Next day electric load curve forecasting using k-means clustering

• Autorzy: Dudek G.

Warianty tytułu

PL

Prognozowanie dobowego przebiegu obciążenia z jednodniowym wyprzedzeniem przy użyciu metody k-średnich

• Języki publikacji: EN

Abstrakty

EN

Accurate models for electric power load forecasting are essential to the operation and planning for the electric industry. They have many applications including energy purchasing, generation, distribution, and contract evaluation. This paper proposes the methods of short-term load forecasting using the k-means clustering. Two approaches are presented based on the similarity of the load sequence patterns. In the first one, each cluster is created from two preprocessed sequences of load time series: one preceding the forecast moment and the forecasted one. In the forecast procedure only the first part is presented to the model. The second forecasted part is reconstructed from the cluster closest to the first part. In the second approach both sequences are divided into clusters independently. After clustering the empirical probabilities that the forecasted sequence is associated to cluster j when the corresponding input sequence is associated to cluster i are calculated. The forecasted sequence for the new input sequence is formed from cluster centroids using these conditional probabilities. The suitability of the proposed approaches is illustrated through an application to real load data.

PL

W tym artykule proponuje się metody prognozowania krótkoterminowego oparte na klasteryzacji k-średnich. Zaprezentowano dwa podejścia wykorzystujące podobieństwo obrazów sekwencji szeregu czasowego obciążeń. W pierwszym podejściu, każdy klaster tworzony jest z dwóch przetworzonych sekwencji szeregu czasowego obciążeń: poprzedzającej moment prognozy i prognozowanej. W procedurze prognostycznej tylko pierwsza sekwencja jest prezentowana na wejście modelu. Druga sekwencja, prognozowana, rekonstruowana jest z klastera najbliższego do sekwencji pierwszej. W drugim podejściu obie sekwencje dzielone są na grupy niezależnie. Po fazie grupowania wyznacza się empiryczne prawdopodobieństwa, że prognozowana sekwencja należy do grupy j, pod warunkiem, że odpowiadająca jej sekwencja poprzedzająca należy do grupy i. Sekwencja prognozowana dla sekwencji wejściowej formowana jest z centroidów klasterów, przy użyciu tych warunkowych prawdopodobieństw. Skuteczność proponowanych metod zilustrowano przykładami prognoz wykonanych na rzeczywistych danych.

Słowa kluczowe

EN

short-term load forecasting; k-means clustering; cluster analysis; similarity-based methods

PL

krótkoterminowe prognozowanie obciążenia; klasteryzacja k-średnich; analiza skupisk; metody oparte na podobieństwie

• Wydawca: KAPRINT
• Czasopismo: Rynek Energii
• Rocznik: 2011
• Tom: nr 1
• Strony: 143--149
• Opis fizyczny: Bibliogr. 31 poz., fig.

Twórcy

autor

Dudek G.

