An innovative coverage optimization method for smart information monitoring in agricultural IoT using the...

Area of Science:

• Agricultural Engineering
• Computer Science
• Optimization Algorithms

Background:

• Smart agriculture relies on Agricultural Wireless Sensor Networks (AWSN) for crop monitoring.
• Optimizing AWSN coverage is vital for efficiency but challenged by NP-hard problems in large-scale deployments.
• Traditional algorithms face limitations in accuracy and local convergence for sensor network optimization.

Purpose of the Study:

• To introduce a novel optimization algorithm for enhancing AWSN coverage in large-scale agricultural fields.
• To address the limitations of existing algorithms in terms of accuracy and convergence.
• To improve production efficiency and resource utilization in smart agriculture through optimized sensor networks.

Main Methods:

• Proposed a Multi-Strategy Pelican Optimization Algorithm (MSPOA).
• Integrated strategies: good point set, 3D spiral Lévy flight, and adaptive T-distribution variation.
• Incorporated pelican-inspired movement and collaboration for adaptability and robustness.

Main Results:

• MSPOA demonstrated significant improvements in network coverage compared to IABC, CAFA, APSO, and LCSO.
• Achieved coverage increases of 5.85%, 11.33%, 21.05%, and 20.66% over benchmark algorithms.
• MSPOA showed strong adaptability and stability in dynamic agricultural environments.

Conclusions:

• The novel MSPOA effectively optimizes AWSN coverage for smart agriculture.
• MSPOA overcomes traditional algorithm limitations, offering enhanced accuracy and global search capabilities.
• The algorithm's adaptability and robustness are beneficial for real-world agricultural applications.