簡易檢索 / 詳目顯示

回結果列表
研究生： 楊雅嵐
Yang, Ya-Lan
論文名稱： 智慧家庭電力管理系統之監控與電器排程
Smart Home Energy Management System for Monitoring and Scheduling of Home Appliances
指導教授： 楊竹星
Yang, Chu-Sing
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 電腦與通信工程研究所
Institute of Computer & Communication Engineering
論文出版年： 2014
畢業學年度： 102
語文別： 英文
論文頁數： 51
中文關鍵詞： 智慧家庭電能管理系統 、粒子群聚演算法 、排程管理最佳化
外文關鍵詞： Home energy management system, particle swarm optimization, scheduling
相關次數： 點閱：124  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 由於現今對能源議題的重視，智慧家庭電力管理的相關技術成為未來發展的重要趨勢之一。而如何能將智慧計算的技術運用家庭用電管理，以達到舒適、節能、節費及安全的目標，即是考量的議題。
    本論文中，提出一智慧家庭的電能管理系統，此系統透過情境感知、統計分析、啟發式演算法的技術，分析各電器使用情形及歷史，自動將電器分類且訂定不同用電規則，在符合使用者自訂的特殊限制下，以期達到電費與用電能量最小化。加上再生能源的發展日趨重要，此系統亦考量家庭中有一電池管理系統，可由再生能源與市電充電，並透過預測與排程管理，及參考電價收費模式，有效地降低用電費用或提供使用者用電建議。
    除了控制用電成本的策略，本系統亦監控家庭用電安全，系統透過用電歷史資訊分析的學習，偵測到用電緊急危險時，可以自動及時處理與通報，避免災害發生。

    Due to the great emphasis on energy issues, smart home technology has become one of the current trends in power management. It is considered that how to implement the computational intelligence technologies into home energy management so as to achieve comfortable environments, saving energy and costs as well as safety.
    This thesis proposes a smart home energy management system (HEMS). This system analyzes the electrical usage and history of all household appliances through context-aware technologies, meta-heuristics algorithms and statistical analysis. It automatically classifies the household appliances and sets usage rules under user-defined limits in order to minimize the energy usage. Furthermore, the development of renewable energy is increasingly important, so this home energy management system also takes the battery management system (BMS) which can be recharged from renewable energy and mains electricity into consideration. Referring to the electricity tariff, this system can reduce electricity costs efficiently and provide users appliances usage recommendations by forecasting approaches and scheduling management.
    In addition to controlling the cost of energy usage, the system also monitors the condition of household electricity to insure the safety. Training through historical power usage information and analysis, the system can detect abnormal situations and automatically handle the emergency as well as notify the users to prevent damage and loss.

    Contents 摘要 .............. i Abstract ............... ii Acknowledgements ............ iv Contents .............. v List of Figures ............viii List of Tables .............. ix Chapter 1 Introduction ............ 1 1.1 Background Information .......... 1 1.2 Motivations and Research Objectives ...... 2 1.2.1 Online database ......... 2 1.2.2 Power usage strategy ......... 3 1.2.3 Safety of Electricity Usage ........ 3 1.3 Contribution of the Thesis ........ 4 1.4 Organization of the Thesis ........ 5 Chapter 2. Related Works ........... 6 2.1 Home Energy Management System ....... 6 2.1.1 Smart Grid .......... 6 2.1.2 Home Energy Management System ...... 7 2.2 Data Mining ............ 10 2.2.1 Introduction .......... 10 2.2.2 Data Mining Technologies for HEMS ..... 15 2.3 Scheduling ............ 16 2.3.1 Introduction ......... 16 2.3.2 Scheduling for HEMS ......... 17 2.4 Electricity Tariff ........... 18 2.4.1 Common Electricity Tariffs ....... 18 2.4.2 Electricity Tariff of Taiwan Power Company ..... 20 Chapter 3. The Proposed Algorithm ......... 24 3.1 Overview of System Architecture ....... 24 3.1.1 Scenario............ 24 3.1.2 HEMS System Architecture ....... 25 3.2 Prediction ............ 26 3.2.1 Introduction of Particle Swarm Optimization .... 26 3.2.2 Prediction for Power Consumption...... 28 3.2.3 Prediction for PV Energy Generation ...... 30 3.3 Clustering for Household Appliances ....... 31 3.4 Electrical Safety Monitoring ......... 35 3.5 Scheduling for Household Appliances ........ 38 3.6 Power Charge of BMS .......... 39 Chapter 4. Simulation Results .......... 41 4.1 Power Dataset ........... 41 4.1.1 Residential Consumption Dataset ...... 41 4.1.2 PV Generation Dataset ......... 41 4.2 Prediction Module Evaluation ........ 42 4.2.1 Prediction Approach ........ 42 4.2.2 Prediction Results for Residential Consumption ..... 44 4.2.3 Prediction Result for PV Generation ....... 46 Chapter 5. Conclusions and Future Prospects ........ 48 5.1 Conclusions ........... 48 5.2 Future Prospects .......... 48 References ............. 50

