Harnessing Data Types for Energy Efficiency: Innovative Cloud Approach. From Theory to Practice: Designing and Assessing Energy-Efficient Load Balancing Algorithms for Cloud Computing

      Аннотация: Maintaining accuracy in load balancing using metaheuristics poses challenges despite recent hybrid approaches. Optimized metaheuristic methods are employed to balance loads in the cloud efficiently. Multi-objective Quality of Service (QoS) metrics like reduced SLA violations, makespan, high throughput, and low energy consumption are crucial. Cloud applications, being computation-intensive, demand effective load balancing to prevent poor solutions due to exponential memory growth.To enhance load balancing in cloud computing, a new hybrid model is proposed, performing file classification using Filetype formatting. Three algorithms—Ant Colony Optimization using Filetype Formatting (ACOFTF), Data Format Classification using Support Vector Machine (DFC-SVM), and Datatype Formatting DFTF/DTF—are developed.Overall, the proposed hybrid metaheuristic approaches offer promising solutions for enhancing load balancing in cloud computing environments.

Ключевые слова: Cloud, load balancing, energy efficiency, Optimization, classification, Hybrid, ACO, pco, SVM