LIVEdataset aec-bench@releasetasks 552models 18last submission … · built …
electricalwith-tool

Pfc Sizing

Calculates the reactive power compensation needed to improve a load from an initial lagging power factor to a target power factor. The reduced method uses Qc = P x (tan phi_initial - tan phi_target), then reports the corrected apparent power and current reduction.

with-tool: The model is given an executable Python calculator script.

Standards

AS/NZS 2067IEEE 3002.2

Tags

capacitordeterministicelectricalload-flowpower-factorreactive-power

How this task is generated

One template produces many comparable benchmark tasks while keeping the scoring contract fixed.

  1. 01

    Template

    The reusable contract shown on this page.

  2. 02

    Scenario

    An archetype and site context are sampled.

  3. 03

    Difficulty tier

    Inputs may be hidden at harder tiers.

  4. 04

    Task prompt

    The model responds with the declared outputs.

Parameters

Inputs the model receives, and the outputs it is scored on.

Inputs

3 inputs

Always given

Included directly in every task prompt.

2

  • Real power

    real_power_kw

    Real load power

    1 – 20000 kW

  • Target power factor

    target_power_factor

    Target corrected power factor

    0.9 – 0.99

Hidden at higher difficulty

Visible in easier tasks and withheld in one or more harder tiers.

1

  • Initial power factor

    initial_power_factor

    Initial lagging power factor

    Hidden at hard difficulty.

    0.5 – 0.94

Scored outputs

4 outputs

Initial apparent power kva

initial_apparent_power_kva

Initial apparent power

Scores if within ±3% of the reference value.

Corrected apparent power kva

corrected_apparent_power_kva

Apparent power after correction

Scores if within ±3% of the reference value.

Required reactive power kvar

required_reactive_power_kvar

Required capacitor reactive power

Scores if within ±3% of the reference value.

Current reduction pct

current_reduction_pct

Reduction in line current at unchanged voltage

Scores if within ±3% of the reference value.

Difficulty

Each template is sampled at three tiers. Harder tiers may hide inputs, forcing the model to infer them from the scenario description.

easy

All inputs given

Small load with all power factors given

medium

All inputs given

Commercial or industrial correction calculation

hard

Some inputs hidden

Larger load with initial power factor hidden in context

Hidden inputs

  • Initial power factorinitial_power_factor

Prompt replacement text

The existing load has the lagging power factor typical of {{ archetype.description }}.

Task bundle

The exact instruction and parameter contract used to generate this task, pinned to the published library source.

/workspace

  • instruction.md
  • pfc-sizing_calc.py

Teal lines show Jinja input conditions, not task visibility policy. A line renders only when that input or tool is visible.

1You are a senior electrical engineer sizing power factor correction for a load.2 3## Problem4 5Calculate the capacitor kVAr required to improve the load power factor from the initial value to the target value.6 7## Given8 9| Parameter | Value | Unit |10|-----------|-------|------|11| Real power | {{ real_power_kw }} | kW |12{% if initial_power_factor is defined %}13| Initial power factor | {{ initial_power_factor }} | - |14{% endif %}15| Target power factor | {{ target_power_factor }} | - |16{% if archetype_description is defined %}17 18### Site Context19 20{{ archetype_description }}21{% endif %}22 23{% if tool_available %}24## Available Tool25 26A power factor correction sizing tool is available at `/workspace/pfc-sizing_calc.py`. Run it with:27 28```bash29python3 /workspace/pfc-sizing_calc.py --help30```31{% endif %}32 33## Required34 35Calculate:36 371. Initial apparent power in kVA382. Corrected apparent power in kVA393. Required capacitor reactive power in kVAr404. Current reduction percentage at unchanged voltage41 42## Constraints43 44- Use `phi = acos(power_factor)`.45- Use `Qc = P x (tan(phi_initial) - tan(phi_target))`.46- Use `S = P / power_factor`.47- Use apparent-power reduction as the current reduction percentage.48 49## Output Format50 51Show your working in Markdown. At the end, include a JSON block with exactly these keys:52 53```json54{55 "initial_apparent_power_kva": <numeric_value>,56 "corrected_apparent_power_kva": <numeric_value>,57 "required_reactive_power_kvar": <numeric_value>,58 "current_reduction_pct": <numeric_value>59}60```61 62Write your complete solution to `/workspace/output.md`.63

Scenario archetypes

Each generated task is drawn from one of these realistic scenario bands.

Site contexts ground each scenario in a real locale the model can use to infer hidden values.

Small commercial load

small_commercial_load

Small commercial motor and HVAC load

commercial-switchboardretail-centre
Parameter ranges
real_power_kw
20 – 250
initial_power_factor
0.7 – 0.88
target_power_factor
0.92 – 0.97

Industrial motor load

industrial_motor_load

Industrial motor control centre load

water-treatment-plantmanufacturing-site
Parameter ranges
real_power_kw
250 – 3000
initial_power_factor
0.65 – 0.88
target_power_factor
0.93 – 0.99

Utility customer load

utility_customer_load

Large utility customer connection

mining-loadlarge-campus
Parameter ranges
real_power_kw
3000 – 20000
initial_power_factor
0.75 – 0.94
target_power_factor
0.95 – 0.99

Example task

water-treatment-plant-industrial-motor-load-preview — hard difficulty, some inputs hidden.

Industrial motor control centre load. water-treatment-plant. Required outputs: initial_apparent_power_kva, corrected_apparent_power_kva, required_reactive_power_kvar, current_reduction_pct

The model sees

Scenario context and visible inputs.

real_power_kw
250 to 3000 kW
target_power_factor
0.93 to 0.99

Executable tool: pfc-sizing_calc.py

The model must infer

Inputs withheld at this difficulty.

  • Initial power factor

    initial_power_factor

Stand-in text in the prompt

The existing load has the lagging power factor typical of {{ archetype.description }}.

The model must produce

The scored JSON answer schema.

{
  "initial_apparent_power_kva": <number>,
  "corrected_apparent_power_kva": <number>,
  "required_reactive_power_kvar": <number>,
  "current_reduction_pct": <number>
}
  • initial_apparent_power_kva · scored within ±3%
  • corrected_apparent_power_kva · scored within ±3%
  • required_reactive_power_kvar · scored within ±3%
  • current_reduction_pct · scored within ±3%