Forecasting
AuraScore 83/100

Day-Ahead Grid Load Forecast Validation Checklist

Prepare a comprehensive verification checklist to validate day-ahead electricity load forecasts before wholesale market submission.

Use this template when operational analytics teams need to cross-examine short-term load projections against telemetry, weather shocks, and historical baselines. It helps grid operators and forecasting leads prevent costly market imbalance penalties.

Template

Role: Senior Power Systems Forecasting Analyst with 15 years of experience in transmission balancing and short-term load modeling.

Context

  • Target Utility: {{utility_name}}
  • Operational Zone: {{grid_balancing_zone}}
  • Prediction Window: {{forecast_horizon_hours}} hours
  • Meteorological Feed: {{weather_model_source}}
  • Baseline History: {{historical_baseline_days}} days
  • Planned Outages & Maintenance: {{outage_schedule_summary}}

Task

Generate a structured, actionable pre-submission checklist for validating day-ahead electricity demand forecasts to ensure grid reliability and minimize settlement variance.

Method

  1. Review input telemetry integrity for all SCADA meters across {{grid_balancing_zone}} to identify missing or stuck data points.
  2. Correlate temperature and humidity forecasts from {{weather_model_source}} with historical non-linear cooling/heating degree days.
  3. Verify model adjustments against {{outage_schedule_summary}} to confirm planned load drops are accurately subtracted.
  4. Benchmark the candidate forecast against similar day profiles from the {{historical_baseline_days}} lookback period.
  5. Evaluate peak hour timing and ramp-rate gradients across the {{forecast_horizon_hours}} window against operational limits.
  6. Flag anomalies where confidence intervals breach historical variance thresholds.
  7. Document approval gates required by {{utility_name}} before passing forecasts to market bidding systems.

Constraints

  • MUST format every checklist item as a binary checkable task with a clear pass/fail criterion.
  • MUST include explicit tolerance limits (percentage or MW) for every variance check.
  • MUST NOT recommend changes to model hyperparameters or source code.
  • Content MUST focus strictly on operational verification for the defined {{forecast_horizon_hours}} horizon.
  • Items MUST be grouped logically by analytical phase.

Output format

Return a markdown checklist organized into three distinct sections: 1. Input Data & Weather Verification, 2. Model Output & Variance Checks, and 3. Sign-off & Dispatch Submission. Each section must contain exactly 3 to 5 markdown task boxes (- [ ]) followed by a one-sentence failure mitigation action.

Self-review

  • Confirm all 6 variables are referenced naturally within the checklist context.
  • Verify every check item has an actionable, objective criteria rather than subjective guidance.
  • Ensure total item count does not exceed 15 checklist items.
AuraScore breakdown
83/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering12/12 · Strong

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency7/10 · Adequate

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

data-analytics
data-forecasting
energy-utilities
load-forecasting
grid-operations
energy-analytics