{"title":"Comparison of Machine Learning Models for the Prediction of System Marginal Price of Greek Energy Market","authors":"Ioannis P. Panapakidis, Marios N. Moschakis","volume":147,"journal":"International Journal of Energy and Environmental Engineering","pagesStart":148,"pagesEnd":153,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/10010164","abstract":"<p>The Greek Energy Market is structured as a mandatory pool where the producers make their bid offers in day-ahead basis. The System Operator solves an optimization routine aiming at the minimization of the cost of produced electricity. The solution of the optimization problem leads to the calculation of the System Marginal Price (SMP). Accurate forecasts of the SMP can lead to increased profits and more efficient portfolio management from the producer`s perspective. Aim of this study is to provide a comparative analysis of various machine learning models such as artificial neural networks and neuro-fuzzy models for the prediction of the SMP of the Greek market. Machine learning algorithms are favored in predictions problems since they can capture and simulate the volatilities of complex time series.<\/p>\r\n","references":"[1]\tF. Ziel, R. Steinert, and S. Husmann, \u201cEfficient modeling and forecasting of electricity spot prices\u201d, Energy Econ, vol. 47, pp. 98-111, 2015.\r\n[2]\tD. Singhal, and K.S. Swarup, \u201cElectricity price forecasting using artificial neural networks\u201d, Int J Elect Power Energy Syst, vol. 33, pp. 550-555, 2011.\r\n[3]\tS.K. Aggarwal, L.M. Saini, and A. Kumar, \u201cElectricity price forecasting in deregulated markets: A review and evaluation\u201d, Int J Elect Power Energy Syst, vol. 31, pp. 13-22, 2009.\r\n[4]\tA. Ahmadi, M. Charwand, and J. Aghaei, \u201cRisk-constrained optimal strategy for retailer forward contract portfolio\u201d, Int J Elect Power Energy Sys, vol. 53, pp. 704-713, 2013.\r\n[5]\tM. Carri\u00f3n, A.J. Conejo, and J.M. Arroyo, \u201cForward contracting and selling price determination for a retailer\u201d, IEEE Trans Power Sys, vol. 22, pp. 2105-2114, 2007.\r\n[6]\tS. Yousefi, M.P. Moghaddam, and V.J. Majd, \u201cOptimal real time pricing in an agent-based retail market using a comprehensive demand response model\u201d, Energy, vol. 36, pp. 5716-5727, 2011.\r\n[7]\tJ. Yang, G. Zhang, K. Ma, \u201cMatching supply with demand: A power control and real time pricing approach\u201d, Appl. Energy, vol. 61, pp. 111-117, 2014.\r\n[8]\tR. Weron, \u201cElectricity price forecasting: A review of the state-of-the-art with a look into the future\u201d, Int J Forecast, vol. 30, pp. 1030-1081, 2014.\r\n[9]\tM. Cerjan, I. Krzelj, M. Vidak, and M. Delimar, \u201cA literature review with statistical analysis of electricity price forecasting methods\u201d, In Proceedings of the 2013 EUROCON, 756-763.\r\n[10]\tR. Gareta, L.M. Romeo, and A. Gil, \u201cForecasting of electricity prices with neural networks\u201d, Energy Conv Manag, vol. 47, pp. 1770-1778, 2006.\r\n[11]\tN. Amjady, and F. Keynia, \u201cDay ahead price forecasting of electricity markets by a mixed data model and hybrid forecast method\u201d, Int J Electr Power Energy Syst, vol. 30, pp. 533-546, 2008. \r\n[12]\tN. Amjady, and F. Keynia, \u201cDay-ahead price forecasting of electricity markets by mutual information technique and cascaded neuro-evolutionary algorithm\u201d. IEEE Trans Power Sys, vol. 24, pp. 306-308, 2009. \r\n[13]\tS. Chakravarty, and P.K. Dash, \u201cDynamic filter weights neural network model integrated with differential evolution for day-ahead price forecasting in energy market\u201d, Expert Sys Appl, vol. 38, pp. 10974-10982, 2011.\r\n[14]\tP. Dev, and M.A. Martin, \u201cUsing neural networks and extreme value distributions to model electricity pool prices: Evidence from the Australian National Electricity Market 1998\u20132013\u201d, Energy Conv Manag, vol. 84, pp. 122-132, 2014.\r\n[15]\tB. Neupane, K.S. Perera, Z. Aung, and W.L. Woon, \u201cArtificial neural network-based electricity price forecasting for smart grid deployment\u201d, In Proceedings of the 2012 International Conference on Computer Systems and Industrial Informatics, Sharjah, pp. 1-6. \r\n[16]\tH.T. Pao, \u201cForecasting electricity market pricing using artificial neural networks\u201d, Energy Conv Manag, vol 48, pp. 907-912, 2007.\r\n[17]\tT.M. Peng, N.F. Hubele, and G.G. Karady, \u201cAdvancement in the application of neural networks for short-term load forecasting\u201d, IEEE Trans Power Syst, vol. 7, pp. 250-257, 1992.