ارزیابی پتانسیل منابع سمت تقاضا در حضور تجهیزات سرمایشی و گرمایشی با استفاده از روش داده-کاوی مبتنی بر الگوریتم طبقه¬بندی k-means
محورهای موضوعی : مهندسی برق و کامپیوتر
فاطمه شیبانی
1
(دانشگاه سیستان و بلوچستان،دانشكده مهندسي برق و كامپيوتر)
مژگان ملاحسنی‌پور
2
(دانشگاه سیستان و بلوچستان،دانشكده مهندسي برق و كامپيوتر)
هنگامه کشاورز
3
(دانشگاه سیستان و بلوچستان،دانشكده مهندسي برق و كامپيوتر)
کلید واژه: انرژی مصرفی, پاسخگویی بار, داده‌کاوی, شبکه هوشمند, قیمت, تغییرات دمایی,
چکیده مقاله :
در بستر سیستم‌های قدرت هوشمند، تعیین پتانسیل منابع پاسخگویی تقاضا به علت اثرگذاری بر تمامی سیاست‌های تصمیم‌گیری حوزه انرژی حایز اهمیت است. در مقاله حاضر، پتانسیل منابع پاسخگویی تقاضا در حضور تجهیزات سرمایشی و گرمایشی، با استفاده از روش الگوریتم طبقه‌بندی k-means به عنوان یک روش داده‌کاوی، تعیین می‌شود. ابتدا داده‌های انرژی مصرفی در ساعات پیک دوره‌های گرم (بهار و تابستان) و دوره‌های سرد (پاییز و زمستان)، با توجه به تغییرات قیمت و دما، با استفاده از الگوریتم k-means در خوشه‌های مختلفی گروه‌بندی می‌شوند. خوشه‌هایی با امکان حضور وسایل سرمایشی و گرمایشی، انتخاب می‌شوند. سپس نمودار بازه اطمینان داده‌های انرژی مصرفی در خوشه‌های منتخب با توجه به تغییرات قیمت انرژی ترسیم می‌گردد. با توجه به فاصله کمینه و بیشینه در میانگین داده‌های موجود در آستانه بالا و آستانه متوسط نمودار بازه اطمینان، پتانسیل نامی منابع پاسخگویی تقاضا (بار انعطاف‌پذیر) به دست می‌آید. اطلاعات انرژی مصرفی، دما و قیمت انرژی شبکه برق BOSTON در یک افق زمانی شش‌ساله به منظور ارزیابی مدل پیشنهادی استفاده می‌شود.
Under the smart power systems, determining the amount of Demand Response Resources(DRRs) potential is considered as a crucial issue due to affecting in all energy policy decisions. In this paper, the potential of DRRs in presence of cooling and heating equipment are identified using k-means clustering algorithm as a data mining technique. In this regard, the energy consumption dataset are categorized in different clusters by k-means algorithm based upon variations of energy price and ambient temperature during peak hours of hot (Spring and Summer) and cold (Autumn and Winter) periods. Then, the clusters with the possibility of cooling and heating equipment’s commitment are selected. After that, the confidence interval diagram of energy consumption in elected clusters is provided based upon energy price variations. The nominal potential of DRRs, i.e. flexible load, will be obtained regarding the maximum and minimum differences between the average of energy consumption in upper and middle thresholds of the confidence interval diagram. The energy consumption, ambient temperature and energy price related to BOSTON electricity network over a six-year horizon time is utilized to evaluate the proposed model.
[1] R. Hassan and G. Radman, "Survey on smart grid," in Proc. of the IEEE SoutheastCon 2010 , SoutheastCon’10, pp. 210-213, Concord, NC, USA, 18-21 Mar. 2010.
[2] M. H. Albadi and E. F. El-Saadany, "Demand response in electricity markets: an overview," in Proc. of the IEEE Power Engineering Society General Meeting, 5 pp., Tampa, FL, USA, 24-28 Jun. 2007.
[3] F. Magnago, J. Alemany, and J. Lin, "Impact of demand response resources on unit commitment and dispatch in a day-ahead electricity market," International J. of Electrical Power & Energy Systems, vol. 68, pp. 142-149, Jun. 2015.
[4] C. Bartusch and K. Alvehag, "Further exploring the potential of residential demand response programs in electricity distribution," Applied Energy, vol. 125, pp. 39-59, 15 Jul. 2014.
[5] Z. Chen, L. Wu, and Y. Fu, "Real-time price-based demand response management for residential appliances via stochastic optimization and robust optimization," IEEE Trans. on Smart Grid, vol. 3, no. 4, pp. 1822-1831, Dec. 2012.
