Multi-objective node placement optimization in multiplex 6G wireless networks using quantum-inspired evolutionary...

Area of Science:

• Computer Science
• Electrical Engineering
• Network Engineering

Background:

• Sixth-generation (6G) wireless networks require advanced node placement algorithms to manage complex, heterogeneous deployments.
• Existing single-layer graph models and traditional optimization methods fail to capture the interdependent nature of 6G networks.

Purpose of the Study:

• To develop a multi-objective optimization framework for efficient node placement in multiplex 6G wireless networks.
• To address challenges of high connectivity density and competing performance requirements in 6G network planning.

Main Methods:

• A multiplex graph representation models interactions between capacity, latency, and interference layers.
• Quantum-inspired representations facilitate global exploration and prevent premature convergence.
• A composite fitness expression optimizes network capacity, incentive-aware participation, and multi-layer node centrality.

Main Results:

• The proposed Quantum-Inspired Evolutionary Algorithm (QIEA) framework achieves a balanced fitness score of 3.0355 and a high node cooperation rate.
• QIEA improves overall deployment fitness by significant margins over random selection and greedy degree-based placement.
• The framework demonstrates [Formula: see text] faster convergence than standard Genetic Algorithms (GA).

Conclusions:

• The QIEA framework offers a superior, scalable solution for large-scale 6G network optimization.
• This approach effectively handles the complexities of interdependent layers in future wireless networks.
• The study highlights the potential of quantum-inspired learning for advancing 6G network design.