簡易檢索 / 詳目顯示

回結果列表
研究生： 翁介誠
Weng, Chieh-Cheng
論文名稱： 舒適感知學習下的電力需求減少最佳化
Optimization of Electricity Demand Reduction with Comfort Conscious Learning
指導教授： 莊坤達
Chuang, Kun-Ta
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 資訊工程學系
Department of Computer Science and Information Engineering
論文出版年： 2020
畢業學年度： 108
語文別： 英文
論文頁數： 37
中文關鍵詞： 需量反應 、住戶舒適度 、反饋學習
外文關鍵詞： Demand Response, Resident Comfort, Feedback Learning
相關次數： 點閱：118  下載：6 
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

    • 在全球氣候變化，溫室效應和環境保護意識增強的情況下，增加來自供應方的電力供應變得越來越困難。需量反應用於指導客戶管理用電量，並以金錢獎勵或電價降低的形式提供激勵措施，以誘使客戶改變其用電習慣並減少用電高峰，從而避免電力系統過載和維持可靠的供電。

    家庭的控制器集成了需量反應工具，該工具可以轉移和減少需求以改善家庭能耗。但控制器在控制電器時，必須顧及住戶的舒適度，如果一昧地將電器全部關閉，雖會最節能，但會導致住戶參與需求響應的意願下降。而每個人認為的生活舒適都不同，不能以同一標準做衡量，由於住戶的喜好，活動和需求各異，我們的方法用個人化的舒適對住戶的舒適度作衡量。在本論文中，我們提出PCF框架，藉由住戶舒適或不舒適的反饋來讓控制器學習最佳的控制方式，同時考慮住戶的舒適度及節能，在執行需求響應時，不會讓住戶感到不舒適。

    在模擬實驗中，我們使用住家的用電紀錄，模擬住戶的反饋行為，以顯示PCF框架的效能，結果顯示我們提出的方法可以使住戶在獲得需求響應的獎勵時，保有舒適度。同時我們也從不同面向來探討方法的效能，包括在不同家庭的表現，以及不同的參數設定。

    With global climate change, the greenhouse effect, and increased environmental awareness, it is becoming more difficult to increase power supply from the power supply side. Demand Response is used to guide customers to manage their electricity consumption and provide incentives in the form of monetary incentives or tariff reductions to induce customers to change their consumption habits and reduce peaks, thereby avoiding overloading the system and maintaining a reliable supply of electricity. The household controller integrates a Demand Response tool that can shift and reduce demand to improve energy consumption. However, the controller must take into account the comfort of the resident when controlling appliances, as turning them off completely, although the most energy-efficient, will result in a reduced willingness to engage in Demand Response. As everyone's perceived living comfort is different and cannot be measured by the same standard, due to the different preferences, activities, and needs of the occupants, our approach is to measure the comfort of the occupants in terms of personalized comfort. In this paper, we propose the PCF framework, in which the controller learns the best way to control the occupants by their comfort or discomfort feedback, taking into account their comfort and energy saving. In simulation experiments, we simulate the resident feedback behavior using the electricity consumption record to show the effectiveness of the PCF framework, and the results show that our proposed approach can enable the resident to retain comfort while being rewarded for Demand Response.

    中文摘要 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . i Abstract . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ii Acknowledgment . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iii Contents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iv List of Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vii List of Figures . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . viii 1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.1 Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.3 Challenge . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 2 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.1 Residential Demand Response Objectives . . . . . . . . . . . . . . . . . . . . . . 6 2.1.1 Cost . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.1.2 Well-being . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.1.3 Load Profiling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 2.1.4 Emission . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 2.2 Energy Systems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 2.2.1 HVAC and DHW . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 2.2.2 Smart Appliance . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 2.2.3 Electric Vehicle . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 2.2.4 Energy Storage . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 3 Problem Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 3.1 Demand Response Event . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 3.2 Problem Statement . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 4 Methodology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 4.1 Personalized Comfort Feedback Framework . . . . . . . . . . . . . . . . . . . . . 17 4.1.1 Flow . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 4.1.2 Pseudo-action . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 4.2 Feedback Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 4.2.1 Policy Gradient . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 4.2.2 Proximal Policy Optimization . . . . . . . . . . . . . . . . . . . . . . . . 21 5 Experiments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 5.1 Simulation Setting . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 5.1.1 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 5.1.2 Simulated Feedback . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 5.1.3 Evaluation Metric . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 5.2 Evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 5.2.1 Optimized appliance consumption . . . . . . . . . . . . . . . . . . . . . . 27 5.2.2 Effect of pseudo-action . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 5.2.3 Different weight coefficient of reward . . . . . . . . . . . . . . . . . . . . 30 5.2.4 Different random variable of feedback . . . . . . . . . . . . . . . . . . . . 30 6 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32 Bibliography . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33

