QRGEC: quantum reinforcement learning with golden jackal optimization for resilient edge cloud coordination in...

Area of Science:

• Computer Science
• Quantum Computing
• Artificial Intelligence

Background:

• Existing edge cloud coordination mechanisms struggle with resilience, energy efficiency, and adaptability in dynamic Internet computing environments.
• Current optimization and learning methods exhibit slow convergence and limited robustness for distributed edge cloud resource management.

Purpose of the Study:

• To introduce QRGEC (Quantum Reinforcement Learning with Golden Jackal Optimization) for resilient edge cloud coordination.
• To enhance distributed Internet computing optimization through quantum-enhanced policy exploration and adaptive metaheuristic tuning.

Main Methods:

• Utilizing variational quantum circuits for policy representation to explore high-dimensional decision spaces.
• Employing Golden Jackal Optimization to adapt reinforcement learning parameters for improved convergence and learning speed.
• Implementing a resilience-aware scheduler to balance energy efficiency, latency, and recovery in edge cloud workloads.

Main Results:

• QRGEC achieved a 36.8% latency reduction, 24.7% increase in energy efficiency, and 48.2% improvement in resilience compared to baseline methods.
• Demonstrated sustained resource utilization of 94% and autonomous recovery from network congestion and failures.
• Successfully balanced latency-energy trade-offs and conserved energy in heterogeneous edge and cloud environments.

Conclusions:

• QRGEC offers a robust and efficient solution for edge cloud coordination in Internet computing.
• The framework demonstrates significant improvements in performance, resilience, and energy conservation.
• QRGEC shows promise for autonomous management and optimization of dynamic distributed systems.