge device to serve as a caching proxy server. In order to obtain more caching storage, the end devices are also exploits to provide some caching space. As the whole caching storage is enlarged, large resource like media files are able to be cached near to the end devices once any of the end devices in the same network just recently requested it. The result shows that the proposed architecture has better downloading latency compares to the single caching proxy approach.
  • Thumbnail Image
    Item type:Item,
    High Scalability for Cloud-Based IoT/M2M Systems
    (2016)
    Cerritos, Eduardo
    ;
    Lin, Fuchun Joseph
    ;
    de la Bastida, David
    ;
    資訊工程學系
    ;
    電機資訊國際碩士學位學程
    International standards such as ETSI SmartM2M and oneM2M have defined a client-server model as the common service architecture for IoT/M2M systems. Moreover, the IoT/M2M servers are normally provisioned in a cloud environment. This paper proposes a highly scalable architecture for all such cloud-based IoT/M2M systems. The uniqueness of our architecture is the incorporation of a Master Node in the cloud that is aware of system resources and incoming traffic so that it not only can dynamically decide load balancing policies but also proactively react to scalability needs. When compared with other cloud implementations without such a Master Node, our proposed system achieves faster response time and lower energy consumption.