    [1] G. Barone, A. Buonomano, F. Calise, C. Forzano, and A. Palombo, “Building to vehicle to building concept toward a novel zero energy paradigm: Modelling and case studies,” Renewable and Sustainable Energy Reviews, vol. 101, pp. 625–648, 2019.
    [2] M. H. Albadi and E. F. El-Saadany, “A summary of demand response in electricity markets,” Electric power systems research, vol. 78, no. 11, pp. 1989–1996, 2008.
    [3] G. Wilkenfeld, “Demand response: a national strategy to address air conditioner peak load,” Sydney, Equipment Energy Efficiency Committee (E3): 50pp, 2006.
    [4] S. Borenstein, M. Jaske, and A. Rosenfeld, “Dynamic pricing, advanced metering, and demand response in electricity markets,” 2002.
    [5] A. Faruqui and S. Sergici, “Household response to dynamic pricing of electricity a survey of seventeen pricing experiments,” Journal Vol, vol. 20, no. 8, pp. 68–77, 2007.
    [6] S. P. Holland and E. T. Mansur, “Is real-time pricing green? the environmental impacts of electricity demand variance,” The Review of Economics and Statistics, vol. 90, no. 3, pp. 550–561, 2008.
    [7] A.-H. Mohsenian-Rad and A. Leon-Garcia, “Optimal residential load control with price prediction in real-time electricity pricing environments,” IEEE transactions on Smart Grid, vol. 1, no. 2, pp. 120–133, 2010.
    [8] I. E. Haukeli, “Smart grid-the effect of increased demand elasticity at the system level,” Master’s thesis, Institutt for elkraftteknikk, 2011.
    [9] G. T. Costanzo, G. Zhu, M. F. Anjos, and G. Savard, “A system architecture for autonomous demand side load management in smart buildings,” IEEE transactions on smart grid, vol. 3, no. 4, pp. 2157–2165, 2012.
    [10] C. Clastres, T. H. Pham, F. Wurtz, and S. Bacha, “Ancillary services and optimal household energy management with photovoltaic production,” Energy, vol. 35, no. 1, pp. 55–64, 2010.
    [11] K. M. Tsui and S.-C. Chan, “Demand response optimization for smart home scheduling under real-time pricing,” IEEE Transactions on Smart Grid, vol. 3, no. 4, pp. 1812–1821, 2012.
    [12] O. A. Sianaki and M. A. Masoum, “A multi-agent intelligent decision making support system for home energy management in smart grid: A fuzzy topsis approach,” Multiagent and Grid Systems, vol. 9, no. 3, pp. 181–195, 2013.
    [13] C. O. Adika and L. Wang, “Autonomous appliance scheduling for household energy management,” IEEE transactions on smart grid, vol. 5, no. 2, pp. 673–682, 2013.
    [14] M. Ilic, J. W. Black, and J. L. Watz, “Potential benefits of implementing load control,” in 2002 IEEE Power Engineering Society Winter Meeting. Conference Proceedings (Cat. No. 02CH37309), vol. 1. IEEE, 2002, pp. 177–182.
    [15] S. Tiptipakorn and W.-J. Lee, “A residential consumer-centered load control strategy in real-time electricity pricing environment,” in 2007 39th North American power symposium. IEEE, 2007, pp. 505–510.
    [16] P. Constantopoulos, F. C. Schweppe, and R. C. Larson, “Estia: A real-time consumer control scheme for space conditioning usage under spot electricity pricing,” Computers & operations research, vol. 18, no. 8, pp. 751–765, 1991.
    [17] M. A. A. Pedrasa, T. D. Spooner, and I. F. MacGill, “Coordinated scheduling of residential distributed energy resources to optimize smart home energy services,” IEEE Transactions on Smart Grid, vol. 1, no. 2, pp. 134–143, 2010.
    [18] A. Agnetis, G. De Pascale, P. Detti, and A. Vicino, “Load scheduling for household energy consumption optimization,” IEEE Transactions on Smart Grid, vol. 4, no. 4, pp. 2364–2373, 2013.
    [19] K. Mets, T. Verschueren, F. De Turck, and C. Develder, “Exploiting v2g to optimize residential energy consumption with electrical vehicle (dis) charging,” in 2011 IEEE first international workshop on smart grid modeling and simulation (SGMS). IEEE, 2011, pp. 7–12.
