Theoretic analysis shows that the output power of the distributed generation system is nonlinear and chaotic. And it is coupled\nwith the microenvironment meteorological data. Chaos is an inherent property of nonlinear dynamic system. A predicator of the\noutput power of the distributed generation system is to establish a nonlinear model of the dynamic system based on real time series\nin the reconstructed phase space. Firstly, chaos should be detected and quantified for the intensive studies of nonlinear systems. If\nthe largest Lyapunov exponent is positive, the dynamical system must be chaotic. Then, the embedding dimension and the delay\ntime are chosen based on the improved C-C method. The attractor of chaotic power time series can be reconstructed based on the\nembedding dimension and delay time in the phase space. By now, the neural network can be trained based on the training samples,\nwhich are observed from the distributed generation system. The neural network model will approximate the curve of output power\nadequately. Experimental results show that the maximum power point of the distributed generation system will be predicted based\non the meteorological data.The system can be controlled effectively based on the prediction.
Loading....