پیش‌بینی مصرف برق با استفاده از الگوریتم جدید بهینه‌سازی زغن و شبکه عصبی مصنوعی پرسپترون چند لایه
محورهای موضوعی : انرژی های تجدیدپذیر
جلال رئیسی گهرویی
1
,
زهرا بهشتی
2
1 - دانشکده مهندسی کامپیوتر- واحد نجف آباد، دانشگاه آزاد اسلامی، نجف آباد، ایران
2 - مرکز تحقیقات کلان داده- واحد نجف‌آباد، دانشگاه آزاد اسلامی، نجف‌آباد، ایران
کلید واژه: الگوریتم‌های فراابتکاری, الگوریتم بهینه‌سازی زغن, پیش‌بینی مصرف برق, شبکه‌های عصبی پرسپترون چندلایه,
چکیده مقاله :
از آنجا که پیش بینی مصرف برق از موارد مهم مدیریت انرژی هر کشور محسوب می شود، در سال های اخیر روش های مختلفی براساس هوش مصنوعی برای آن ارائه شده است. یکی از این روش ها، استفاده از شبکه های عصبی مصنوعی است. برای آن که این شبکه ها عملکرد خوبی داشته باشند، باید به خوبی آموزش ببینند. یکی از متداول ترین الگوریتم های آموزش مورد استفاده در این شبکه ها، الگوریتم پس انتشار خطاست که براساس گرادیان نزولی است. از آنجا که الگوریتم های مبتنی برگرادیان نزولی ممکن است به نقاط بهینه محلی گرفتار شوند، در برخی از مسائل راه حل خوبی ارائه نمی دهند. از این رو برای آموزش این شبکه ها می توان از الگوریتم های بهینه سازی مانند الگوریتم های فراابتکاری که امکان فرار از بهینه های محلی را دارند، استفاده نمود. در این تحقیق، الگوریتم فراابتکاری جدیدی به نام الگوریتم بهینه سازی زغن معرفی می گردد که از زندگی اجتماعی زغن ها در طبیعت الهام گرفته شده است و دارای مزایایی مانند تعداد پارامترهای کم، قابلیت اکتشاف و سرعت همگرایی خوب، است. کارایی الگوریتم پیشنهادی، با چند الگوریتم جدید فراابتکاری روی توابع محک CEC2018 و برای آموزش شبکه عصبی در پیش بینی مصرف برق ایران در زمان های اوج مصرف بار، مقایسه گردیده است. نتایج حاصل، نشان می دهد الگوریتم پیشنهادی راه حل بهتری با خطای کمتری، در مقایسه با الگوریتم های رقیب به دست می آورد.
Since the electricity consumption’s prediction is one of the most important aspects of energy management in each country, various methods based on artificial intelligence have been proposed to manage it. One of these methods is Artificial Neural Networks (ANN). To improve the performance of ANNs, an efficient algorithm is necessary to train it. Back Propagation (BP) algorithm is the most common algorithm employed in training ANNs, which is based on gradient descent. Since BP may fall in local optima, it cannot provide a good solution in some problems. To overcome this shortcoming, optimization algorithms like meta-heuristic algorithms can be applied to train ANNs. In this study, a new meta-heuristic algorithm called Red Kite Optimization Algorithm (ROA) is introduced, which is inspired by the social life of red kites in nature. The ROA has several advantages such as simplicity in structure and implementation, having few parameters and good convergence rate. The perfprmance of ROA is compared with some recent metaheuristic algorithms on benchmark functions of CEC2018. Also, it is employed to train Multi-Layer Perceptron (MLP) for the electricity consumption prediction at peak load times in Iran. The results show the good performance of proposed algorithm compared with competitor algorithms in terms of solution accuracy and convergence speed.
[1] A. Román-Portabales, M. López-Nores, J.J. Pazos-Arias, "Systematic Review of electricity demand forecast using ANN-based machine learning algorithms", Sensors, vol. 21, no. 13, Article Number: 4544, July 2021 (doi: 10.3390/s21134544).
[2] M.R. Kazemzadeh, A. Amjadian, T. Amraee, "A hybrid data mining driven algorithm for long term electric peak load and energy demand forecasting", Energy, vol. 204, Article Number: 117948, Aug. 2020 (doi: 10.1016/j.energy.2020.117948).
