Büyükbıçakcı, ErdalAtlı, CahitDumanlı, MetinBulat, Selçuk2025-04-082025-04-082024979835035293110.1109/ICMNWC63764.2024.108720322-s2.0-105000142276https://doi.org/10.1109/ICMNWC63764.2024.10872032https://hdl.handle.net/11501/20834th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024, Tumkuru -- 4-5 December 2024Modern energy management struggles to integrate renewable energy (RE) resources like wind and solar electricity into power networks. Accurate power forecasting models improve grid reliability and stability, helping solve this problem. This research analyses renewable energy power forecasting models' literature, focusing on significant improvements in the last decade.High-quality statistical error metrics-based forecasting model research articles are examined. The proposed system includes data analysis, feature engineering, and model training. Feature engineering includes normalization, PCA, and WD. To increase the feature set, photovoltaic (PV) and wind power generating factors are considered. The GA-SVM-based model forecasted solar power outputs in renewable energy systems with 93.18% training accuracy. Innovative renewable energy forecasting methods, including feature engineering and model optimization, are reviewed in this article. For optimal RE resource integration into power networks, renewable energy forecasting must be more accurate and efficient.eninfo:eu-repo/semantics/closedAccessGenetic Algorithm (GA)Photovoltaic Power ForecastingRenewable EnergyConference ObjectN/A