Table 8 Comparative analysis with State-of-the-art methods.
References | Method | Objective (s) | Key techniques | Optimisation goal | Performance metrics | Challenges addressed | Results |
|---|---|---|---|---|---|---|---|
Ghafir et al.1 | PSO-based Feedback Controller | Load balancing in the cloud | PSO feedback controller | Load distribution optimisation | Load balancing efficiency: 20%, Energy efficiency: 10% | Dynamic load balancing | Improved load balancing in dynamic environments |
Dhabliya et al.2 | Dynamic Load Balancing Policies | Dynamic load balancing in the cloud | Policy-driven strategies | Efficient load balancing | Load balancing improvement: 12%, Response time: 8% | Real-time load balancing | Enhanced load balancing in dynamic environments |
Khan3 | RL-based Clustering for Load Balancing | Dynamic load balancing | RL-based clustering | Optimised task scheduling | Energy reduction: 14%, Load balancing: 10% | Scaling for large systems | Effective dynamic load balancing in cloud systems |
Dubey and Mishra4 | Performance & Trust Analysis for Load Balancing | Load balancing in cloud | Trust and performance evaluation | Trust-based load balancing | Trust evaluation: 16%, Performance improvement: 12% | Trust and security | Improved trust-based load balancing in clouds |
Choudhary and Rajak5 | Min-Min Heuristic for Workflow Scheduling | Workflow scheduling | Min-min heuristic | Task completion time and load balancing | Makespan reduction: 15%, Task completion: 10% | Scalability issues | Efficient for small cloud workflows |
Geetha et al.8 | Hybrid Optimization for Load Balancing | Optimal load balancing | Hybrid optimisation algorithms | Energy and resource optimisation | Energy efficiency: 18%, Load balancing: 14% | Scalability for large systems | Improved load balancing, limited scalability |
Forghani et al.9 | Krill Herd Algorithm for Load Balancing | Load balancing in SDNs | Krill herd metaheuristic | Energy and load balancing | Energy reduction: 20%, Load efficiency: 16% | Network load balancing | Effective in SDNs, limited for the general cloud |
Singh et al.6 | JAYA-based Metaheuristic for Fog-Cloud Ecosystem | Workload distribution in fog-cloud systems | JAYA algorithm for task scheduling | Energy-efficient workload distribution | Energy reduction: 12%, Task completion: 10% | Workload distribution | Effective for fog-cloud systems |
Tiwari et al.7 | Knapsack-based Metaheuristic for Edge Placement | Edge server placement optimisation | Knapsack-based optimisation | Edge server placement | Placement efficiency: 14%, Load balancing: 10% | Edge network optimisation | Effective for edge systems, not scalable to the cloud |
Rostami et al.13 | Capuchin Search & IACO for Task Scheduling | Energy-efficient task scheduling | Capuchin search & IACO | Energy and task scheduling | Energy reduction: 18%, Task completion: 12% | Energy efficiency challenges | Improved task scheduling with energy efficiency |
Kumar and Karri36 | AGWO Hybrid for Task Scheduling | Cost-aware task scheduling | Hybrid Ant Lion & WOA | Cost and task scheduling optimisation | Cost reduction: 14%, Task allocation: 9% | Resource utilisation | Efficient scheduling in cloud-fog systems |
Proposed model | Hybrid WWO-ACO | Task scheduling and resource allocation | ACO + WWO | Task completion, load balancing, energy consumption | Makespan reduction: 18%, Energy reduction: 15%, Load balancing: 20% | Scalability and adaptability | Outperforms others in multi-objective optimisation |