\r\n[18]\tN.M. Pindoriya, S.N. Singh, and S.K. Singh, \u201cAn adaptive wavelet neural network-based energy price forecasting in electricity markets\u201d, IEEE Trans Power Syst, vol. 23, pp. 1423-1431, 2008\r\n[19]\tP. Areekul, Y. Senjyu, H. Toyama, and A. Yona, \u201cA hybrid ARIMA and neural network model for short-term price forecasting in deregulated market\u201d, IEEE Trans Power Syst, vol. 25, pp. 524-530, 2010.\r\n[20]\tA. Khosravi, S. Nahavandi, and D. Creighton, \u201cA neural network-GARCH-based method for construction of Prediction Intervals\u201d, Elect Power Sys Res, vol. 96, pp. 185-193, 2013.\r\n[21]\tN. Amjady, A. Daraeepour, and F. Keynia, \u201cDay-ahead electricity price forecasting by modified relief algorithm and hybrid neural network\u201d, IET Gener Transm Distrib, vol. 4, pp. 432-444, 2010.\r\n[22]\tS. Hassan, A. Khosravi, J. Jaafar, amd M.Q. Raza, \u201cElectricity load and price forecasting with influential factors in a deregulated power industry\u201d, In Proceedings of the 2014 9th International Conference on System of Systems Engineering (SOSE), 79-84.\r\n[23]\tH.S. Sandhu, L. Fang, and L. Guan, \u201cForecasting day-ahead electricity prices using data mining and neural network techniques\u201d, In Proceedings of the 2014 11th International Conference on Service Systems and Service Management (ICSSSM), 1-6.\r\n[24]\tA. Agarwal, A. Ojha, S,C, Tewari, and M.M. Tripathi, \u201cHourly load and price forecasting using ANN and fourier analysis\u201d, In Proceedings of the 2014 6th IEEE Power India International Conference (PIICON), 1-6.\r\n[25]\tE. Elattar, and E.K. Shebin, \u201cDay-ahead price forecasting of electricity markets based on local informative vector machine\u201d, IET Gener Trans Distrib, vol. 7, pp. 1063-1071, 2013. \r\n[26]\tH. Shayeghi, and A. Ghasemi, \u201cDay-ahead electricity prices forecasting by a modified CGSA technique and hybrid WT in LSSVM based scheme\u201d, Energy Conv Manag, vol. 74, pp. 482-491, 2013.\r\n[27]\tN.A. Shrivastava, A. Khosravi, and B.K. Panigrahi, \u201cPrediction interval estimation for electricity price and demand using support vector machines\u201d, In Proceedings of the 2014 International Joint Conference on Neural Networks (IJCNN), 3995-4002.\r\n[28]\tS. Fan, C. Mao, and L. Chen, \u201cNext-day electricity-price forecasting using a hybrid network\u201d, IET Gener Trans Distrib, vol. 1, pp. 176-82, 2007.\r\n[29]\tD. Niu, D. Liu, and D.D. Wu, \u201cA soft computing system for day-ahead electricity price forecasting\u201d, Appl. Soft Comp, vol. 10, pp. 868-875, 2010.\r\n[30]\tM. Bashari, A. Darudi, and N. Raeyatdoost, \u201cKalman Fusion algorithm in electricity price forecasting\u201d, In Proceedings of the 2014 14th International Conference on Environment and Electrical Engineering (EEEIC), 313-317.\r\n[31]\tLAGIE S.A.: http:\/\/www.lagie.gr\/\r\n[32]\tD. Graupe. Principles of Artificial Neural Networks. Singapore: World Scientific Publishing Company; 2007.\r\n[33]\tJ-SR. Jang, \u201cANFIS: adaptive-network-based fuzzy inference system\u201d, Syst Man Cyber, vol. 23, pp. 665-685, 1993.\r\n[34]\tB. Soldo, P. Potocnik, G. Simunovi, T. Sari, and E. Govekar, \u201cImproving the residential natural gas consumption forecasting models by using solar radiation\u201d, Energy and Buildings, vol. 69, pp. 498-506, 2014.\r\n[35]\tR.A. Hatami, H. Seifi, and M.K. Sheikh-El-Eslami, \u201cOptimal selling price and energy procurement strategies for a retailer in an electricity market\u201d, Elect Power Syst Res, vol. 79, 246-254, 2009\r\n[36]\tJ.M. Yusta, I.J.R. Rosado, J.A.D. Navarro, J.M.P. Vidal, \u201cOptimal electricity price calculation model for retailers in a deregulated market\u201d, Int J Elect Power Energy Syst vol.27, pp. 437-447, 2005\r\n[37]\tS.A. Gabriel, M.F. Genc, and S. Balakrishnan, \u201cA simulation approach to balancing annual risk and reward in retail electrical power markets\u201d, IEEE Trans Power Syst, vol. 17, pp. 1050-1057, 2002\r\n[38]\tS.A. Gabriel, A.J. Conejo, M.A. Plazas, and S. Balakrishnan, \u201cOptimal price and quantity determination for retail electric power contracts\u201d, IEEE Trans Power Syst, vol. 21, pp. 180-187, 2006\r\n[39]\tM. Carri\u00f3n, J.M. Arroyo, and A.J. Conejo, \u201cA bilevel stochastic programming approach for retailer futures market trading\u201d, IEEE Trans Power Syst, vol. 24, pp. 1446-1456, 2009 \r\n[40]\tN. Mahmoudi-Kohan, M. Parsa Moghaddam, and M.K. Sheikh-El-Eslami, \u201cAn annual framework for clustering-based pricing for an electricity retailer\u201d, Elect Power Syst Res, vol. 80, pp. 1042-1048, 2010","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 147, 2019"}