The application of different optimization techniques and Artificial Neural Networks (ANN) for coal-consumption forecasting: a case study

The demand for energy on a global scale increases day by day. Unlike renewable energy sources, fossil fuels have limited reserves and meet most of the world's energy needs despite their adverse environmental effects. This study presents a new forecast strategy, including an optimization-based S curve approach for coal consumption in Turkey. For this approach, Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), Grey Wolf Optimization (GWO), and Whale Optimization Algorithm (WOA) are among the meta-heuristic optimization techniques used to determine the optimum parameters of the S curve. In addition, these algorithms and Artificial Neural Network (ANN) have also been used to estimate coal consumption. In evaluating coal consumption with ANN, energy and economic parameters such as installed capacity, gross generation, net electric consumption, import, export, and population energy are used for input parameters. In ANN modeling, the Feed Forward Multilayer Perceptron Network structure was used, and Levenberg-Marquardt Back Propagation has used to perform network training. S curves have been calculated using optimization, and their performance in predicting coal consumption has been evaluated statistically. The findings reveal that the optimization-based S-curve approach gives higher accuracy than ANN in solving the presented problem. The statistical results calculated by the GWO have higher accuracy than the PSO, WOA, and GA with R2=0.9881, RE=0.011, RMSE=1.079, MAE=1.3584, and STD=1.5187. The novelty of this study, the presented methodology does not need more input parameters for analysis. Therefore, it can be easily used with high accuracy to estimate coal consumption within other countries with an increasing trend in coal consumption, such as Turkey.