Open Access
Table 9
Comparison of the performance of the ANFIS controller with other controllers.
| Metrics | ANFIS | PID | Fuzzy logic | ANN |
|---|---|---|---|---|
| Energy cost (per kWh) | Lowest due to dynamic optimization of energy sources. | Moderate; relies on fixed gain values. | Lower but limited by pre-set fuzzy rules. | Low, but computationally expensive to train. |
| Renewable energy utilization | ~95% utilization through adaptive allocation. | ~70-80% due to lack of adaptability. | ~85% with well-defined fuzzy rules. | ~90% dependent on accurate data training. |
| Battery health (degradation) | Minimal due to efficient charge/discharge cycles. | Higher due to fixed response parameters. | Moderate; lacks adaptive learning for cycles. | Low, if training includes battery dynamics. |
| Response time | 0.2–0.5 s for real-time changes. | 0.1–0.3 s, faster but less adaptive. | 0.3–0.6 s, dependent on complexity. | 0.4–0.7 s, training-dependent. |
| System adaptability | High; self-tunes to dynamic conditions. | Low; requires manual tuning. | Moderate; relies on fuzzy rule refinement. | High; depends on quality of training data. |
| Scalability | Easily scalable to larger, complex systems. | Limited by complexity and tuning. | Moderate; requires more fuzzy rules. | High but resource-intensive. |
| Implementation cost | Moderate; requires expert design and training. | Low; simple implementation. | Moderate; depends on fuzzy rule complexity. | High; significant computational resources. |
| Real-time decision-making | Excellent due to hybrid fuzzy-neural learning capabilities. | Limited real-time performance in complex systems. | Performs well but slower in complex scenarios. | Real-time decision-making is challenging without pre-training. |
| Real-world applications | Used in hybrid microgrids for EV charging, smart grids, and renewable energy optimization. | Commonly used in industrial control systems but less in energy optimization. | Applied in smart home energy systems and microgrids with less complexity. | Found in predictive maintenance and energy forecasting systems. |
Les statistiques affichées correspondent au cumul d'une part des vues des résumés de l'article et d'autre part des vues et téléchargements de l'article plein-texte (PDF, Full-HTML, ePub... selon les formats disponibles) sur la platefome Vision4Press.
Les statistiques sont disponibles avec un délai de 48 à 96 heures et sont mises à jour quotidiennement en semaine.
Le chargement des statistiques peut être long.