Table 9 Hypothetical numerical comparison table.
Metric | Bipolar fuzzy graph-based ML optimization (BFG-MLO) | Traditional engineering models (TEM) | Data-driven optimization models (DDOM) |
|---|---|---|---|
Optimization efficiency (%) | 85% | 60% | 75% |
Cost-effectiveness | High (Long-term savings in maintenance, energy) | Moderate (High initial costs) | Moderate (Requires large datasets) |
Accuracy | 0.12 | 0.20 | 0.15 |
Adaptability | High (Can adapt over time based on feedback) | Low (Static models) | Moderate (Relies on predefined datasets) |
Sustainability impact (Reduction in runoff %) | 30% | 15% | 25% |
Maintenance costs (Annual) | $5000 (due to optimized design and materials) | $8000 (more frequent repairs needed) | $6000 |
Scalability | High (Can be applied to larger cities with adjustments) | Low (Requires significant redesign for different cities) | Moderate (Applicable to similar contexts) |
Energy consumption (kWh/year) | 50 kWh | 80 kWh | 70 kWh |
