Green Communication in Internet of Things: A Hybrid Bio-Inspired Intelligent Approach.

Area of Science:

• Computer Science
• Electrical Engineering
• Artificial Intelligence

Background:

• Internet of Things (IoT) networks face significant energy consumption challenges.
• Inefficient cluster head (CH) distribution and selection lead to higher energy usage in IoT networks.
• Optimizing energy consumption is crucial for extending the operational life of IoT devices.

Purpose of the Study:

• To propose a Hybrid Intelligent Optimization Algorithm (HIOA) for optimal cluster formation in IoT networks.
• To minimize overall energy consumption and improve network load balancing.
• To enhance the efficiency of IoT networks through bio-inspired optimization techniques.

Main Methods:

• A novel Hybrid Intelligent Optimization Algorithm (HIOA) combining fuzzy logic, Chicken Swarm Optimization (CSO), and a genetic algorithm was developed.
• The HIOA utilizes a fitness function to minimize inter- and intra-cluster distances and communication energy.
• CSO's hierarchical classification combined with genetic crossover and mutation enhances population diversity for balanced CH distribution.

Main Results:

• The HIOA algorithm achieved optimal performance with specific parameters: popsize=60, Nr=0.3, Nh=0.6, and θ=10.
• Simulations in MATLAB2019A demonstrated HIOA's effectiveness compared to traditional bio-inspired algorithms.
• HIOA resulted in a 12% decrease in node death percentage, a 19% increase in average residual energy, and a 23% improvement in network lifetime.

Conclusions:

• The proposed HIOA algorithm effectively addresses energy consumption issues in IoT networks.
• HIOA provides a superior solution for cluster formation, leading to balanced network load and extended network lifetime.
• This hybrid approach offers significant advantages over existing bio-inspired algorithms for IoT energy optimization.