The natural environment of the island is characterized by large uncertainties, such as temperature, humidity, and irradiance, which may affect the power generation efficiency of renewable energy. This paper takes the photovoltaic power generation as the research background, studies the direct relationship between the photovoltaic power generation power and the external environment (irradiance and temperature), and proposes a generalized regression neural network prediction (GRNN) based MPPT control strategy. Firstly, starting from the mathematical model of photovoltaic power generation system, under the premise of neglecting the power loss of DC/DC converter, the relationship between the maximum output power of the photovoltaic system and the optimal duty cycle is obtained. Then, the GRNN is trained with historical simulation data to obtain a direct relationship between the maximum output power of the photovoltaic system, the external environment (irradiance and temperature), and the internal parameters of the photovoltaic cell that affect the power generation efficiency. Finally, some simulation experiments are done in simulink. The results verify that the MPPT strategy proposed in this paper has better transient performance than traditional P&O method in photovoltaic power generation system.
[1]
Bin Wang,et al.
An improved perturbation and observation maximum power point tracking algorithm based on a PV module four-parameter model for higher efficiency
,
2017
.
[2]
S. Sheik Mohammed,et al.
A novel hybrid Maximum Power Point Tracking Technique using Perturb & Observe algorithm and Learning Automata for solar PV system
,
2016
.
[3]
Kashif Ishaque,et al.
The performance of perturb and observe and incremental conductance maximum power point tracking method under dynamic weather conditions
,
2014
.
[4]
S. Saravanan,et al.
RBFN based MPPT algorithm for PV system with high step up converter
,
2016
.
[5]
Shaowu Li,et al.
Maximum power point tracking control strategies with variable weather parameters for photovoltaic generation systems
,
2013
.
[6]
Carlos Andrés Ramos Paja,et al.
Maximum power point tracking of photovoltaic systems based on the sliding mode control of the module admittance
,
2016
.