[3] S. Moalem, R. M. Ahari, G. Shahgholian, M. Moazzami, S.M. Kazemi, "Long-term demand forecasting in electrical energy supply chain of espidan ironstone industry using deep learning and extreme learning machine", Journal of Intelligent Procedures in Electrical Technology, vol. 13, no. 49, pp. 1-20, June 2022 (dor: 20.1001.1.23223871.1401.13.49.1.0).
[4] H. Fu, J.C. Baltazar, D.E. Claridge, "Review of developments in whole-building statistical energy consumption models for commercial buildings", Renewable and Sustainable Energy Reviews, vol. 147, Article Number: 111248, Aug. 2021 (doi: 10.1016/j.rser.2021.111248).
[5] S. Lange, J. Pohl, T. Santarius, "Digitalization and energy consumption. Does ICT reduce energy demand?", Ecological Economics, vol. 176, Article Number: 106760, Oct. 2020 (doi: 10.1016/j.ecolecon.2020.106760).
[6] S. Williams, M. Short, "Electricity demand forecasting for decentralised energy management", Energy Built Environ. vol. 1, no. 2, pp. 178-186, April 2020 (doi: 10.1016/j.enbenv.2020.01.001).
[7] A. Daniel, B. Bharathi Kannan, N. Yuvaraj, N. V Kousik, "Predicting energy demands constructed on ensemble of classifiers", International Journal of Mechanical Engineering, vol. 6, no. 3, pp. 575-583, Dec. 2021.
[8] K. Otoufat shamsi, S. Ghane, R. Ghaemmaghami, H. Hedayati, A. Abdalisousan, "Effect of corona virus on electricity consumption in iran and the world", Journal of Intelligent Procedures in Electrical Technology, vol. 12, no. 45, pp. 49-62, June 2021 (dor: 20.1001.1.23223871.1400.12.1.4.0).
[9] N. Shirzadi, A. Nizami, M. Khazen, M. Nik-Bakht, "Medium-term regional electricity load forecasting through machine learning and deep learning", Designs, vol. 5, no. 2, Article Number: 5020027, April 2021 (doi: 10.3390/designs5020027).
[10] F.M. Andersen, H. V Larsen, T.K. Boomsma, "Long-term forecasting of hourly electricity load: Identification of consumption profiles and segmentation of customers", Energy Conversion and Management, vol. 68, pp. 244-252, April 2013 (doi: 10.1016/j.enconman.2013.01.018).
[11] H. Eskandari, M. Imani, M.P. Moghaddam, "Convolutional and recurrent neural network based model for short-term load forecasting", Electric Power Systems Research, vol. 195, Article Number: 107173, June 2021 (doi: 10.1016/j.epsr.2021.107173).
[12] H.M. Al-Hamadi, S.A. Soliman, "Long-term/mid-term electric load forecasting based on short-term correlation and annual growth", Electric Power Systems Research, vol. 74, no. 3, pp. 353-361, June 2005 (doi: 10.1016/j.epsr.2004.10.015).
[13] E. Elbeltagi, H. Wefki, "Predicting energy consumption for residential buildings using ANN through parametric modeling", Energy Reports, vol. 7, pp. 2534-2545, Nov. 2021 (doi: 10.1016/j.egyr.2021.04.053).
[14] K. Balachander, D. Paulraj, "ANN and fuzzy based household energy consumption prediction with high accuracy", Journal of Ambient Intelligence and Humanized Computing, vol. 12, pp. 7543-7557, July 2021 (doi: 10.1007/s12652-022-04223-y).
[15] D. Ramos, P. Faria, Z. Vale, R. Correia, "Short time electricity consumption forecast in an industry facility", IEEE Trans. on Industry Applications, vol. 58, no. 1, pp. 123-130, Feb. 2022 (doi: 10.1109/TIA.2021.3123103).
[16] H.T. Yang, C.M. Huang, "A new short-term load forecasting approach using self-organizing fuzzy ARMAX models", IEEE Trans. on Power Systems, vol. 13, no. 1, pp. 217-225, Feb. 1998 (doi: 10.1109/59.651639).
[17] K. Subramanian, A.P. Sathiyagnanam, D. Damodharan, N. Sivashanmugam, "Artificial neural network based prediction of a direct injected diesel engine performance and emission characteristics powered with biodiesel", Materials Today: Proceedings, vol. 43, pp. 1049-1056, Jan. 2021 (doi: 10.1016/j.matpr.2020.08.015).