    [20] E. Matallanas, M. Castillo-Cagigal, A. Gutiérrez, F. Monasterio-Huelin, E. Caama˜noMart´ın, D. Masa, and J. Jiménez-Leube, “Neural network controller for active demand-side management with pv energy in the residential sector,” Applied Energy, vol. 91, no. 1, pp. 90–97, 2012.
    [21] M. C. Bozchalui, S. A. Hashmi, H. Hassen, C. A. Canizares, and K. Bhattacharya, “Optimal operation of residential energy hubs in smart grids,” IEEE Transactions on Smart Grid, vol. 3, no. 4, pp. 1755–1766, 2012.
    [22] S. Liu and G. P. Henze, “Evaluation of reinforcement learning for optimal control of building active and passive thermal storage inventory,” 2007.
    [23] B. Sun, P. B. Luh, Q.-S. Jia, and B. Yan, “Event-based optimization within the lagrangian relaxation framework for energy savings in hvac systems,” IEEE Transactions on Automation Science and Engineering, vol. 12, no. 4, pp. 1396–1406, 2015.
    [24] D. O’Neill, M. Levorato, A. Goldsmith, and U. Mitra, “Residential demand response using reinforcement learning,” in 2010 First IEEE international conference on smart grid communications. IEEE, 2010, pp. 409–414.
    [25] B.-G. Kim, Y. Zhang, M. Van Der Schaar, and J.-W. Lee, “Dynamic pricing and energy consumption scheduling with reinforcement learning,” IEEE Transactions on Smart Grid, vol. 7, no. 5, pp. 2187–2198, 2015.
    [26] S. Bahrami, V. W. Wong, and J. Huang, “An online learning algorithm for demand response in smart grid,” IEEE Transactions on Smart Grid, vol. 9, no. 5, pp. 4712–4725, 2017.
    [27] A. Sheikhi, M. Rayati, and A. M. Ranjbar, “Demand side management for a residential customer in multi-energy systems,” Sustainable cities and society, vol. 22, pp. 63–77, 2016.
    [28] I. Dusparic, C. Harris, A. Marinescu, V. Cahill, and S. Clarke, “Multi-agent residential demand response based on load forecasting,” in 2013 1st IEEE conference on technologies for sustainability (SusTech). IEEE, 2013, pp. 90–96.
    [29] A. Taylor, I. Dusparic, E. Galvan-Lopez, S. Clarke, and V. Cahill, “Accelerating learning in multi-objective systems through transfer learning,” in 2014 International joint conference on neural networks (IJCNN). IEEE, 2014, pp. 2298–2305.
    [30] C. Jiang, Z. Jing, X. Cui, T. Ji, and Q. Wu, “Multiple agents and reinforcement learning for modelling charging loads of electric taxis,” Applied Energy, vol. 222, pp. 158–168, 2018.
    [31] H. Berlink, N. Kagan, and A. H. R. Costa, “Intelligent decision-making for smart home energy management,” Journal of Intelligent & Robotic Systems, vol. 80, no. 1, pp. 331–354, 2015.
    [32] D. Li and S. K. Jayaweera, “Reinforcement learning aided smart-home decision-making in an interactive smart grid,” in 2014 IEEE Green Energy and Systems Conference (IGESC). IEEE, 2014, pp. 1–6.
    [33] P. Kofinas, A. Dounis, and G. Vouros, “Fuzzy q-learning for multi-agent decentralized energy management in microgrids,” Applied energy, vol. 219, pp. 53–67, 2018.
    [34] R. S. Sutton, D. A. McAllester, S. P. Singh, and Y. Mansour, “Policy gradient methods for reinforcement learning with function approximation,” in Advances in neural information processing systems, 2000, pp. 1057–1063.
    [35] J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, “Proximal policy optimization algorithms,” arXiv preprint arXiv:1707.06347, 2017.
    [36] S. Barker, A. Mishra, D. Irwin, E. Cecchet, P. Shenoy, J. Albrecht et al., “Smart*: An open data set and tools for enabling research in sustainable homes,” SustKDD, August, vol. 111, no. 112, p. 108, 2012.
    [37] T. Cover and P. Hart, “Nearest neighbor pattern classification,” IEEE transactions on information theory, vol. 13, no. 1, pp. 21–27, 1967.
    [38] “Temporary electricity consumption reduction measures, limited power feedback model,” Taiwan Power Company. [Online]. Available: https://www.taipower.com.tw/upload/135/2018071708513325281.pdf

    下載圖示
    2022-12-31公開
    QR CODE