Correlation analysis and MLP/CMLP for optimum variables to predict orientation and tilt angles in intelligent solar tracking systems

Abstract

Different solar tracking variables have been employed to build intelligent solar tracking systems without considering the dominant and optimum ones. Thus, several low performance intelligent solar tracking systems have been designed and implemented due to the inappropriate combination of solar tracking variables and intelligent predictors to drive the solar trackers. This research aims to investigate and evaluate the most effective and dominant variables on dualand single-axis solar trackers and to find the appropriate combination of solar variables and intelligent predictors. The optimum variables will be found by using correlation results between different variables and both orientation and tilt angles. Then, to use the selected variables to develop different intelligent solar trackers. The results revealed that month, day, and time are the most effective variables for horizontal single-axis and dual-axis solar tracking systems. Using these variables in cascade multilayer perceptron (CMLP) and multilayer perceptron (MLP) produced high performance. These predictors could predict both orientation and tilt angles efficiently. It is found that day variable is very effective to increase the performance of solar trackers although day variable is neither correlated nor significant with both orientation and tilt angles. Linear regression predicted less than 70% of the given data in most cases, whereas nonlinear models could predict the optimum orientation and tilt angles. In single-axis tracker, month, day, and time variables achieved prediction rates of 96.85% and 96.83% for three hidden layers of MLP and CMLP, respectively, whereas the MSE are 0.0025 and 0.0008, respectively. In dual-axis solar tracker, MLP and CMLP predicted 96.68% and 97.98% respectively, with MSE of 0.0007 for both.