Open Access
Review
Table 4
Swarm-based vs. hybrid AI for power quality improvement.
| Parameter considered | Swarm-based AI methods | Hybrid AI methods |
|---|---|---|
| Convergence time | Slower due to extensive exploration | Faster due to improved exploitation |
| Computational cost | Higher due to more iterations and tuning efforts | Lower due to faster convergence and optimized learning |
| Scalability | Limited in large-scale MGs due to high computational burden | More scalable, adaptable to large MGs with complex dynamics |
| Voltage unbalance reduction | Less effective | More effective |
| THD reduction | Moderate | Significant improvement |
| Transient response | Slower | Faster |
| Complexity | Less complex, easy to implement | More complex due to hybridization, but with better performance |
| Accuracy of optimization | Moderate due to local optima issues | High, better exploration-exploitation balance |
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.