No abstract

The propose of this work is to describe the implementation of a controller for tracking the point of maximum power transfer based on neural networks, using a microcontroller of the PIC family, on energy systems that use photovoltaic panels. A neural network is used to determine at each instant, the output voltage in a DC-DC boost converter connected to the solar panels, in way to obtain the maximum power transfer of these panels. This implementation releases the use of a great performance computer, once the neural network was already trained and this way, it can be implemented in a dedicated system. The maximum power transfer of the system is obtained adjusting the duty cycle of the DC-DC boost converter. One three-phase inverter was implemented with a new control circuit to generate the PWM signal. Vontificia Universidade Catolica do Rio Grande do SUIPUCRS -FENG -DEE CEP 906 19-900 -Avenida Ipiranga, 668 1Porto Alegre -RS -B r a d e-mai I: fdosreis @ ieee.org temperature of these cells. Several techniques that use non linear equations systems to describe the operation of photovoltaic cells have been used to determine the maximum power point (2,4]. An alternative to this approach has been the employment of artificial neural networks [ l,51, with which were obtained excellent I-esults, once these constitute a universal approximator for non-linear dynamic systems.The objective of this work is to describe the application of an artificial. neural network to determine the maximum power transfer point i n energy systems based on photovoltaic panels. The implantation of this neural network is made with a microcontroller of the PIC family [6], in way to build a low cost and efficient system. One three-phase inverter based on FPCA device was implemented to maintain 'simplicity and low cost. DESCRIPTION OF THE SYSTEM I. INTRODUCTIONThe technology on photovoltaic systems comes expanding, thanks to growing demand for energy alternatives, mainly for safe sources and clean energy sources [ I ] . Photovoltaic cells are non-linear devices, where the current/voltage characteristics depend mainly of the solar irradiation [2]. These devices are expensive and have low efficiency.Studies . shows that on energy systems based on photovoltaic cells, 57% of the total costs of the implantation refer at the cost of tlie solar panels and 30% refer at the cost of the battery systems [3]. In way to turn economy viable the implantation of this energy source, is essential the construction of a system that always obtain the maximum power of these solar panels. Several systems that permit the maximum power transfer between the photovoltaic panels and the power net were proposed, in way to increase the efficiency and to decrease the costs. The objective of these systems is to obtain through electronic circuits and of control algorithms, adjustment in the output voltage of the photovoltaic cells,'in way to obtain at any moment, always the maximum power allowed. The maximum power supplied by a system based on photovoltaic cells change with the time...

No abstract

No abstract

No abstract