Optimising pump scheduling across a water transmission network
A hydraulic model and a mixed-integer optimiser schedule pumps against tariff periods and reservoir constraints, cutting energy cost while keeping storage within agreed limits.
- Location
- Saudi Arabia
- Duration
- 9 months
- -16%pumping energy cost
- -38%pump starts per day
- 0reservoir limit breaches in 9 months
The challenge
Twelve pump stations were operated on fixed timers and operator judgement. Energy was the largest controllable cost, and tariff periods were not being exploited consistently.
Reservoir levels, pump efficiency curves and demand all interacted, so any change in one station affected the others.
What we did
We calibrated a hydraulic network model against a month of flow and pressure records, then expressed the scheduling problem as a mixed-integer optimisation with tariff, storage, pressure and pump-switching constraints.
Robust variants were evaluated against demand uncertainty so that schedules remain feasible when consumption exceeds forecast.
The optimiser produces a 24-hour schedule each evening; the control room reviews and releases it to the SCADA system, with overrides and interlocks defined with the operators.
The outcome
Energy cost fell by a sixth with no change to service pressure, and the number of pump starts per day dropped, reducing wear.
A representative engagement. The figures are indicative of typical outcomes for this kind of work and are not drawn from a named client.
Contact
Tell us about the problem you need to solve
You may have a defined project, an underperforming process or a technical question that needs investigation. We can help assess the challenge, identify the information required and define an appropriate next step.