[6] A. Moshari, A. Ebrahimi, and M. Fotuhi-Firuzabad, "Short-term impacts of DR programs on reliability of wind integrated power systems considering demand-side uncertainties," IEEE Trans. on Power Systems, vol. 31, no. 3, pp. 2481-2490, May 2015.
[7] A. Tabandeh, A. Abdollahi, and M. Rashidinejad, "Reliability constrained congestion management with uncertain negawatt demand response firms considering repairable advanced metering infrastructures," Energy, vol. 104, pp. 213-228, 1 Jun. 2016.
[8] N. Li, L. Chen, and S. H. Low, "Optimal demand response based on utility maximization in power networks," Proc. of the IEEE Power and Energy Society General Meeting, 8 pp., Detroit, MI, USA, 24-28 Jul. 2011.
[9] W. Shi, N. Li, X. Xie, C. C. Chu, and R. Gadh, "Optimal residential demand response in distribution networks," IEEE J. on Selected Areas in Communications, vol. 32, no. 7, pp. 1441-1450, Jul. 2014.
[10] Z. Sun and L. Li, "Potential capability estimation for real time electricity demand response of sustainable manufacturing systems using Markov Decision Process," J. of Cleaner Production, vol. 65, pp. 184-193, 15 Feb. 2014.
[11] M. López, S. De La Torre, S. Martín, and J. Aguado, "Demand-side management in smart grid operation considering electric vehicles load shifting and vehicle-to-grid support," International J. of Electrical Power & Energy Systems, vol. 64, pp. 689-698, Jan. 2015.
[12] V. M. Shiljkut and N. L. Rajakovic, "Demand response capacity estimation in various supply areas," Energy, vol. 92, pt. 3, pp. 476-486, 1 Dec. 2015.
[13] W. J. Cole, et al., "Community-scale residential air conditioning control for effective grid management," Applied Energy, vol. 130, pp. 428-436, 1 Oct. 2014.
[14] M. Hu, F. Xiao, and L. Wang, "Investigation of demand response potentials of residential air conditioners in smart grids using grey-box room thermal model," Applied Energy, vol. 207, pp. 324-335, 1 Dec. 2017.
[15] R. Deshmukh, G. Ghatikar, R. Yin, G. G. Das, and S. K. Saha, "Estimation of potential and value of demand response for industrial and commercial consumers in Delhi," in Proc. India Smart Grid Week, ISGW’15, 7 pp., 2015.
[16] S. Gyamfi and S. Krumdieck, "Scenario analysis of residential demand response at network peak periods," Electric Power Systems Research, vol. 93, pp. 32-38, Dec. 2012.
[17] O. Motlagh, G. Foliente, and G. Grozev, "Knowledge-mining the Australian smart grid smart city data: a statistical-neural approach to demand-response analysis," Planning Support Systems and Smart Cities: Springer, pp. 189-207, 2015.
[18] D. P. Zhou, M. Balandat, and C. J. Tomlin, "Estimating treatment effects of a residential demand response program using non-experimental data," in Proc. IEEE Int. Conf. on Data Mining Workshops, ICDMW’17, pp. 95-102, New Orleans, LA, USA, 18-21 Nov. 2017.
[19] S. Park, S. Ryu, Y. Choi, and H. Kim, "A framework for baseline load estimation in demand response: data mining approach," in Proc. IEEE Int. Conf. on Smart Grid Communications, SmartGridComm’15, pp. 638-643, Venice, Italy, 3-6 Nov. 2015.
[20] Z. Luo, S. Hong, and Y. Ding, "A data mining-driven incentive-based demand response scheme for a virtual power plant," Applied Energy, vol. 239, pp. 549-559, 1 Apr. 2019.
[21] dsp.ut.ac.ir/en/wpcontent/uploads/2015/09/S tatNLP-Lecture5 Clustering.pdf
[22] J. Han, J. Pei, and M. Kamber, Data Mining: Concepts and Techniques, Elsevier, 2011.
[23] -, The Power Consumption Historical Data Boston Region. Available at: http://www.iso-ne.com; [accessed 07.02.14].
[24] Massachusetts Department of Energy Resources, Clean Peak Energy Standard, Available at: https://www.mass.gov/service-details/clean-peak-energy-standard.
[25] ف. شیبانی، ﻫ. کشاورز و م. ملاحسنی‌پور، "تخمین پتانسیل منابع سمت تقاضا با توجه به تغییرات آب و هوایی،" نشریه مهندسی و مدیریت انرژی، سال 11، شماره 3، صص. 77-66، 1400.