<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.Edge computing

Search Results

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item type:Item,
    ECOMSNet - An edge computing-based sensory network for real-time water level prediction and correction
    (2020-09-01)
    Yang, Tsun-Hua
    ;
    Wang, Chia-Wei
    ;
    Lin, Sheng-Jhe
    ;
    土木工程學系
    ;
    Department of Civil Engineering
    Water level monitoring and forecasting are essential tasks in flood emergency response. This study proposes an Edge COMputing-based Sensory NETwork (ECOMSNet), an innovative decentralized early warning system (EWS), for water level monitoring and prediction. A sensor-embedded algorithm integrates the direct step method (DSM) with a microgenetic algorithm (MGA). This algorithm predicts the water surface profile and corrects it once water level observations are available. It also meets efficiency requirements to accommodate sensor computation limitations. The errors in the predicted water surface profiles in channels with gradually varied flows are 5% in a laboratory flume experiment and below 10% in a field experiment. The ECOMSNet is an achievement of edge computing-based Internet of Things. It shows potential to increase emergency response efficiency. However, the system requires further refinement and testing if it is to adequately address rapidly varied unsteady flow in a scaled-up implementation.
  • Thumbnail Image
    Item type:Item,
    Network reliability evaluation for a distributed network with edge computing
    (2020-09-01)
    Huang, Cheng-Fu
    ;
    Huang, Ding-Hsiang
    ;
    Lin, Yi-Kuei
    ;
    工業工程與管理學系
    ;
    Department of Industrial Engineering and Management
    Reliability and speed are crucial for ensuring robustness in a computer network, which is used for sharing information and resources within a business. The two most recent and important developments in the field of computing are cloud computing and edge computing. In this study, a modern distributed network comprising computers, internet of things (IoT), edge servers, and cloud servers for data transmission was investigated. A distributed network can be modeled as a graph with nodes and arcs, in which each arc represents a transmission line, and each node represents an IoT device, an edge server, or a cloud server. The data are transmitted through these transmission lines which are combined with numerous physical lines such as fiber cables. Therefore, each transmission line has several possible capacities and the capacity of each arc in the distributed network can be regarded as a multistate. Such the distributed network is called a multi-state distributed network (MDN). In an MDN, the data produced by IoT devices are transmitted to the edge servers. After being processed and compressed by the edge servers, the data are then transmitted to the cloud servers for advance computing. The purpose of this study is to first construct a model of a network in order to elucidate the flow relationship among the IoT devices, edge servers, and cloud servers and subsequently develop an algorithm to evaluate network reliability, which is the probability of the data being successfully processed by the MDN.
  • Thumbnail Image
    Item type:Item,
    Resource provisioning towards OPEX optimization in horizontal edge federation
    (2020-05-15)
    Baghban, Hojjat
    ;
    Huang, Ching-Yao
    ;
    Hsu, Ching-Hsien
    ;
    電子工程學系及電子研究所
    ;
    電機工程學系
    Energy consumption is a key performance metric in multi-access edge computing (MEC) system. Therefore, minimizing consumed energy cost is critically essential. The 5G networks deal with edge computing resources so that the operator would face with power supply limitation. Therefore, it may not be able to provide sufficient resources to ever-increasing user's requests. One way to compensate such limitation is to form horizontal edge federation (HEF) so that all participant can share the resource capacities as well as request workloads. Energy efficient and ultra-low latency HEF involves the setting of critical factor in each participant: offloading ratios. The decided offloading ratios must provide satisfactory service level to meet latency and physical resource types capacity constraints demanded by requests. Our proposed problem is an energy efficient operational cost (eOPEX) optimization problem. In this paper, we formulate it as a mixed integer linear program and demonstrate that the problem is NP-hard and proposed a federated multidimensional fractional knapsack based algorithm (FMFK) as our approach. The result shows that the horizontal edge federation based on the FMFK performs better and saves the more e-OPEX as well as serving more input requests compare with the non-federation approach. The experimental results show that our approach save about 40% of e-OPEX specially for high latency sensitive application requests in hotspot zone. It shows around 50% e-OPEX saving in the case of high computation unit cost compare with non-federation approach.
  • Thumbnail Image
    Item type:Item,
    Transparent AAA Security Design for Low-Latency MEC-Integrated Cellular Networks
    (2020-03-01)
    Li, Chi-Yu
    ;
    Lin, Ying-Dar
    ;
    Lai, Yuan-Cheng
    ;
    Chien, Hsu-Tung
    ;
    Huang, Yu-Sheng
    Multi-access edge computing (MEC) is a key enabler for low-latency services in the cellular network. It enables service requests to be served at the edge without reaching the Internet. However, this service model allows data traffic to bypass conventional security functions deployed at the core network, and may pose security threats. To examine its security impact, we analyze current security functions that span authentication, authorization, accounting (AAA), and access control, and then identify two major issues. First, conventional user authentication methods prevent MEC applications from achieving low-latency service offering. Second, current cellular authorization, accounting, and access control mechanisms hardly secure MEC traffic. We thus propose a transparent security design called MECsec to secure the MEC with low latency in the cellular network. It contains three main components: cellular-based OpenID Connect (OIDC) authentication, bitmap-based authorization/accounting, and two-tier hash-based access control. Especially, its transparent design does not need any changes on current cellular operations, and is standard-compliant. We implement and evaluate the MECsec prototype on an MEC-integrated LTE network architecture developed based on the OpenAirInterface (OAI) cellular platform. Our results show that the cellular-based OIDC can reduce delays of current authentication methods by up to 88.3%, and the other components can successfully defend against possible threats with negligible overhead.
  • Thumbnail Image
    Item type:Item,
    Workload and Capacity Optimization for Cloud-Edge Computing Systems with Vertical and Horizontal Offloading
    (2020-03-01)
    Thai, Minh-Tuan
    ;
    Lin, Ying-Dar
    ;
    Lai, Yuan-Cheng
    ;
    Chien, Hsu-Tung
    ;
    交大名義發表
    A collaborative integration between cloud and edge computing is proposed to be able to exploit the advantages of both technologies. However, most of the existing studies have only considered two-tier cloud-edge computing systems which merely support vertical offloading between local edge nodes and remote cloud servers. This paper thus proposes a generic architecture of cloud-edge computing with the aim of providing both vertical and horizontal offloading between service nodes. To investigate the effectiveness of the design for different operational scenarios, we formulate it as a workload and capacity optimization problem with the objective of minimizing the system computation and communication costs. Because such a mixed-integer nonlinear programming (MINLP) problem is NP-hard, we further develop an approximation algorithm which applies a branch-and-bound method to obtain optimal solutions iteratively. Experimental results show that such a cloud-edge computing architecture can significantly reduce total system costs by about 34%, compared to traditional designs which only support vertical offloading. Our results also indicate that, to accommodate the same number of input workloads, a heterogeneous service allocation scenario requires about a 23% higher system costs than a homogeneous scenario.