Multi-Group Gorilla Troops Optimizer with Multi-Strategies for 3D Node Localization of Wireless Sensor Networks.

Area of Science:

• Computer Science
• Electrical Engineering
• Artificial Intelligence

Background:

• Wireless sensor networks (WSNs) face significant challenges in accurate node localization.
• Existing optimization algorithms often struggle with exploration and diversity, impacting localization precision.

Purpose of the Study:

• To propose and evaluate an Opposition-based learning and Parallel strategies Artificial Gorilla Troop Optimizer (OPGTO) for reducing WSN localization error.
• To enhance the global exploration capability and population diversity of optimization algorithms.

Main Methods:

• Implemented opposition-based learning to expand the algorithm's exploration space.
• Utilized a parallel strategy to divide populations, increasing diversity and designing inter-group communication.
• Tested OPGTO on the CEC2013 benchmark functions and compared it with PSO, SCA, WOA, and GTO.

Main Results:

• OPGTO demonstrated superior optimization performance, particularly on complex multimodal and combinatorial functions.
• The algorithm effectively reduced localization error in 3D wireless sensor networks on real terrain.
• OPGTO showed significant improvements over existing algorithms in localization accuracy using Time Difference of Arrival (TDOA).

Conclusions:

• OPGTO offers a robust and effective approach for optimizing complex problems, including WSN localization.
• The combination of opposition-based learning and parallel strategies enhances algorithmic performance.
• OPGTO successfully addresses the challenge of reducing localization errors in real-world WSN applications.