Fuzzy game-theoretic optimization for sustainable cloud computing

Cloud computing has become a cornerstone of modern technology, yet optimizing resource allocation while ensuring sustainability remains a significant challenge. This research explores the application of fuzzy game theory to optimize the allocation of renewable energy in cloud data centers (CDCs) based in virtual machine (VM) migration, aiming to improve energy efficiency and system performance. The purpose of the study is to enhance decision-making in cloud environments by integrating fuzzy logic into game-theoretic optimization. The approach is based on the Game Theory-enhanced Gray Wolf Optimizer (GTGWO) algorithm, which incorporates fuzzy rules to model uncertainties in cloud system dynamics. The proposed model was implemented and evaluated using a set of cloud computing scenarios, including varying workloads and renewable energy availability across multiple data centers. The results demonstrate that the GTGWO algorithm significantly outperforms traditional optimization algorithms, achieving improvements of up to 2.17% in renewable energy usage compared to existing methods. This work concludes that the integration of fuzzy game theory provides a more efficient and interpretable solution for optimizing energy consumption in cloud computing systems, offering valuable insights for sustainable cloud infrastructure management. • Integration of fuzzy logic into game theory, using fuzzy payoffs and strategies. • Novel fuzzy game-theoretic optimization, modeling strategic players with fuzzy rules. • Intelligent knowledge acquisition mechanism in game theory for cloud optimization.