A genetic programming approach for the prediction of solar chimney power plant power

Abstract

This study empirically examines the effectiveness of the solar chimney power plants (SCPP), which is an innovative method for the use of solar energy, in the middle latitude region (37.88° N) in the northern hemisphere. Experimental measurement parameters of temperature, velocity, and radiation obtained from four cardinal directions (north, south, east, and west) and from 26 different locations were recorded throughout the day (08:00 am-07:30 pm). These measurements were used to calculate and estimate the power values used to measure the energy efficiency of the solar chimney. In the study, the genetic programming method was used to estimate the power value. In the five different forecast models developed, 15 different parameters were used diagonally. The obtained power estimation equations were cross-checked using statistical methods. Determination coefficient value is higher than >0.90 in all equations and is close to the ideal. In the comparison of all statistical models, the Global Performance Indicator (GPI) was used, with the best result obtained from Model 2. The results of this model are MAPE:6.5233, MBE: −0.0124, RMSE:1.1036 ve t-stat:0.0374, which is quite close to zero. In addition, the power values obtained from both the calculated and developed models were dimensioned and compared over the power-time factor of eight different studies in the literature. The mean relative error value nof the values calculated as a result of this comparison varies between 2.3% and 21.3%. This study provides a model for the different geometries of solar chimney prototypes and provides an example for measuring the design and performance of solar chimney systems to be installed in the middle latitudes and in regions with “Csa” climate characteristics, and is recommended for academic and industrial users. The mathematical models developed can be considered as a step to increase the efficiency of the solar chimney power plants.