Dynamic wind-integrated hydrothermal scheduling using a novel oppositional learning-based chaotic whale algorithm

Recent challenges in the power generation sector include high generation costs and environmental pollution due to high dependence on fossil fuels. In this proposed work, these issues are addressed and overcome by integrating wind energy with thermal plants. In recent times, the whale algorithm (WA), inspired by food-searching behavior, has proven to be an effective real-time issue solver by addressing difficult challenges in recent times. To boost dynamic optimization efficiency and manage more complex constraints, the work has included an OL-based chaotic approach into the WA. To evaluate the efficacy of the enhanced WA, specifically the oppositional learning-based chaotic WA (OL-CWA), three scenarios, such as economic load scheduling (ELS), economic emission scheduling (EES), and combined economic emission scheduling (CEES), related to conventional and wind-integrated scheduling problems have been analyzed. The OL-CWA method has been utilized to optimally allocate the required power among the selected power plants, aiming to minimize pollution and achieve cost-effective power generation. The robustness of OL-CWA and the usefulness of wind energy in the scheduling problem have been shown by achieving 11% reduction in generation costs and 30% decrease in emissions, compared to the conventional scheduling model. The effective performance of OL-CWA has been also observed by comparing the optimal results of ELS, EES, and CEES from the results of other algorithms like WA, differential evolution (DE), modified DE, particle swarm optimization (PSO), quantum-behaved PSO, etc. Superiority of the proposed wind-based generation model has been demonstrated through its reduced emissions and costs, which can help to mitigate environmental degradation caused by excessive pollution from traditional power plants.