Day-ahead Electricity Price Prediction Based on Improved ANN Information Fusion

• Autorzy: Li K.

Warianty tytułu

PL

Jednodniowa predykcja cen elektryczność metodą fuzji danych z wykorzystaniem sieci neuronowych

• Języki publikacji: EN

Abstrakty

EN

A novel information fusion method is proposed based on the characters of day-ahead electricity price. An improved BPNN is used for its better performance as the core algorithm of information fusion. Using the information fusion ideas, a new modelling approach is proposed to establish the prediction model. The day-ahead electricity price prediction model is tested by the real data. The experiments demonstrate that the new prediction model established by improved BPNN information fusion method has better performance.

PL

W artykule przedstawiono nową metodę fuzji danych w oparciu o charakterystyki cenowe elektryczności z dnia poprzedniego. Algorytm oparto na sieci neuronowej BPNN. Jego działanie poddano badaniom, bazując na prawdziwych danych, których wyniki wskazują na skuteczność działania proponowanego rozwiązania.

Słowa kluczowe

EN

information fusion; electricity price prediction; BP neural network

PL

fuzja danych; predykcja cen elektryczności; sieć neuronowa BP

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2013
• Tom: R. 89, nr 3b
• Strony: 78--80
• Opis fizyczny: Bibliogr. 11 poz., schem., tab.

Twórcy

autor

Li K.

• School of Management, Tianjin Polytechnic University, Tianjin, China, 300387

Bibliografia

• [1] Haldrup N, Haldrup Niels Haldrup, MO, et al. A RegimeSwitching Long Memory Model for Electricity Prices, Journal of Econometrics, Vol. 135, No. 1-2, pp. 349-376, 2006.
• [2] A.J.Conejo, M.A.Plazas, R.Espinola, et al. Day-ahead Electricity Price Forecasting Using the Wavelet Transform and ARIMA Models. IEEE Transactions on Power Systems, Vol. 20, No. 2, pp. 1035-1042, 2005.
• [3] Liu Da, Niu Dongxiao, etc. al., Combined Models for Dayahead Electricity Price Forecasting Based on Improved Gray Correlation Methodology, Kybernetes: The International Journal of Systems & Cybernetics, Vol. 38, No. 3-4, pp. 354-361, 2009.
• [4] Muge Mutlu, Sorin C. Popescu, Curt Stripling and Tom Spencer. Mapping Surface Fuel Models Using Lidar and Multispectral Data Fusion for fire behavior, Remote Sensing of Environment, Vol. 112, No. 2-3, pp. 274–285, 2008.
• [5] Robi Polikar, Apostolos Topalis, Devi Parikh, Deborah Green, Jennifer Frymiare, John Kounios and Christopher M. Clark. An Ensemble Based Data Fusion Approach for Early Diagnosis of Alzheimer’s Disease. Information Fusion, Vol. 9, No. 1, pp. 83–95, 2008.
• [6] Huixin Tian, Zhizhong Mao, Shu Wang and Kun Li, Application of Genetic Algorithm Combined with BP Neural Network in Soft Sensor of Molten Steel Temperature, Proceedings of the 6th World Congress on Control and Automation, 2006, June, 21-23, dalian China, 1-12: 7742-7745.
• [7] Q. Tao, Tj. Fang, H. Qiao, “A novel continuous-time neural network for realizing associative memory”, IEEE Transactions on Neural Networks, vol. 12, no. 2, pp. 418-423, 2001.
• [8] PJM, 2007. Summary of PJM-Initiated Load Management Events, September 2007, available at http://www.pjm.com/planning/resadequacy/downloads/20070907-alm-history.pdf.
• [9] PJM Daily Real-Time Locational Marginal Pricing Files, available at http://www.pjm.com/markets/jsp/lmp.jsp.
• [10] PJM, 2008. Manual 11, Scheduling Operations. Revision 34, February 21, 2008, pp. 104–106, available at http://www.pjm.com/contributions/pjm-manuals/pdf/m11.pdf
• [11] Tian Huixin, Zhang Mu; Meng Bo, Prediction of day-ahead electricity price based on information fusion, Proceedings of ICCIA 2010, pp: 457-460, 2010.