Table 1 Comparative analysis of various load-balancing methods based on various parameters.

Whale Optimization Algorithm

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n²) (quadratic due to iterative population evaluation)

¹

Water Wave Optimization

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n²) (similar to WOA, with moderate iterative steps)

²

Genetic Algorithm

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n × m) (population size × number of generations)

³

Particle Swarm Optimization

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n × m) (population size × number of iterations)

⁴

Ant Colony Optimization

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n × m) (number of ants × number of iterations)

⁵

Adaptive Genetic Whale Optimization

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n × m) (Genetic operations plus whale optimization)

⁸

Inverted Ant Colony Optimization

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n × m) (number of ants × number of iterations, less complex)

⁹

Fuzzy-Based PSO

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n × m) (iterative updates of particle positions)

¹⁰

Ripple-Induced Whale Optimization

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n²) (due to ripple effects and evaluation complexity)

⁶

Grasshopper Optimization Algorithm

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n × m) (population × number of iterations)

¹²

Meta-Heuristic Approaches for Microgrid

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n × m) (depending on the nature of metaheuristics)

¹⁴

Load balancing via intelligent PSO

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n × m) (particle updates per iteration)

²⁰

Dynamic Load Balancing via Optimized RL-Based Clustering

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n²) (RL-based updates + clustering evaluation)

¹⁵

Modified min-min heuristic

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n × m) (iterative heuristic-based evaluation)

¹⁶

Optimal load balancing via hybrid optimization

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n³) (complexity due to hybrid optimization processes)

¹⁷

Dynamic optimization via utilizing the Krill Herd meta-heuristic algorithm

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n × m) (meta-heuristic iteration-based, high overhead)

¹⁸

Tactical Unit Algorithm

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n²) (time complexity increases with more tactical units)

²¹

Optimising workload distribution via a JAYA-based meta-heuristic

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n × m) (iterative updates, with moderate computational cost)

¹⁹

Hybrid WWO-ACO

Yes

Yes

Yes

Yes

Yes

Yes

Yes

Yes

O(n²) (a hybrid of WWO and ACO, the computational cost is moderate)

Proposed