2026-05-04T23:04:13.324Z http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai

ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai:1:11821 2026-03-27T12:38:48Z 1

Optimizing Recurrent Neural Networks for Solar Energy Forecasting Using Modified Metaheuristics 2025 http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai/record/1/11821 https://ieeexplore.ieee.org/abstract/document/11256238 D. Bulaja S. Andjelic T. Zivkovic L. Jovanovic M. Zivkovic N. Bacanin S. Ivanovic Addressing climate change, reducing greenhouse gas emissions, and achieving global sustainability goals all depend on the switch to renewable energy. Distributed solar power integration with traditional electrical networks is fraught with difficulties, though. The inherent unpredictability and irregularity of solar energy generation make integrating it with grid operations more challenging. One important technique for dealing with these issues is time-series forecasting. System operators can improve energy storage management, optimize power distribution, and preserve system stability with accurate forecasts of solar energy output. The capacity of recurrent neural networks (RNNs) to represent temporal connections and identify intricate nonlinear patterns in sequential data is well known. However, hyperparameter adjustment, a computationally demanding and NP-hard job, is crucial to their success. Because of their ability to effectively explore high-dimensional search spaces, metaheuristic algorithms have become popular as a solution to this problem. In this work, a method that combines RNNs with a modified crayfish optimization algorithm (COA) tailored for time-series forecasting of solar energy production is presented. Tests on solar power plant data from India show the method’s potential, with the best-performing models reaching mean absolute errors (MAEs) as low as 0.092387. conferenceObject 1 6 10.1109/InC465408.2025.11256238 2025 IEEE International Conference on Contemporary Computing and Communications (InC4), IEEE, Bangalore, India