[18] P.V Paul, N. Deepika, "Stock market prediction based on technical-deviation-ROC indicators using stock and feeds data", Recent Advances in Computer Science and Communications, vol. 15, no. 3, pp. 367-375, Mar. 2022 (doi: 10.2174/2666255813999200831120847).
[19] A. Jafarian, R. Rezaei, A. Khalili-Golmankhaneh, "On solving fractional higher-order equations via artificial neural networks", Iranian Journal of Science and Technology, vol. 46, no. 2, pp. 535-545, Feb. 2022 (doi: 10.1007/s40995-021-01254-6).
[20] A. Baba, "Advanced AI-based techniques to predict daily energy consumption: A case study", Expert Systems with Applications, vol. 184, Article Number: 115508, Dec. 2021 (doi: 10.1016/j.eswa.2021.115508).
[21] Y. Wu, X. Li, Q. Liu, G. Tong, "The analysis of credit risks in agricultural supply chain finance assessment model based on genetic algorithm and backpropagation neural network", Computational Economics, June 2021 (doi: 10.1007/s10614-021-10137-2).
[22] S.R. Naganna, P.C. Deka, M.A. Ghorbani, S.M. Biazar, N. Al-Ansari, Z.M. Yaseen, "Dew point temperature estimation: Application of artificial intelligence model integrated with nature-inspired optimization algorithms", Water Resources Management Strategy Under Global Change, vol. 11, no. 4, pp. 742-759, April 2019 (doi: 10.3390/w11040742).
[23] Y. Xue, Y. Wang, J. Liang, "A self-adaptive gradient descent search algorithm for fully-connected neural networks", Neurocomputing, vol. 478, pp. 70-80, March 2022 (doi: 10.1016/j.neucom.2022.01.001).
[24] M. Puig-Arnavat, J.C. Bruno, "Artificial neural networks for thermochemical conversion of biomass, in: Recent Adv", Recent Advances in Thermo-Chemical Conversion of Biomass, pp. 133-156, Jan. 2019 (doi: 10.1016/B978-0-444-63289-0.00005-3).
[25] D.H. Tran, D.L. Luong, J.S. Chou, "Nature-inspired metaheuristic ensemble model for forecasting energy consumption in residential buildings", Energy, vol. 191, Article Number: 116552, Jan. 2015 (doi: 10.1016/j.energy.2019.116552).
[26] M.A. Sahraei, M.K. Çodur, "Prediction of transportation energy demand by novel hybrid meta-heuristic ANN", Energy, vol. 249, Article Number: 123735, June 2022 (doi: 10.1016/j.energy.2022.123735).
[27] T. Singh Rajput, A. Thomas, "Optimizing passive design strategies for energy efficient buildings using hybrid artificial neural network (ANN) and multi-objective evolutionary algorithm through a case study approach", International Journal of Construction Management, pp. 1-13, March 2022 (doi: 10.1080/15623599.2022.2056409).
[28] Z. Beheshti, S.M. Shamsuddin, S. Hasan, "Improved centripetal accelerated particle swarm optimization", vol. 258, pp. 54-79, Feb. 2014 (doi: 10.1016/j.ins.2013.08.015).
[29] S. Kiani, R. Tarkesh Esfahani, Z. Zojaji, "Optimizing the Cutting of Inconel 718 Sheets with CO2 Laser by Particle Swarm Algorithm", Intelligent Procedures in Electrical Technology, vol. 13, pp. 111-124, May 2022 (dor: 20.1001.1.23223871.1401.13.51.7.0).
[30] Z. Beheshti, M. Firouzi, S.M. Shamsuddin, "A new rainfall forecasting model using the CAPSO algorithm and an artificial neural network", Neural Computing and Applications, vol. 27, no. 8, pp. 2551-2565, Nov. 2016 (doi: 10.1007/s00521-015-2024-7).
[31] L. Ajami Bakhtiarvand, Z. Beheshti, "A New Data Clustering Method Using 4-Gray Wolf Algorithm", Nashriyyah Muhandisi Barq va Muhandisi Kampyutar Iran, vol. 4, no. 1, pp. 261-274, Winter 2022 (dor: 20.1001.1.16823745.1400.19.4.12.5).
[32] Z. Beheshti, "BMNABC: Binary Multi-Neighborhood Artificial Bee Colony for High-Dimensional Discrete Optimization Problems", Cybernetics and Systems, vol. 49, no. 7, Article Number: 1541597, pp. 452-474, Nov. 2018 (doi: 10.1080/01969722.2018.1541597).
