Chaotic Salp Swarm Optimization-Based Energy-Aware VMP Technique for Cloud Data Centers

Area of Science:

• Cloud Computing
• Data Center Energy Efficiency
• Optimization Algorithms

Background:

• Increasing energy consumption in Cloud Data Centers (CDCs) necessitates efficient resource management.
• Virtual Machine Placement (VMP) is crucial for reducing energy usage but is an NP-hard problem.
• Metaheuristic Optimization Algorithms are commonly used for VMP challenges.

Purpose of the Study:

• To introduce a novel energy-aware VMP technique for CDCs.
• To enhance energy efficiency in CDCs through optimized virtual machine placement.
• To improve resource operation balancing (CPU, RAM, Bandwidth) and reduce waste.

Main Methods:

• Developed an Energy-Aware VMP technique based on the Disordered Salp Swarm Optimization Algorithm (EAVMP-CSSA).
• Integrated chaotic maps with the Salp Swarm Optimization Algorithm (SSA) to create CSSA for improved performance and reduced costs.
• Reduced CDC energy consumption by minimizing active servers supporting virtual machines.

Main Results:

• The EAVMP-CSSA technique achieved a maximum service rate of 98.12%.
• Outperformed existing methods like Random (74.40%), FFD (78.80%), ACO (90.70%), and AP-ACO (96.31%).
• Demonstrated superior performance across various assessment metrics.

Conclusions:

• The proposed EAVMP-CSSA technique effectively reduces energy consumption in CDCs.
• The method enhances resource utilization and operational efficiency.
• EAVMP-CSSA represents a significant advancement in VMP strategies for energy-efficient data centers.