政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/142380
English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  全文筆數/總筆數 : 113873/144892 (79%)
造訪人次 : 51936319      線上人數 : 410
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜尋範圍 查詢小技巧：
  • 您可在西文檢索詞彙前後加上"雙引號"，以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋，建議至進階搜尋限定作者欄位，可獲得較完整資料
    •  進階搜尋
    政大機構典藏 > 資訊學院 > 資訊科學系 > 會議論文 >  Item 140.119/142380


    請使用永久網址來引用或連結此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/142380


    題名: Using Deep Q-Network in Bandwidth Allocation of Smart Homes
    作者: 張宏慶
    Jang, Hung-Chin
    Chiu, Chr-Jr
    貢獻者: 資科系
    關鍵詞: Deep Q-Network;Bandwidth Allocation;Smart Home
    日期: 2021-10
    上傳時間: 2022-10-07 14:41:38 (UTC+8)
    摘要: Smart homes provide users with a more convenient, comfortable, and safe living environment through various automation equipment, high-tech home appliances, and network services. With the development of the Internet of Things and widespread smart home, there are many Internet-enabled services in smart homes. Each kind of service has distinct service quality requirements. Remote disaster warning and remote monitoring and detection service emphasize realtime and reliability. UHD video (4K/8K) and VR /AR services require high transmission bandwidth. As the number of IoT-enabled equipment of smart homes increases, it becomes imperative to effectively allocate limited bandwidth resources and improve the overall network performance to ensure the effectiveness of various services. From the perspective of Internet service providers (ISP), this research studied deep reinforcement learning techniques cooperating with software-defined networks (SDN) to improve traditional smart homes` bandwidth management architecture and bandwidth allocation method. The SDN architecture separates the control plane and the data plane. It centralizes the control mechanism to simplify and support flexible network management. Deep reinforcement learning does not rely on labeled data instead of exploring the unknown environment and the environment`s feedback on current as the basis for the subsequent action. This study used SDN to simulate the network environment from smart homes to an ISP. Due to the lack of a sufficient amount of labeled data, and it is not easy to establish a standard for data labeling, we used the Deep Q-network (DQN) of deep reinforcement learning in the bandwidth allocation for smart homes. The simulation results show that Deep Q-network can achieve high performance in both the jitter reduction ratio and the probability of successfully fulfilling bandwidth allocation termination conditions.
    關聯: 2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON), pp. 98-101
    資料類型: conference
    DOI 連結: https://doi.org/10.1109/IEMCON53756.2021.9623084
    DOI: 10.1109/IEMCON53756.2021.9623084
    顯示於類別:[資訊科學系] 會議論文

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    index.html0KbHTML2257檢視/開啟


    在政大典藏中所有的資料項目都受到原著作權保護.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回饋