A quantum fuzzy logic-enhanced evolutionary framework for energy-latency optimization in 6G Edge-IioT

Area of Science:

• Network Engineering
• Artificial Intelligence
• Edge Computing

Background:

• The 6G Industrial Internet of Things (IIoT) demands Ultra-Reliable Low-Latency Communication (URLLC), posing a challenge for energy efficiency.
• Resource orchestration in dynamic edge environments is complex and often leads to suboptimal performance with traditional methods.

Purpose of the Study:

• To develop a robust multi-objective orchestration framework, QFLN-AMRO, addressing the energy-latency trade-off in 6G IIoT.
• To enhance resource management by integrating advanced AI techniques for dynamic parameter adjustment.

Main Methods:

• Proposed QFLN-AMRO framework integrating a Fractional-Order NSGA-II evolutionary engine and a Quantum Fuzzy Logic Network (QFLN).
• Incorporated a Lyapunov-guided resilience mechanism to prevent network saturation under URLLC stress.
• Validated using real-world data from EUA spatial topologies, Edge-IIoT payloads, and Google Cluster Traces.

Main Results:

• QFLN-AMRO significantly reduced energy consumption while ensuring deterministic latency thresholds.
• Demonstrated superior performance compared to state-of-the-art deep reinforcement learning (PPO, GAT) and metaheuristic algorithms (GA, PSO, GWO).
• Statistical analysis (Omnibus ANOVA, Tukey HSD) confirmed the framework's reliability and robustness.

Conclusions:

• QFLN-AMRO offers a reliable solution for next-generation edge orchestration in 6G IIoT.
• The framework effectively resolves the conflict between low latency and energy efficiency in demanding network conditions.