An optimization method for wireless sensor networks coverage based on genetic algorithm and reinforced whale...

Area of Science:

• Computer Science
• Network Engineering
• Optimization Algorithms

Background:

• Random node deployment in wireless sensor networks (WSN) leads to coverage redundancy and holes.
• Existing optimization methods struggle to balance global search and local development effectively.

Purpose of the Study:

• To propose a novel WSN coverage optimization method, GARWOA, that integrates genetic algorithm (GA) and reinforced whale optimization algorithm (RWOA).
• To enhance the performance of the whale optimization algorithm (WOA) for improved exploration and development efficiency in WSN coverage optimization.

Main Methods:

• Population initialization using sine map and piecewise linear chaotic map (SPM) for even distribution.
• Non-linear improvement of the WOA control factor 'a' to boost exploration and development.
• Incorporation of a Levy flight mechanism to mitigate local optima and premature convergence.

Main Results:

• GARWOA demonstrated superior optimization ability across 10 standard test functions compared to other algorithms.
• In coverage experiments, GARWOA achieved coverage ratios of 95.73%, 98.15%, and 99.34%.
• GARWOA outperformed the mutant grey wolf optimizer (MuGWO) by 3.27%, 2.32%, and 0.87% in coverage ratio.

Conclusions:

• GARWOA effectively balances global search and local development for WSN coverage optimization.
• The proposed method significantly improves coverage ratios and overcomes limitations of existing algorithms.
• GARWOA offers a robust solution for addressing coverage redundancy and holes in wireless sensor networks.