[33] Z. Beheshti, "UTF: Upgrade transfer function for binary meta-heuristic algorithms", Applied Soft Computing, vol. 106, Article Number: 107346, July 2021 (doi: doi.org/10.1016/j.asoc.2021.107346).
[34] Z. Beheshti, "A novel x-shaped binary particle swarm optimization", Soft Computing, vol. 25, no. 4, Feb. 2021 (doi: 10.1007/s00500-020-05360-2).
[35] S. Saremi, S. Mirjalili, A. Lewis, "Grasshopper Optimisation Algorithm: Theory and application", Advances in Engineering Software, vol. 105, pp. 30-47, March 2017 (doi: 10.1016/j.advengsoft.2017.01.004).
[36] G. Dhiman, V. Kumar, "Spotted hyena optimizer: A novel bio-inspired based metaheuristic technique for engineering applications", Advances in Engineering Software, vol. 114, pp. 48-70, Dec. 2017 (doi: 10.1016/j.advengsoft.2017.05.014).
[37] A.A. Heidari, S. Mirjalili, H. Faris, I. Aljarah, M. Mafarja, H. Chen, "Harris hawks optimization: Algorithm and applications", Future Generation Computer Systems, vol. 97, pp. 849-872, Aug. 2019 (doi: 10.1016/j.future.2019.02.028).
[38] M.M. Noel, V. Muthiah-Nakarajan, G.B. Amali, A.S. Trivedi, "A new biologically inspired global optimization algorithm based on firebug reproductive swarming behavior", Expert Systems with Applications, vol. 183, Article Number: 115408, Nov. 2021 (doi: 10.1016/j.eswa.2021.115408).
[39] L. Abualigah, A. Diabat, S. Mirjalili, M. Abd Elaziz, A.H. Gandomi, "The arithmetic optimization algorithm", Computer Methods in Applied Mechanics and Engineering, vol. 376, Article Number: 113609, April 2021 (doi: 10.1016/j.cma.2020.113609).
[40] K. V Price, N.H. Awad, M.Z. Ali, P.N. Suganthan, "Problem definitions and evaluation criteria for the 100-digit challenge special session and competition on single objective numerical optimization", Technical Report Nanyang Technological University of Singapore, Nov. 2018.
[41] S.M. Barakchian, S.F. Ardestani, H. Shokoohian, "Short-term Forecast of Hourly Electricity Demand in Iran Using a Forecast Combination Method", Planning and Budgeting, vol. 24, no. 4, pp. 57-73, Feb. 2020 (doi: 10.29252/jpbud.24.4.57).
[42] S.S.S. Ali, M.R. Razman, A. Awang, M.R.M. Asyraf, M.R. Ishak, R.A. Ilyas, R.J. Lawrence, "Critical determinants of household electricity consumption in a rapidly growing city", Energy Consumption and Sustainable Urban Environment, vol. 13, no. 8, April 2021 (doi: 10.3390/su13084441).
[43] Z. Wang, T. Hong, H. Li, M.A. Piette, "Predicting city-scale daily electricity consumption using data-driven models", Advances in Applied Energy, vol. 2, Article Number: 100025, May 2021 (doi: 10.1016/j.adapen.2021.100025).
[44] M. Oh, K.M. Jang, Y. Kim, "Empirical analysis of building energy consumption and urban form in a large city: A case of Seoul", Energy and Buildings, vol. 245, Article Number: 111046, August 2021 (doi: 10.1016/j.enbuild.2021.111046).
[45] Z. Shafiei Chafi, H. Afrakhte, "Short-term load forecasting using neural network and particle swarm optimization (PSO) algorithm", Mathematical Problems in Engineering, vol. 2021, Article Number: 5598267, April 2021 (doi: 10.1155/2021/5598267).
[46] H. Moayedi, A. Mosavi, "Electrical power prediction through a combination of multilayer perceptron with water cycle ant lion and satin bowerbird searching optimizers", Applications of Artificial Intelligence in New Energy Technology Systems, vol. 13, no. 4, Feb. 2021 (doi: 10.3390/su13042336).
[47] M. Ishaq, S. Kwon, "Short-term energy forecasting framework using an ensemble deep learning approach", IEEE Access, vol. 9, Article Number: 3093053, June 2021 (doi: 10.1109/ACCESS.2021.3093053).
