Online prediction of ultra-short-term photovoltaic power using chaotic characteristic analysis, improved PSO and KELM

Abstract

Accurate photovoltaic (PV) power prediction can guarantee the stable operation of a power system. However, complex environmental factors contribute to the chaotic nature of PV power sequences, consequently affecting the prediction accuracy. In this paper, an online PV power prediction model is proposed based on chaotic characteristic analysis, improved particle swarm optimization (PSO), and kernel-based extreme learning machine (KELM). The proposed method includes data pre-processing, offline parameters extraction and online prediction. At first, historical data are classified according to the degree of fluctuation of PV power and seasonal characteristics. The PV power sequences are filtered by singular spectrum analysis (SSA) to eliminate noise and outliers. Then, extracted parameters include the decomposing modes of variational mode decomposition (VMD) and the ideal parameters of phase space reconstruction (PSR) and KELM. The ideal parameters are searched by improved PSO. Finally, during the online prediction process, the training data needs to be reconstructed using VMD and PSR to update the network of KELM at each point prediction. Chaotic characteristic analysis is reflected in the application of SSA, VMD and PSR. Compared with the other seven different prediction methods, the experimental results verify that the proposed method is effective with higher accuracy.