English  |  正體中文  |  简体中文  |  Items with full text/Total items : 68069/68069 (100%)
Visitors : 23145545      Online Users : 372
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version


    Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/81902


    Title: 基於機器學習的LED照明調控機制:以智慧農場為實施例;LED Dimming Control Mechanism Based on Machine Learning:A Practical Case in Smart Farms
    Authors: 鄧博謙;Teng, Po-Chien
    Contributors: 通訊工程學系
    Keywords: 機器學習;物聯網;machine learing;IoT
    Date: 2019-12-20
    Issue Date: 2020-01-07 14:32:51 (UTC+8)
    Publisher: 國立中央大學
    Abstract: 隨著當代用電量的需求逐漸地提高,能源消耗過度的議題與提升能源使用效
    率的研究因而開始受到重視。然而,若僅依靠人力進行能源的管理與配置,將大幅降
    低能源使用效率與決策的即時性。近年來,有鑑於物聯網技術發展的蓬勃發展,產、
    官、學、業界開始將物聯網技術應用在民眾的生活中,如智慧農場、智慧家庭與智慧
    電表等。透過物聯網技術監控環境的變化與影響,不僅可以有效地使用能源,同時亦
    降低能源管理的成本。因此,物聯網技術與能源管理的結合,儼然成為提升能源使用
    效率的議題上重要的解決方法之一。在本論文中,我們針對智慧農場的能源管理情
    境,設計一套結合物聯網技術的智慧調光系統,此系統由三個子系統所組成,分別為
    物聯網設備端、使用者端以及雲端。為了達到增加增加農場管理的效率以及加強調光
    的精確性及能源效率之目的,此系統同時導入及整合低功耗通訊技術傳輸、能源監控
    裝置、雲端整合性服務平台以及類神經網路演算法等四項功能模組。
    在本論文中設計的三個子系統中,首先,物聯網設備端透過多種異質感測器(如:
    色彩感測器、溫溼度感測器、電子計量器等等)感測農場內環境的變化後,閘道器
    藉由低功耗通訊傳輸技術MQTT將感測資料上傳至雲端平台進行資料圖形化呈現與
    資料儲存,並且可以接收由使用者端與雲端控制裝置的開關以及調整LED的亮度;
    再者,在雲端方面,我們選擇Microsoft開發的Azure雲端整合性平台,於虛擬機中建
    構Node-RED平台作為本系統的開發工具,連接三個子系統。最後,在使用者端中,使
    用者能夠即時透過Node-RED平台中設計的圖形化界面存取需要的資訊並進行遠端的
    控制與管理,進而實現了物聯網雙向傳輸架構以及垂直整合的服務。此外,本論文導
    入GRNN神經網路以協助計算室內光與陽光互補的最佳配置策略。透過GRNN神經網
    路,系統將判斷當前環境下是否需要調整光源,並針對個別區域計算出最佳的PWM調
    光值,達到於調光的即時性、能源消耗以及維持光源供給的穩定性等三者間的平衡。
    最後,透過本論文的系統設計,我們期望以基於物聯網技術的整合性服務提供使用者
    隨時隨地能遠端監控與管理農場內的情況,並依照外部光源變化能即時、精準的進行
    互補調光,以最低的能源消耗成本實現亮度供給的最佳化。在未來的研究中,本論文
    期能在智慧家庭的環境下,將本文設計的系統結合能源管理系統(HEMS)的應用,達到
    同時減少家用照明設備的能源消耗以及優化光源供應的目的。;With the increasing demand of electricity consumption, the issue of excessive energy
    consumption and the study of improving energy e ciency have been receive more atten-
    tion. However, relying solely on human resources for energy management and allocation
    will signi cantly reduce the e ciency of energy use and the immediacy of decision-making.
    In recent years, in view of the rapid development of Internet of things technology, indus-
    try, government, academic and industrial sectors have begun to apply IoT technology
    in people′s life, such as smart farms, smart homes and smart meters,etc. Monitoring
    environmental changes and impacts through IoT technology can not only e ectively use
    energy, but also reduce the cost of energy management. Therefore, the combination of
    Internet of things technology and energy management has become one of the important
    solutions to improve energy e ciency . In this paper, we design a smart dimming system
    that combines IoT technology for the energy management scenario of smart farms. This
    system consists of three subsystems, namely the IoT device end, the user end and the
    cloud. In order to increase the e ciency of farm management and enhance the accuracy
    of light regulation and energy e ciency, this system simultaneously introduces and inte-
    grates four functional modules, including low-power communication technology , energy
    monitoring device, cloud integrated service platform and neural network algorithm.
    In this thesis design of three subsystems, rst of all, the Internet of things devices
    through a variety of heterogeneous sensors (such as: colour sensor, the temperature and
    humidity sensors, electronic meter, etc.) after sensing changes in the environment on the
    farm, gateway will upload sensing data to the cloud platform by low power communication
    transmission technology MQTT for graphical representations and data storage, and it
    can receive by the end user and the cloud control switch and adjust the LED brightness ;
    Furthermore, in the cloud-end, we choose the Azure cloud platform developed by Microsoft
    and build Node-RED platform in the virtual machine as the development tool of the
    system, which connect three subsystems. Finally, in the user -end, users can access the
    required information, control and manage IoT devices remotely through the graphical
    interface designed in Node-RED platform, thus realizing the bidirectional transmission
    architecture of the IoT and vertically integrated services. In addition, GRNN neural
    network is introduced in this paper to help calculate the optimal allocation strategy of
    light and sunlight complementing each other. Through GRNN neural network, the system
    will judge whether the light source needs to be adjusted in the current environment, and
    calculate the best PWM dimming value for certain regions, so as to achieve the balance
    among the immediacy of dimming, energy consumption and stability of the light source
    supply. Finally, through the system design of this paper, we expect to provide users
    with integrated services based on the Internet of things technology to remotely monitor
    and manage the situation in the farm at any time and anywhere, and make timely and
    accurate complementary dimming according to the change of external light source, so as
    to optimize the brightness supply with the lowest energy consumption cost. In the future
    research, this paper is expected to combine the system designed in this paper with the
    application of energy management system (HEMS) in the smart home environment, so as
    to achieve the purpose of simultaneously reducing the energy consumption of household
    lighting equipment and optimizing the supply of light source.
    Appears in Collections:[通訊工程研究所] 博碩士論文

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML45View/Open


    All items in NCUIR are protected by copyright, with all rights reserved.

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback  - 隱私權政策聲明