Table 1 Comparison of Existing Works
Study | Utilized technique | Dataset | Performance metrics | Advantages | Disadvantages |
|---|---|---|---|---|---|
Liang et al.8 | Evolutionary multi-task optimization using multisource knowledge transfer | Synthetic datasets | Task optimization accuracy, convergence speed | Significant improvement in task optimization | Limited scalability in high-dimensional IoT networks |
Mirjalili et al.21 | Multi-objective Gray Wolf Optimization (MOGWO) | Benchmark datasets | Convergence rate, Pareto front diversity | Foundational approach in multi-objective optimization | Limited exploitation capabilities |
Dev et al.3 | Rider-GWO hybrid algorithm | IoT-based synthetic dataset | Network lifetime, energy efficiency | Enhanced IoT network lifetime through hybrid techniques | Lack of multi-objective scalability |
Jin et al.22 | Hybrid Wolf optimization for control strategies | Electric motor control dataset | Energy efficiency, optimization accuracy | Practical application in control systems | Application-specific focus |
Bilal et al.32 | Quantum-enhanced Gray Wolf Optimizer | Breast cancer diagnostic dataset | Accuracy, convergence time | High accuracy in breast cancer diagnosis | Limited IoT-specific application |
Jain and Sharma17 | Hybrid SSA-GWO algorithm | Cloud computing workload datasets | Energy consumption, resource allocation efficiency | Effective resource allocation in cloud computing | Focused only on cloud environments |
Elaziz et al.18 | Quantum artificial hummingbird algorithm | Feature selection datasets in social IoT | Classification accuracy, feature selection quality | Improved feature selection for social IoT applications | Limited scalability and heterogeneity handling |
Dong et al.33 | Quantum particle swarm optimization | Mobile edge computing datasets | Task offloading efficiency, energy consumption | Efficient task offloading in mobile edge computing | Limited applicability to non-edge computing scenarios |
Alanis et al.34 | Quantum-assisted joint multi-objective routing and load balancing | Socially-aware network datasets | Routing efficiency, load balancing performance | Improved routing and load balancing in socially-aware networks | High computational complexity |
Ghorpade et al.35 | Enhanced quantum particle swarm optimization | Heterogeneous industrial IoT datasets | Network configuration efficiency, energy consumption | Optimal network configuration in heterogeneous IoT | Limited focus on non-industrial IoT applications |
Bey et al.36 | Quantum-inspired differential evolution | Edge network datasets | Service placement efficiency, resource utilization | Efficient IoT service placement in edge networks | Limited applicability to non-edge environments |
Proposed work | Hybrid MOGWOA-MOWOA enhanced with quantum principles | IoT application scenarios | Energy efficiency, delay cost, convergence speed, Pareto front diversity | Balances exploration and exploitation, enhances scalability, and optimizes QoS in heterogeneous IoT networks | Potential challenges in hardware requirements for quantum-inspired implementation |