[48] K. Xie, H. Yi, G. Hu, L. Li, Z. Fan, "Short-term power load forecasting based on Elman neural network with particle swarm optimization", Neurocomputing, vol. 416, pp. 136-142, Nov. 2020 (doi: 10.1016/j.neucom.2019.02.063).
[49] M.K. Kim, Y.-S. Kim, J. Srebric, "Predictions of electricity consumption in a campus building using occupant rates and weather elements with sensitivity analysis: Artificial neural network vs. linear regression", Sustainable Cities and Society, vol. 62, Article Number: 102385, Nov. 2020 (doi: 10.1016/j.scs.2020.102385).
[50] S.L. Karunathilake, H.R.K. Nagahamulla, "Artificial neural networks for daily electricity demand prediction of Sri Lanka", 017 Seventeenth International Conference on Advances in ICT for Emerging Regions (ICTer), pp. 1-6, Sep. 2017 (doi: 10.1109/ICTER.2017.8257823).
[51] M. Talaat, M.A. Farahat, N. Mansour, A.Y. Hatata, "Load forecasting based on grasshopper optimization and a multilayer feed-forward neural network using regressive approach", Energy, vol. 196, Article Number: 117087, April 2020 (doi: 10.1016/j.energy.2020.117087).
[52] S. Duman, A. Dalcalı, H. Özbay, "Manta ray foraging optimization algorithm–based feedforward neural network for electric energy consumption forecasting", International Transactions on Electrical Energy Systems, vol. 31, no. 9, Sep. 2021 (doi: 10.1002/2050-7038.12999).
[53] G. Oğcu, O.F. Demirel, S. Zaim, "Forecasting electricity consumption with neural networks and support vector regression", Procedia- Social and Behavioral Sciences, vol. 58, August 2012 (doi: 10.1016/j.sbspro.2012.09.1144).
[54] K. Lan, D. Wang, S. Fong, L. Liu, K.K.L. Wong, N. Dey, "A survey of data mining and deep learning in bioinformatics", medical systems, vol. 42, no. 8, June 2018 (doi: 10.1007/s10916-018-1003-9).
[55] A. Shrestha, A. Mahmood, "Review of deep learning algorithms and architectures", IEEE Access, vol. 7, April 2019 (doi: 10.1109/ACCESS.2019.2912200).
[56] R.P. Parouha, P. Verma, "State-of-the-art reviews of meta-heuristic algorithms with their novel proposal for unconstrained optimization and applications", Archives of Computational Methods in Engineering, vol. 28, no. 5, pp. 4049-4115, August 2021 (doi: 10.1007/s11831-021-09532-7).
[57] S. Desale, A. Rasool, S. Andhale, P. Rane, "Heuristic and meta-heuristic algorithms and their relevance to the real world: a survey", Computer Engineering in Research Trends, vol. 2, no. 5, pp. 296-304, May 2015.
[58] A. Kaveh, M.I. Ghazaan, "Comparison of four meta-heuristic algorithms for optimal design of double-layer barrel vaults", International Journal of Space Structures, vol. 33, no. 3-4, pp. 115-123, Oct. 2018 (doi: 10.1177/0266351118803019).
[59] J. Nayak, B. Naik, H.S. Behera, "A novel nature inspired firefly algorithm with higher order neural network: performance analysis", Engineering Science and Technology, vol. 16, no. 1, pp. 197-211, March 2016 (doi: 10.1016/j.jestch.2015.07.005).
[60] M.R. Gabor, "Is the old communist brand preferred by the young consumers? A country of origin study case with multimethod analysis", Risk in Contemporary Economy, vol. 19, pp. 355-366, Oct. 2018 (doi: 10.26397/rce2067053243).
[61] A. Agresti, “Analysis of Ordinal Cathegorical Data”, New York City John Willey & Sons, March 2010 (doi: 10.1002/9780470594001).
[62] Kendall, M. G, "The treatment of ties in ranking problems", Biometrika, vol. 33, no. 3, pp. 239-251, Nov. 1945 (doi: 10.2307/2332303).
[63] A.N. Mandeville, P.E. O’connell, J. V Sutcliffe, J.E. Nash, "River flow forecasting through conceptual models part III-The Ray catchment at Grendon Underwood", Hydrology, vol. 11, no. 2, pp. 109-128, August 1970 (doi: 10.1016/0022-1694(70)90098-3).
[64] C.J. Willmott, "On the validation of models", Physical Geography, vol. 2, no. 2, pp. 184-194, July 1981 (doi: 10.1080/02723646.1981.10642213).
_||_