SHORT-TERM FORECAST OF LOAD BY MACHINE LEARNING MODEL: APPLICATION TO ITALIA
186 viewsKeywords:
Short-term focast of load; Similar shape algorithms; Machine learning model; Electricity market.Abstract
This paper presents a method based on machine learing model to forcast daily electrical loads. The model requires only historical datasets of load data. Hence, it is simple and more available to implement. The algorithm model “K-nearest neighbor - Regression” is used to predict the power load for 24 hours of the next day by looking in historical data set of days with weak factors most similar to the next day and using the load of those days to calculate and forecast the load in day ahead. Finally, data of Italia is used to verify the proposed model. The resulting error performanced by this model is calculated and compared with Terna's forecast. In addition, the introduced method is realized by applying to Italy and data of GME (electricity market data in Italy).
References
[1]. M.Tucci, M.Raugi, G.Giunta, E.Crisostomi, “A Multi-Objective Method for Short- Term Load Forecasting in European Countries”, IEEE Transactions on Power Systems, vol. 31 , Issue: 5, pp. 3537-3574, Sept 2016.
[2]. Ervin Ceperic, Vladimir Ceperic, Adrijan Baric, “A Strategy for Short-Term Load Forecasting by Support Vector Regression Machines”, IEEE Transactions on Power Systems (Volume: 28, Issue: 4, Nov. 2013).
[3]. Yanying Li, Jinxing Che, Youlong Yang, “Subsampled support vector regression ensemble for short term electric load forecasting”, Energy Volume 164, 1 December 2018, Pages 160-170.
[4]. A. Navot, L. Shpigelmen, N. Tishby, E. Vaadia, “Nearest Neighbor Based Feature Selection for Regression and its Application to Neural Activity”, Advances in Neural Information Processing Systems 18, NIPS 2005, December 5-8, 2005.
[5]. H. S. Hippert, C. E. Pedreira and R. C. Souza, “Neural Networks for ShortTerm Load Forecasting: a Review and Evaluation”, IEEE Transactions on Power Systems, vol. 16, no. 1, pp. 44-55, 2001.
[6]. Kunjin Chen, Kunlong Chen, Qin Wang, Ziyu He, Jun Hu, Jinliang He, “Short-Term Load Forecasting with Deep Residual Networks”, IEEE Transactions on Smart Grid, Volume: 10, Issue: 4, July 2019.
[7]. P. Mandal, T. Senjyu, N. Urasaki and T. Funabashi, “A neural network based saveral-hour-ahead electric load forecasting using similar days approach”, Elec. Power and Energy Systems, vol. 28, pp. 367-373, 2006.
[8]. Ying Chen, Peter B. Luh, Che Guan, Yige Zhao, Laurent D. Michel, Matthew A. Coolbeth, Peter B. Friedland, “Short-Term Load Forecasting: Similar Day-Based Wavelet Neural Networks”, IEEE Transactions on Power Systems, Volume: 25, Issue: 1, Feb. 2010.
[9]. Gabriel Trierweiler Ribeiro, Viviana Cocco Mariani, Leandro dos Santos Coelho, “Enhanced ensemble structures using wavelet neural networks applied to short-term load forecasting”, Engineering Applications of Artificial Intelligence, Volume 82, June 2019, Pages 272-281.
[10]. https://www.terna.it/en/electric-system/transparency-report/total-load
[11]. L. Semeraro, E. Crisostomo, A. Franco, A. Landi, M. Raugi, M. Tucci, “Electrical load clustering: The Italian case”, IEEE PES Innovative Smart Grid Technologies, Europe, 2014.
