This paper proposes a maximum power point tracking scheme using neural networks for a grid connected photovoltaic system. The system is composed of a photovoltaic array, a boost converter, a three phase inverter and grid. The neural network proposed can predict the required terminal voltage of the array in order to obtain maximum power. The duty cycle is calculated and the boost converter switches are controlled. Hysteresis current technique is applied on the three phase inverter so that the output voltage of the converter remains constant at any required set point. The complete system is simulated using MATLAB/SIMULINK software under sudden weather conditions changes. Results show accurate and fast response of the converter and inverter control and which leads to fast maximum power point tracking.
- Neural networks
- Grid connected
- Maximum power point tracking
- Photovoltaic system
- Hysteresis control.
Fig. 1. Block diagram of the grid connected photovoltaic system
EXPECTED SIMULATION RESULTS:
Fig. 2. Power-voltage curves for the two cases
Fig. 3. (a) Temperature, (b) Irradiance, (c) Output power of the array, (d)Terminal voltage of the array.
Fig. 4. (a) Reference voltage of inverter control, (b) Voltage at inverter’s DC side.
This paper presents a complete control scheme for a grid connected photovoltaic system. The whole system was simulated and the controllers were tested. The proposed maximum power point tracking control using neural networks maintains accurately the maximum power and shows fast dynamic response against sudden environmental condition changes or disturbances. Further research can be carried out in the near future to implement a physical model of the system and to compare the applied scheme with other conventional ones.
- G. Villalva, J. R. Gazoli and E. Ruppert F. “Analysis and simulation of the P&O MPPT algorithm using alinearized array model”. Power electronics conference, 2009, Brazil.
- Safri and S. Mekhilef. “Incremental conductance MPPT method for PV systems”. Electrical and Computer Engineering (CCECE). 2011. Canada.
- I. Sulaiman, T.K. Abdul Rahman, I.Musirin and S.Shaari. “Optimizing Three-layer Neural Network Model for Grid-Connected Photovoltaic output prediction”. Conference on innovative technologies in intelligent systems and industrial applications.2009.
- Subiyanto, A.Mohamed and M.A.Hannan. “Maximum Power Point Tracking in Grid Connected PV System using A Novel Fuzzy Logic Controller”. IEEE student conference on research and development, 2009.
- Trishan Esram and Patrick L. Chapman. “Comparison of Photovoltaic Array Maximum Power Point Tracking Techniques. “ IEEE Transactions on energy conversion, Vol.22, NO. 2, 2007.