• Czestochowa University of Technology,

Bibliografia

• [1] Dash P.K., Liew A.C., Rahman S., Dash S.: Fuzzy and neuro-fuzzy computing models for electric load forecasting, Engng Applic. Artif. Intell. Vol.8, No.4, 1995, pp. 423-433.
• [2] Dobrzańska I.: Hausdorff dimension as a tool of step prediction, Badania Operacyjne i Decyzje, No.2, 1991, pp. 31-62 (in Polish).
• [3] Duda R.O., Hart P.E.: Pattern Classification and Scene Analysis. Wiley, 1973, New York.
• [4] Dudek G.: Application of the Hecht-Nielsen neural network to short term load forecasting, Proceedings of the International Conference on Present-Day Problems of Power Engineering. APE’97, Gdańsk-Jurata, Poland, Vol.4, 1997, pp. 65-72 (in Polish).
• [5] Dudek G.: Short term load forecasting using radial basis neural networks. Proceedings of the National Conference on Forecasting in Power Engineering PE 2000,, pp. 59-68 (in Polish).
• [6] Dudek G.: Regression tree as a forecasting tool, Proceedings of the National Conference on Forecasting in Power Engineering PE 2004, pp. 99-105 (in Polish).
• [7] Dudek G.: Application of hierarchical clustering methods to the daily electrical load profile forecasting, Przegląd Elektrotechniczny. No.9, 2006, pp. 9-11 (in Polish).
• [8] Dudek G.: Data preprocessing in similarity-based methods of short-term load forecasting. Przegląd Elektrotechniczny. No.9, 2006, pp. 15-19 (in Polish).
• [9] Dudek G.: Short-term electrical load forecasting using fuzzy clustering method. Przegląd Elektrotechniczny, No.9, 2006, pp. 26-28 (in Polish).
• [10] Dudek G.: Short-term load forecasting using fuzzy clustering and genetic algorithms, Final report of the Polish State Committee for Scientific Research founded grant no. 3T10B02329, Dept. Elect. Eng., Czestochowa University of Technology 2006, (unpublished, in Polish)
• [11] Dudek G.: Artificial immune system for short-term electric load forecasting. In: Rutkowski L., Tadeusiewicz R., Zadeh L., Zurada J. (eds): Lecture Notes in Artificial Intelligence, vol. 5097, Springer, Proceedings of the 9th International Conference on Artificial Intelligence and Soft Computing ICAISC 2008, pp. 1007-1017.
• [12] Dudek G.: Similarity-Based Approaches to Short-Term Load Forecasting, in Forecasting Models: Methods and Applications, pp. 161-178, iConcept Press 2010 (http://www.iconceptpress.com/books/forecastingModels/chapter11.pdf).
• [13] Engle R.F., Mustafa C., Rice J.: Modeling peak electricity demand. Journal of Forecasting, Vol.11, 1992, pp. 241-251.
• [14] Gross G., Galiana F.D.: Short-term load forecasting. Proceedings of the IEEE, Vol.75, No.12, 1987, pp. 1558-1573.
• [15] Khotanzad A., Afkhami-Rohani R., Lu T.L., Davis M.H., Abaye A., Maratukulam D.: ANNSTLF - a neural network based electric load forecasting system. IEEE Trans. on Neural Networks, Vol.8, 1997, No.4, pp. 835-846.
• [16] Kodogiannis V.S., Anagnostakis E.M.: Soft computing based techniques for short-term load forecasting. Fuzzy Sets and Systems, Vol.128, 2002, pp. 413-426.
• [17] Lendasse A., Verleysen M., de Bodt E., Cottrell M., Gregoire P.: Forecasting time-series by Kohonen Classification. Proceedings of the European Symposium on Artificial Neural Networks, Bruges, Belgium, 1998, pp. 221-226.
• [18] Liang R.-H., Cheng C.-C.: Short-term load forecasting by a neuro-fuzzy based approach. Electrical Power and Energy Systems, Vol.24, 2003, pp. 103-111.
• [19] Łyp J.: Methodology of the Electric Load Analysis and Forecasting for the Local Power Systems. Ph.D. Dissertation, Dept. Elect. Eng., Czestochowa University of Technology, 2003 (in Polish).
• [20] Malko J., Mikołajczyk H., Skorupski W.: Problems of short-term hourly load modeling accuracy with use layered neural networks. Proceedings of the National Conference on Forecasting in Power Engineering PE 1996,, pp. 69-75 (in Polish).
• [21] Markovic M., Fraissler W.: Short-term load forecast by plausibility checking of announced demand: an expert system approach. Eur Trans Electr Power Eng, Vol.3, No.5, 1993, pp. 353-358.
• [22] Metaxiotis K., Kagiannas A., Askounis D., Psarras J.: Artificial intelligence in short term load forecasting: a state-of-the-art survey for the researcher. Energy Conversion and Management, Vol.44, 2003, pp. 1525-1534.
• [23] Osowski S., Siwek K., Kądzielawa A.: Neural network approach to load forecasting. Proceedings of the Conference on Neural Networks and Their Applications, Szczyrk, 1996, Poland, pp. 355-360.
• [24] Pai P.-F., Hong W.-C.: Support vector machines with simulated annealing algorithms in electricity load forecasting. Energy Conversion and Management, Vol.46, 2005, pp. 2669-2688.
• [25] Papadakis S.E., Theocharis J.B., Bakirtzis A.G.: A load curve based fuzzy modeling technique for short-term load forecasting. Fuzzy Sets and Systems, Vol.135, 2003, pp. 279-303.
• [26] Popławski T., Dąsal K.: Canonical distribution in short-term load forecasting. In: Szkutnik J., Kolcun M. (Eds.), Technical and Economic Aspect of Modern Technology Transfer in Context of Integration with European Union, Mercury-Smekal Pub House, Kosice, 2004, Slovak Republic, pp. 147-153.
• [27] Rahman S., Hazim O.: A generalized knowledge-based short term load forecasting technique. IEEE Trans. on Power Systems, Vol.8, No.2, 1993, pp. 508-514.
• [28] Rutkowski L.: Methods and Techniques of Artificial Intelligence. PWN, Warszawa, 2005, Poland (in Polish).
• [29] Simon G., Lendasse A., Cottrell M., Fotr J.C., Verleysen M.: Double SOM for long-term time series prediction. Proceedings of the European Workshop on Self-Organizing Maps, Hibikino, Japan, 2003, pp. 35-40.
• [30] Tamimi M., Egbert R.: Short term electric load forecasting via fuzzy neural collaboration, Electric Power System Research, Vol.56, 2000, pp. 243-248.
• [31] Vermaak J., Botha E.C.: Recurrent neural networks for short-term load forecasting. IEEE Trans. on Power Systems, Vol.13, No.1, 1998, pp. 126-132.