KRATKOROČNA PROGNOZA POTROŠNJE ELEKTRIČNE ENERGIJE PUTEM VIŠESTRUKE LINEARNE REGRESIJE (MLR) I NEURALNE MREŽE SA VIŠESLOJNIM PERCEPTRONOM (MLP)

Флексибилност електроенергетског система / Зборник CIGRE (2023).  (стр 1062-1073)

АУТОР(И) / AUTHOR(S): Vladimir Urošević, Željko Marković

Е-АДРЕСА / E-MAIL: vladimir.urosevic@gmail.com

Download Full Pdf   

DOI:  10.46793/CIGRE36.1062U

САЖЕТАК / ABSTRACT:

Prognoza potrošnje električne energije predstavlja prvi i najvažniji korak u upravljanju potrošnjom, donošenju investicionih odluka u trgovini električnom energijom i planiranju sistema u uslovima liberalizovanog tržišta električne energije. U zavisnosti od vremenskog horizonta na kom se vrši prognoza, prognozi se pristupa putem različitih metoda od jednostavnih algoritma za klasifikaciju i predviđanje, različitih statističkih metoda regresije, „fuzzy“ logike, neuronskih mreža, do hibridnih sistema koji kombinuju više pristupa.
U radu se ispituju dva metodološka pristupa. U okviru prvog pristupa razmatra se pristup korišćenjem višestruke linearne regeresije, dok drugi pristup podrazumeva primenu veštačke neuralne mreže – višeslojnog perceptrona. Rezultati ova dva pristupa se na kraju porede i sa modifikovanim KNN (k-Nearest Neighbors) algoritmom koji osim temperature uzima i ostvarene dijagrame potrošnje iz bliske prošlosti. Svi navedeni pristupi se koriste za kratkoročnu prognozu satne potrošnje električne energije, na nivou dva dana unapred, na konzumu Republike Srbije. U radu se, na osnovu konkretnih rezultata, obrazlažu prednosti i nedostaci svakog od izabranih modela.

КЉУЧНЕ РЕЧИ / KEYWORDS:

Prognoza potrošnje električne energije, MLR, MLP, KNN

ЛИТЕРАТУРА / REFERENCES:

  • Magnano L, Boland J, 2007, “Generation of synthetic sequences of electricity demand: application in South Australia”, “Energy”;32, 2230–43.
  • Soares LJ, Souza LR, 2006, “Forecasting electricity demand using generalized long memory”, “International Journal of Forecasting”, 22, 17–28.
  • Ramanathan R, Engle R, Granger CWJ, Vahid-Araghi F, Brace C, 1997, “Short-run forecasts of electricity loads and peaks”, “International Journal of Forecasting”, 13, 161–74.
  • Thatcher MJ, 2007, “Modelling changes to electricity demand load duration curves as a consequence of predicted climate change for Australia”, “Energy”, 32, 1647–59.
  • Harvey A, Koopman SJ, 1993, “Forecasting hourly electricity demand using time-varying splines”, “Journal of American Statistical Association”, 88, 1228–36.
  • Taylor J, 2003, “Short-term electricity demand forecasting using double seasonal exponential smoothing”, “Journal of the Operational Research Society”, 54, 799–805.
  • Wang JZ, Chi DZ, Wu J. Lu HY, 2011, “Chaotic time series method combined with particle swarm optimization and trend adjustment for electricity demand forecasting”, “Journal of Expert System with Application”, 38, 8419–29.
  • Bianco V, Manca O, Nardini S, 2009, “Electricity consumption forecasting in Italy using linear regression models”, “Energy”, 34, 1413–21.
  • Pao HT, 2009, “Forecasting energy consumption in Taiwan using hybrid nonlinear models”, “Energy”, 34, 1438–46.
  • Metaxiotis K, Kagiannas A, Askounis D, Psarras J, 2003, “Artificial intelligence in short term electrical load forecasting: a state-of-the-art survey for the researcher”, “Journal of Energy Conversion and Management”, 44, 1525–34.
  • Chang PC, Fan CY, Lin JJ, 2011, “Monthly electricity demand forecasting based on a weighted evolving fuzzy neural network approach”, “International Journal of Electric Power Energy Systems”, 33, 17–27.
  • Azadeh A, Ghaderi F, Tarvardiyan S, 2007, “Integration of artificial neural network and genetic algorithm to predict electricity energy consumption”, “Journal of Applied Mathematics and Computing”, 186(2):1731–41
  • Kucukali S, Baris K, 2010, “Turkey’s short-term gross annual electricity demand forecast by fuzzy logic approach”, “Energy Policy”, 38, 2438–45.
  • Dash PK, Liew AC, Rahman S, Ramakrishna G, 1995, “Building a fuzzy expert system for electric load forecasting using a hybrid neural network”, “Journal of Expert System with Application”, 9, 407–21.
  • Urošević V, Marković Ž, 2020, “Kratkoročna prognoza potrošnje električne energije putem modifikovanog KNN algoritma i ARIMA statističkog modela“, Zbornik radova XII Savetovanja CIRED.
  • Rumelhart, David E., Geoffrey E. Hinton, and R. J. Williams. „Learning Internal Representations by Error Propagation“. David E. Rumelhart, James L. McClelland, and the PDP research group. (editors), Parallel distributed processing: Explorations in the microstructure of cognition, Volume 1: Foundation. MIT Press, 1986.
  • Glorot, X., & Bengio, Y. (2010, March). Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics (pp. 249-256). JMLR Workshop and Conference Proceedings.
  • Altman, N. S, 1992, “An introduction to kernel and nearest-neighbor nonparametric regression”, „The American Statistician“, 46, 175—185.
  • Kouiroukidis, Nikolaos, G. Evangelidis, 2011. “The effects of dimensionality curse in high dimensional KNN search”, Procedings of 15th Panhellenic Conference on Informatics IEEE, 421-442
  • Hyndman, Rob J., and George Athanasopoulos. Forecasting: principles and practice. OTexts, 2018.