    1. Savio, D., L. Karlik, and S. Karnouskos, Predicting energy measurements of service-enabled devices in the future smartgrid, in International Conference on Computer Modelling and Simulation. 2010.
    2. Basu, K., V. Debusschere, and S. Bacha, Appliance Usage Prediction Using a Time Series Based Classifi cation Approach in IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society. 2012.
    3. Rahayu, D., Balakrishnan, and S. Krishnaswamy, Learning to Be Energy-Wise: Discriminative Methods for Load Disaggregation, in Future Energy Systems: Where Energy, Computing and Communication Meet (e-Energy). 2012.
    4. Kalogridis, G. and S.Z. Denic, Data Mining and Privacy of Personal Behaviour Types in Smart Grid, in Data Mining Workshops (ICDMW). 2011.
    5. Veleva, S. and D. Davcev, Data Mining as an Enabling Technology for Home Energy Management System, in IEEE PES Innovative Smart Grid Technologies. 2012.
    6. Shiba, M., et al., Factor Analysis in Home Energy Consumption by Information Entropy and Bayesian Network in International Symposium on Aware Computing. 2010.
    7. Wicaksono, H., S. Rogalski, and E. Kusnady. Knowledge-based Intelligent Energy Management Using Building Automation System. in INTERNATIONAL POWER ELECTRONICS CONFERENCE. 2010.
    8. Yu, T., D.S. Kim, and S.-Y. Son, Home Appliance Scheduling Optimization with Time-Varying Electricity Price and Peak Load Limitation Information and Software Technology, 2013. 23: p. 196-199.
    9. Sou, K.C., et al., Scheduling Smart Home Appliances Using Mixed Integer Linear Programming, in 50th IEEE Conference on Decision and Control and European Control Conference. 2011: Orlando, FL, USA.
    10. Giorgio, S., OPTIMAL SCHEDULING OF SMART HOME APPLIANCES USING MIXED-INTEGER LINEAR PROGRAMMING. 2013, UNIVERSITA DEGLI STUDI DI PADOVA.
    11. Eßer, A., et al. Scheduling of Electrical Household Appliances with Price Signals. in Operations Research. 2007.
    12. Chen, X., T. Wei, and S. Hu, Uncertainty-Aware Household Appliance Scheduling Considering Dynamic Electricity Pricing in Smart Home. IEEE TRANSACTIONS ON SMART GRID, 2013. 4.
    13. Lin, C.-I., Home Energy Management System Considering Forecasting System and Appliance Scheduling, in Electrical Engineering. 2012, National Cheng Kung University: Tainan, Taiwan. p. 118.
    14. Sou, K.C., et al. Energy and CO 2 efficient scheduling of smart home appliances in the Stockholm Royal Seaport in HYCON2 Workshop on Energy. 2012.
    15. Chen, C., et al., A Communication-Based Appliance Scheduling Scheme for Consumer-Premise Energy Management Systems. IEEE Transactions on Smart Grid, 2013.

    無法下載圖示 校內：2024-12-31公開
    校外：不公開
    電子論文尚未授權公開，紙本請查館藏目錄
    QR CODE