Build a District Cooling Thermal Energy Storage Night-Chilling Optimizer

Model district cooling plant chiller load shifting and stratified thermal storage tank charging during off-peak night hours. Reduce peak-demand electrical charges while guaranteeing daytime cooling tonnage.

District Cooling Operations Lead

Ingest commercial customer cooling load forecasts and thermal energy storage (TES) state-of-charge.

Retrieve time-differentiated electricity tariffs and chiller coefficient-of-performance curves.

Formulate optimal nocturnal TES charging sequences using building energy balance principles from EnergyPlus.

Produce verified chiller staging plans and thermal reserve reports for operational shift sign-off.

A real-time plant load balancing dashboard showing TES thermocline levels, chiller staging Gantt charts, and demand tariff cost deltas.

Synthesize 24-hour district cooling demand profiles (ton-hours), TES tank capacity limits, and utility tariff rate tables in JSON. Starter examples below are synthetic. They are not downloaded records.

EnergyPlus Employs EnergyPlus chilled water loop and thermal storage tank energy balance conventions to model charging and discharging dynamics.

dspy, pydantic, fastapi. Compiles and optimizes structured prompt-based reasoning for complex thermodynamic scheduling decisions under tariff constraints. Local or hosted LLM with strong math reasoning capabilities for validating thermal balance calculations.

Submit runnable source, pinned dependencies, setup commands, a working interface, example outputs, and a recorded end-to-end demo. Include tests and an action log.

Maintains TES state-of-charge within safe operating bounds without overcharging.

Demonstrates load shifting away from designated peak electrical tariff hours.

Outputs hourly chiller stage assignments and expected peak demand cost reductions.

Enforces mandatory engineering review check prior to transmitting setpoints to plant operators.

```json [ { "input": { "plant_id": "DCP-MARINA", "tes_capacity_ton_hours": 20000, "initial_tes_storage_ton_hours": 4000, "max_charge_rate_tons": 2500, "forecast_peak_cooling_demand_tons": 8000, "chiller_base_capacity_tons": 6000, "off_peak_hours": [ 0, 1, 2, 3, 4, 5 ] }, "expected_output": { "recommended_night_charge_ton_hours": 15000, "projected_peak_coverage_deficit_tons": 0, "chiller_night_utilization_ratio": 0.83, "peak_shaving_feasible": true, "status": "APPROVED_FOR_REVIEW" } }, { "input": { "plant_id": "DCP-MARINA", "tes_capacity_ton_hours": 10000, "initial_tes_storage_ton_hours": 1000, "max_charge_rate_tons": 1000, "forecast_peak_cooling_demand_tons": 9000, "chiller_base_capacity_tons": 6000, "off_peak_hours": [ 2, 3, 4 ] }, "expected_output": { "recommended_night_charge_ton_hours": 3000, "projected_peak_coverage_deficit_tons": 2000, "chiller_night_utilization_ratio": 1, "peak_shaving_feasible": false, "status": "SUPPLEMENTAL_CHILLER_REQUIRED" } } ] ```

Generates advisory scheduling proposals; thermal setpoints require confirmation by qualified plant shift engineers. Use mock external writes. Require human review before any real deployment.