Watch how MPC shifts pumping to off-peak tariff windows, pre-fills the elevated tank overnight, and avoids peak-hour electricity costs — saving 25–40% on pump energy.
Cyan = off-peak (pump hard), amber = mid tariff (partial), red = peak (coast on tank). Bar height = pump speed %. Click any bar to jump to that hour.
TOD tariffs penalise peak-hour consumption. The same kWh of pumping work costs 60% less at night than at peak.
| Component | Rate | AI strategy |
|---|---|---|
| Energy charge | ₹3.2/kWh | Pump at full speed — cheapest window. Fill tank to 88%+. |
| TOD multiplier | 0.80× (20% discount) | Off-peak discount fully exploited |
| Demand charge | ₹400/kVA/month | VFD keeps power factor >0.95 |
| kVAh billing | Unity PF target | Capacitor banks auto-switched |
AI scheduling vs. fixed-speed reactive operation on the same network.
The MPC needs to know how much water each zone will need over the next 24 hours. ML learns these patterns continuously.
| ML input | Why it matters | Update frequency |
|---|---|---|
| Historical zone demand by hour/day | Baseline demand curve per DMA | Continuous — 90-day weighted |
| Day of week / holiday calendar | Industrial Zone C drops 60% on Sundays | Daily via calendar API |
| Max temperature forecast | +1°C → +0.8% residential demand | 6-hourly NWP forecast |
| Pressure sensor readings | Leak detection via model anomaly | Every 5 minutes |
| Pipe roughness C (calibrated) | Keeps friction model accurate | Weekly ML re-fit |