Firefly algorithm-based neural network for GCPV system output prediction: article / Nor Syakila Mohd Zainol Abidin

This paper presents a Multi-Layer Feedforward Neural Network (MLFNN) for predicting the AC power output from a grid-connected photovoltaic (GCPV) system. In the proposed MLFNN, Firefly Algorithm (FA) was employed as the optimizer and search tools of the MLFNN training parameters. FA was used to optimize the number of neurons in the hidden layer, the learning rate and the momentum rate such that the Root Mean Square Error (RMSE) was minimized. In addition, the MLFNN utilized solar irradiance (SI), ambient temperature (AT) and module temperature (MT) as its inputs and AC power as its output. Additionally, the optimal population size, absorption confession, learning algorithm and type of transfer functions in FA were also investigated in this study. The performance of the proposed FA-based MLFNN had been compared with the performance of the Classical Evolutionary Programming-based Neural Network (CEP-based MLFNN). The results showed that the proposed FA-based MLFNN had outperformed the CEP-based MLFNN in producing lower RMSE.