Abstract
Photovoltaic (PV) energy is a free-energy that is used
as an alternative to fossil fuel energy. However, PV system
without maximum power point tracking (MPPT) produces a low,
unstable power and with a long energy pay-back time. This paper
presents an innovative artificial neuro-fuzzy inference system
(ANFIS) MPPT technique that could extract maximum power
from a complete PV system and with a lessened EPBT. To
confirm the effectiveness of the ANFIS algorithm, its result was
compared with the results of PV system using Perturb&Observe
(P&O) technique, non-MPPT technique, combination of artificial
neural network and support vector machine as ANN-SVM
technique and using Pretoria city weather data as case studies.
Results show that ANFIS-MPPT yielded the best result and with
the lowest EPBT.