Forecast of Power Generation for Grid-Connected Photovoltaic System Based on Markov Chain

A grid-connected photovoltaic system has the characteristics of time-varying and random. A Markov chain model of the power generation forecast was built based on the Markov decision theory according to the 6 kW PV system operating data. The initial formation probability matrix and transition matrix for power generation forecast have been obtained. After considering the weather conditions, solar radiation and other specific factors, if the statistical sample is large enough, the theoretical calculations are very close to the actual results. The results show forecast of power generation for grid-connected photovoltaic system based on Markov chain is feasible, correct and effective. The initial state and termination status have the character of good correlation between the transfer matrix and the results are more relatively reliable.

[1]  Wang Xian.  An Improved Method for Short-Term Electric Load Forecasting Using Time Series Techniques , 2002 .

[2]  Liang Haifeng,et al.  An adaptive BP-network approach to short term load forecasting , 2004, 2004 IEEE International Conference on Electric Utility Deregulation, Restructuring and Power Technologies. Proceedings.

[3]  Saifur Rahman,et al.  Input variable selection for ANN-based short-term load forecasting , 1998 .

[4]  A.M. Al-Kandari,et al.  Fuzzy systems application to electric short-term load forecasting. II. Computational results , 2003, Large Engineering Systems Conference on Power Engineering, 2003.

[5]  Xiao Li-min.  Available Transfer Capability Calculation Based on Markov Chain and Enumeration Method , 2006 .

[6]  Lu Hai.  RECURSIVE AND ADAPTIVE SUPER-SHORT TERM LOAD FORECAST METHOD , 2000 .

[7]  Hiroyuki Mori,et al.  Short-term load forecasting with chaos time series analysis , 1996, Proceedings of International Conference on Intelligent System Application to Power Systems.

[8]  J. Samimi,et al.  Optimal sizing of photovoltaic systems in varied climates , 1997 .

[9]  T. Funabashi,et al.  Next day load curve forecasting using hybrid correction method , 2005, IEEE Transactions on Power Systems.

[10]  Gao Zhong-wen.  The Load Forecasting of Electric Energy Based on Time Sequence and Neural Network , 2003 .

[11]  Chen Hao.  A New Method of Load Forecasting Based on Generalized Autoregressive Conditional Heteroscedasticity Model , 2007 .

[12]  Bo Li,et al.  Short-term load forecast based on fuzzy wavelet support vector machines , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

[13]  Yijia Cao,et al.  Short-term load forecasting using a new fuzzy modeling strategy , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

[14]  Kuihe Yang,et al.  Design of short-term load forecasting model based on fuzzy neural networks , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

[15]  Hak-Keung Lam,et al.  Short-term electric load forecasting based on a neural fuzzy network , 2003, IEEE Trans. Ind. Electron..

[16]  Zhang Zhen-gao.  Load Derivation in Short Term Forecasting Using Weather Factor , 2006 .

[17]  Tai Neng-ling.  NEW PRINCIPLE BASED ON WAVELET TRANSFORM FOR POWER SYSTEM SHORT-TERM LOAD FORECASTING , 2003 .