Abstract
Wind speed forecasts can boost the quality of wind energy generation by increasing the efficiency and enhancing the economic viability of this variable renewable resource. This work proposes a hybrid model for wind energy capacity for electrical power generation at coastal sites by utilizing wind-related variables’ characteristics. The datasets of three coastal locations of Kuwait validate the proposed method. The hybrid model is a merger of Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) and predicts one-month-ahead wind speed for wind power density calculation. The neural network starts its performance evaluation with a variable number of hidden-layer neurons to finally identify the optimal ANN topology. Comparisons of statistical indices with both expected and observed test results indicate that the ANN-PSO based hybrid model with the low root-mean-square-error and mean-square-error values outperforms ANN-based trivial models. The prediction model developed in this work is highly accurate with a Mean Absolute Percentage Error (MAPE) of approximately (3-6%) for all the sites.
Highlights
Renewable energy sources have received considerable scientific attention due to the rapid depletion in fossil fuel resources
The prediction of the wind power density on short-term bases, one-day-ahead forecast models based on an artificial neural network (ANN) Support Vector Machines (SVM), and a hybrid model that combines Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) is developed and implemented
The accuracy was assessed by using the root-mean-square error (RMSE) and Mean Absolute Percentage Error (MAPE) as a performance index
Summary
Renewable energy sources have received considerable scientific attention due to the rapid depletion in fossil fuel resources. The prediction of the wind power density on short-term bases, one-day-ahead forecast models based on an artificial neural network (ANN) Support Vector Machines (SVM), and a hybrid model that combines ANN and PSO is developed and implemented. It involves three input variables, including the wind speed, generation hours and relative humidity, and one variableenergy output of the wind farms. The data set was analyzed from three different Kuwait locations, including Al Wafrah, Abadaly, and Al Asimah, composed of regular sampled meteorological variables linked to winding. The data examination highlights the numbers of second-standard deviations, third-standard deviations, and forth-standard deviation outliers, which can be eliminated from the training data to ensure the useful estimation of wind potential
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have