跳到主要內容

臺灣博碩士論文加值系統

(44.200.101.84) 您好!臺灣時間:2023/09/25 14:11
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:寒河江智也
研究生(外文):Sagae Tomoya
論文名稱:於IotTalk平台基於強化學習之高效率電梯排程設計
論文名稱(外文):An Efficient Elevator Scheduler Design Using Reinforcement Learning in the IoTtalk Platform
指導教授:范倫達
指導教授(外文):Van, Lan-Da
口試委員:范倫達林一平李皇辰
口試委員(外文):Van, Lan-DaLin, Yi-BingLee, Huang-Chen
口試日期:2022-07-22
學位類別:碩士
校院名稱:國立陽明交通大學
系所名稱:資訊科學與工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2022
畢業學年度:110
語文別:英文
論文頁數:30
中文關鍵詞:電梯群控制排程Q學習物聯網
外文關鍵詞:Elevator Group ControlQ-learningIoT
相關次數:
  • 被引用被引用:0
  • 點閱點閱:113
  • 評分評分:
  • 下載下載:17
  • 收藏至我的研究室書目清單書目收藏:0
在本論文中,我們提出了物聯網的環境下基於強化學習的電梯排程系統.為了減少等待時間,使用者在電梯外叫電梯時,我們用Q學習的方法來分配給特定的電梯.我們把電梯跟人的狀態分了18個情況,設計了獎勵函數。模擬時我們用了16層樓跟32層樓,4台車廂的情況,訓練了上班尖峰,下班尖峰,中間尖峰,一整天的四種模型,然後跟我們實驗室之前做的減少耗能的方法比較等待時間、移動時間、耗能。我們最後得到在16層樓的上班時間的情況減少了39.5%的等待時間,32層樓的上班時間的情況減少了39.4%的等待時間。
We propose new elevator scheduling system using Q learning in IoTtalk which is a IoT platform. For reducing waiting time, when a user calls an elevator, our system assigns specific car to the user using Q-learning method. We categorize user and state situation into 18 cases and design a new reward function. We use 16-floor and 32-floor building, with 4 cars, in simulation. We train 4 models: up peak, down peak ,inter floor and all day Compared with the energy saving algorithm developed in our lab, the average waiting time can be reduced by 39.5% in 16-floor for up peak situation and 39.4% in 32-floor for up peak situation.
摘要 i
ABSTRACT ii
誌謝 iii
CONTENTS iv
LIST OF TABLES vi
LIST OF FIGURES vii
Chapter 1 Introduction 1
1.1 Motivation 2
1.2 Thesis Organization 2
Chapter 2 Background and Related Work 4
2.1 Travel Pattern 4
2.1 Related Work 4
2.3 IoTtalk Introduction 6
2.4 ElevatorTalk 6
2.5 Reinforcement Learning Introduction 8
2.5.1 Q-Learning 9
Chapter 3 Proposed method 10
3.1 Panel 10
3.2 Scheduler 12
3.3 Assign Car 13
3.3.1 Create state 13
3.3.1 Update Q-table 14
3.4 Car Schedule 16
3.5 Car 18
3.6 Design Reward Function 21
Chapter 4 Simulation and Result 23
4.1 Environment 23
4.1 Result 24
Chapter 5 Conclusion and Future Work 26
Appendix 27
Appendix A 27
Bibliography 29
Biography 30
[1] G. Barney and S. D. Santos, Elevator Traffic Analysis, Design and Conrol, 2nd ed. Stevenage, U.K.: Peregrinus, 1985.
[2] J. R. Fernandez and P. Cortes, “A survey of elevator group control systems for vertical transportation,” IEEE Control System Magzine, pp. 38-55, Aug. 2015.
[3] L. Marcus and A. Elias, “Impact of machine learning on elevator control strategies,” Technical Report, KTH Royal Institute Of Technology, 2015
[4] L. D. Van, Y. B. Lin, T. H. Wu, and T. H. Chao, “Green elevator scheduling based on IoT communications,” IEEE Access, vol. 8, pp. 38404-38415, Mar. 2020.
[5] L. D. Van, Y. B. Lin, T. H. Wu, and Y. C. Lin, “An intelligent elevator development and management system,” IEEE Systems Journal, vol. 14, no. 2, pp. 3015-3026, Jun. 2020.
[6] A. Krizhevsky, I. Sutskever, G.E.Hinton: ImageNet Classification with Deep Convolutional Neural Networks, 2012
[7] C. J. C. H. Watkins and P. Dayan. Q-learning. Machine Learning, 8:279–292, 1992.
[8] Y.-B. Lin, Y. W. Lin, C. Y. Chih, T. Y. Li, C. C. Tai, Y. C. Wang, F. J. Lin, H. C. Kuo, C. C. Huang, and S. C. Hsu, “EasyConnect: A management system for IoT devices and its applications for interactive design and art,” IEEE Internet of Things Journal, vol. 2, no. 6, pp. 551-561, Dec. 2015.
[9] Y.-B. Lin, Y. W. Lin, C. M. Huang, C. Y. Chih, and P. Lin, “IoTtalk: A management platform for reconfigurable sensor devices,” IEEE Internet of Things Journal, vol. 4, no. 5, pp. 1552-1562, Oct. 2017.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top