Wind Power Prediction Model Based on Capuchin-Prairie Dog Optimization Technique
Hamed M. Aly, Rabab
Hamed M. Aly, Rabab
Type
Supervisor
Date
2025-10-01
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Wind energy production is involved in the existing conventional energy system or microgrid. Integrating renewable distributed generators into distribution networks offers numerous advantages in terms of technology, economy and the environment. Wind power output is significantly concerned by the wind speed, which results in unpredictable alternatives in power production. The wide range of wind speeds, a critical factor in producing energy, describes several opportunities for short-term wind power forecasting. The data set of wind turbines comprises measurements of different parameters, including wind velocity, wind flow orientation and other environmental factors that affect the measurement of wind energy production. Recently, various AI and optimization-based methods have been improved for wind production forecasting. Many wind power prediction projects estimate the total power generated by all turbines in the area, considering time-varying characteristics. Unfortunately, the location and surroundings of wind turbines are often overlooked, and there is a lack of consideration for the variability of power output from turbines at various locations. Furthermore, effective wind power prediction is a complex undertaking that must consider the geographic proximity of wind power factors and the time dependence of sequential data. The model of this paper is based on optimization techniques called Capuchin-Prairie Dog Optimization (CPDO). The objective of the proposed method is to systematically examine the correlation between different wind parameters such as average wind speed, average wind direction and wind power. It purposes to adopt the values of parameter selection, at last adjusting the predictive accuracy of the model. The proposed technique also evaluates the prediction values of wind speed, and it achieved a higher performance and the overall evaluation in short-term wind energy prediction, demonstrating superior prediction accuracy.
Department
Publisher
Sponsor
Copyright
Book title
The Future of Inclusion: Bridging the Digital Divide with Emerging Technologies