Build an Industrial Chiller Thermal Storage Pre-Cooling Optimizer — implementation

## Build
Build an application to monitor Sparkplug B chiller telemetry and determine optimal thermal storage pre-cooling windows. Avoid peak utility tariffs by calculating required refrigeration ramp-up times using thermal inertia constraints and outputting setpoint adjustment schedules.

## User
Industrial Energy Systems Architect

## Workflow
1. Parse Sparkplug B telemetry payloads to extract chilled water loop temperatures and active factory cooling load demands.
2. Calculate the thermal mass energy required to reach the target setpoint using the configured energy-per-degree coefficient.
3. Model the required pre-cooling duration using Semantic Kernel to orchestrate the calculation against available chiller capacity.
4. Generate a precise schedule of automated setpoint adjustment start times designed to complete pre-cooling before peak tariff hours.

## Interface
JSON API endpoint returning calculated pre-cooling start times and duration metrics.

## Data
Generate synthetic JSON records modeling Sparkplug B metric streams for chilled water supply temperatures and operational capacities.
Starter examples below are synthetic. They are not downloaded records.

## Source
[Eclipse Sparkplug](https://raw.githubusercontent.com/eclipse-sparkplug/sparkplug/master/README.md)
Leverages Sparkplug B metric properties and complex data types from Source 2 to parse industrial thermal states.

## Tools
semantic-kernel, pydantic, fastapi.
Semantic Kernel orchestrates the integration of AI-driven scheduling heuristics with deterministic thermal storage calculation tools.
Local or hosted LLM capable of function calling and strict JSON output generation.

## Deliverables
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.

## Acceptance
- Accurately calculates required pre-cooling duration using the formula: (delta_temp_c * energy_per_c_kwh) / available_cooling_kw.
- Properly deducts the calculated pre-cooling duration from the peak tariff start hour to determine the optimal start command time.
- Exports a structured JSON schedule containing the required cooling hours and the setpoint start time for the HVAC control system.

## Starter Examples
```json
[
  {
    "input": {
      "delta_temp_c": 4,
      "energy_per_c_kwh": 50,
      "available_cooling_kw": 100,
      "peak_tariff_start_hour": 15
    },
    "expected_output": {
      "required_precool_hours": 2,
      "start_command_hour": 13,
      "record_type": "simplified synthetic app record"
    }
  },
  {
    "input": {
      "delta_temp_c": 3,
      "energy_per_c_kwh": 50,
      "available_cooling_kw": 100,
      "peak_tariff_start_hour": 14
    },
    "expected_output": {
      "required_precool_hours": 1.5,
      "start_command_hour": 12.5,
      "record_type": "simplified synthetic app record"
    }
  }
]
```

## Safety
Read-only planning tool; all generated pre-cooling setpoints require manual review by plant facility engineers before being applied to live equipment.
Use mock external writes. Require human review before any real deployment.