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. |
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.