Short-Term Power Prediction of Photovoltaic Plant Based on SVM with Similar Data and Wavelet Analysis

• Autorzy: Yang X. , Jiang F. , Liu H.

Warianty tytułu

PL

Krótkoterminowa predykcja mocy dla paneli fotowoltaicznych – zastosowanie maszyny wektorów pomocniczych z przykładowymi danymi i analizy Falkowej

• Języki publikacji: EN

Abstrakty

EN

Photovoltaic(PV) power prediction is an important way to guarantee the stability for grid-connected PV power generation. In this paper, a power prediction method of PV plant was proposed. Firstly, the solar radiation was predicted based on support vector machine(SVM) combining the wavelet analysis with similar data. Similar data was extracted from large amounts of historical data. The original solar radiation signal was decomposed into trend signal of low frequency band and random signal of high frequency band by wavelet decomposition. Then different SVM radiation prediction models were trained respectively and the prediction result of every model was combined to obtain the final predicted radiation. Furthermore, the short-term power was predicted by the power curve to better fit the relationship between solar radiation and output power. Simulation results show that the improved SVM model can better fit the characteristics of solar radiation and improve the prediction accuracy; the power prediction model using the power curve has good generalization capability for engineering application.

PL

W artykule przedstawiono metodę predykcji generowanej przez panele PV mocy. W algorytmie zastosowano maszynę wektorów pomocniczych oraz analizę falkową, które wykorzystano do predykcji promieniowania słonecznego, na podstawie danych historycznych. Dokonując porównania z krzywą mocy panelu określono zależność między promieniowaniem a mocą wyjściową. Badania symulacyjne wykazały, że proponowana nowa metoda pozwala na zwiększenie dokładności predykcji mocy.

Słowa kluczowe

EN

solar radiation; wavelet analysis; SVM; power curve

PL

promieniowanie słoneczne; predykcja; analiza falkowa; SVM; krzywa mocy

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2013
• Tom: R. 89, nr 5
• Strony: 81--85
• Opis fizyczny: Bibliogr. 16 poz., rys., tab., wykr.

Twórcy

autor

Yang X.

• School of Control and Computer Engineering,North China Electric Power University

autor

Jiang F.

• School of Control and Computer Engineering,North China Electric Power University

autor

Liu H.

• School of Control and Computer Engineering,North China Electric Power University

Bibliografia

• [1] Dr. Bernhard ERNST, Dr.Frank REYER, Wind power and photovoltaic prediction tools for balancing and grid operation, Integration of Wide-Scale Renewable Resources Into the Power Delivery System, 2009 CIGRE/IEEE PES Joint Symposium, 2009, 1-9
• [2] G. S. Kinsey, K. Stone, J. Brown, Energy prediction of amonix cpv solar power plants, Progress in Photovoltaics: Research and Applications, 19(2011),No.7,794-796
• [3] Elke Lorenz, Johannes Hurka and Detlev Heinemann, Irradiance Forecasting for the Power Prediction of Grid- Connected Photovoltaic Systems, IEEE Journal of Selected Topics In Applied Earth Observations and Remote Sensing, 2(2009),NO.1,2-10
• [4] M.G. Abraha, M.J. Savage, Comparison of estimates of daily solarradiation from air temperature range for application in crop simulations, Agricultural and Forest Meteorology, 148(2008),401–416
• [5] Jianwu Zeng, Wei Qiao, Short-Term Solar Power Prediction Using an RBF Neural Network, Power and Energy Society General Meeting, 2011 IEEE.1-8
• [6] C. Paolik, C. Voyant, M. Muselli and M. Nivet, Solar radiation forecast-ing using ad-hoc time series preprocessing and neural networks, Proc. 5th International Conference on Emerging Intelligent Computing technology and applications, 2009,898-907
• [7] Zengxin Wang , Shi Su, Shaoquan Zhang, The Application of Photovoltaic Power Prediction Technology, 2011 International Conference on Communications and Control (ICECC), 2011,2343-2346
• [8] Ji-Long Chen, Hong-Bin Liu and Wei Wu, Estimation of monthly solar radiation from measured temperatures using support vector machines, Renewable Energy, 36(2011), No.1, 413–420
• [9] A. Ahhi, M. Shamisi and M. Jama, Prediction of monthly average daily global radiation in Al Ain city - UAE using artificial neural networks, Proc. 4th Wseas International Conference on Renewable Energy Sources (RES 10), 2010, 109-113
• [10] Samsul Ariffin Abdul Karim, Balbir Singh Mahinder Singh, Radzuan Razali and Noorhana Yahya, Data Compression Technique for Modeling of Global Solar Radiation, 2011 IEEE International Conference on Control System, Computing and Engineering, 2011,348-352
• [11] H.B. Liu, D.T. Xie and W. Wu, Soil water content forecasting by ANN and SVM hybrid architecture Environ Monit Assess, Environmental Monitoring and Assessment, 143 (2008), 187–193
• [12] B.Dong, C. Cao and S.E. Lee, Applying support vector machines to predict building energy consumption in tropical region, Energy and Buildings, 37 (2005), 545–553
• [13] Rong Xiao, Jicheng Wang and Fuyan Zhang, An Approach to Incremental SVM Learning Algorithm, 12th IEEE International Conference on Tools with Artificial Intelligence, 2000, 268 - 273.
• [14] E.M. Crispim, Pedro M. Ferreira and A.E. Ruano, Solar radiation prediction using RBF neural networks and cloudiness indices, 2006 International Joint Conference on Neural Networks, 2006, 2611-2618
• [15] V. Vapnik, S.E. Golowich and A.J. Smola, Support vector method for function approximation, regression estimation and signal processing, Adv Neural Inf Process Syst, 9(1996), 281–287.
• [16] V. Vapnik. Statistical learning theory Wiley, New York (1998).