An improved energy-efficient cloud-optimized load-balancing for IoT frameworks

Area of Science:

• Computer Science
• Network Engineering
• Cloud Computing

Background:

• The proliferation of wireless communication and the Internet of Things (IoT) necessitates efficient network solutions.
• Existing IoT networks face challenges with communication overheads and data management, driving the need for advanced load-balancing techniques.
• Migrating IoT data and applications to the cloud requires specialized load balancing algorithms tailored for cloud-integrated IoT architectures.

Purpose of the Study:

• To design a novel cloud-based load balancer algorithm specifically for IoT networks.
• To improve network response time and reduce energy consumption in cloud-integrated IoT environments.
• To develop a load balancing solution that is easily integrable with existing IoT frameworks.

Main Methods:

• Analysis of actual and virtual host machine requirements in cloud computing environments.
• Development of a unique method for load control in cloud-integrated IoT networks.
• Integration of the proposed load balancer algorithm with existing IoT frameworks.

Main Results:

• The proposed load balancer significantly boosts IoT network response time by 60%.
• Demonstrated reductions in energy consumption (31%), execution time (24%), node shutdown time (45%), and infrastructure cost (48%).
• Simulation results confirm the effectiveness of the proposed framework in addressing IoT-based cloud load-balancing issues.

Conclusions:

• The developed cloud-based load balancer offers a superior solution for managing loads in cloud-integrated IoT architectures.
• The algorithm effectively enhances network performance metrics, including response time and energy efficiency.
• The proposed framework provides significant cost and time savings compared to existing solutions.