Gray wolf algorithm based short therm hibrid wind power forecasting models and aplication

The increasing population of the world and the increasing energy demand accordingly have brought us the target of being clean and sustainable for the energy demanded today. For this reason, the orientation towards renewable energy systems has increased rapidly. Since the initial installation costs of wind energy systems are high, before the installation of a wind energy system in a desired region, the wind speed of the region and the wind power characteristics of the region should be determined, planning and survey studies should be done in this direction. This thesis study includes original intelligent heuristic forecasting models for wind power estimation and their applications. Intelligent heuristic approaches and their hybrid models, which are frequently used in recent years, have led to the emergence of more sensitive models with different decomposition methods or different optimization techniques. Gray Wolf Optimization (GWO), one of the meta-heuristic optimization algorithms used in this thesis, is basically based on the hunting method and social hierarchy of gray wolves in nature. This paper presents the Multi-strategy Random-weighted Gray Wolf Optimizer (MsRwGWO) including some effective and novel mechanisms added to the original GWO algorithm to improve the search performance. These are a transition mechanism for updating the parameter 𝑎⃗, a weighted updating mechanism, a mutation operator, a boundary checking mechanism, a greedy selection mechanism, and an updating mechanism of leader three wolves (alpha, beta, and delta wolves). We utilized some benchmark functions known as CEC 2014 test suite to evaluate the performance of MsRwGWO algorithm in this study. Firstly, during the solution of optimization problems, the MsRwGWO algorithm's behaviors such as convergence, search history, trajectory, and average distance were analyzed. Secondly, the comparison statistical results of MSRwGWO and GWO algorithms were presented for CEC 2014 benchmarks with 10, 30 and 50 dimensions. In addition, some of the popular meta-heuristic algorithms taken from the literature were compared with the proposed MsRwGWO algorithm for 30D CEC 2014 test problems. Finally, MsRwGWO algorithm was adapted to the training process of a MultiLayer Perceptron (MLP) used in wind speed estimation and comparative results with GWO based MLP were obtained. The statistical results of the benchmark problems and training performance of MLP model for short-term wind speed forecasting show that the proposed MsRwGWO algorithm has better performance than GWO algorithm.