This paper presents the design and implementation of a neural network using backpropagation method in order to track the maximum power point of a solar panel by focusing it to the sunlight; this is achieved due to the prediction ability of the network which will use light sensors in order to rotate the solar panel to its optimal position. All of this is implemented using a prototype that contains: a solar panel, a motor and six photovoltaic sensors. The sensors are the entries of the network that based on its training should be able to analyze the data and then transform it into an output that allows the actuator to rotate the panel to a specific location.