Load Forecast Calculator

Choose a model, set horizon, and tune parameters. See metrics, confidence bands, and residual checks. Download results, validate assumptions, and iterate with new data.

AI & Machine Learning
Advanced smoothing, seasonality, and regression options.

Calculator

Paste time series data, pick a model, and generate forecasts.

Regression uses extra numeric columns as features.
Number of future steps to generate.
Used for metrics on a held-out test slice.
For future timestamps when dates are present.
Example: 1 hour, 7 days, 1 month.
Bands are based on test RMSE.
Level smoothing (SES/Holt/HW).
Trend smoothing (Holt/HW).
Season smoothing (HW).
Examples: 24 (hourly daily), 7 (daily weekly).
Used by moving-average models.
Provide exactly W weights for WMA.
Matches your pasted format.
If present, first row is column names.
Applied to load and feature columns.
Clips extreme points before modeling.
Typical values: 1.5 to 3.0.
Adds a plot of actual, test, and forecast.
Format: timestamp,load[,feature...]. Dates can be YYYY-MM-DD HH:MM.
For regression with features. If omitted, last feature row repeats.

Example data table

Use this structure for your own datasets.

timestamp load temperature
2026-02-22 06:00116823.6
2026-02-22 07:00132524.8
2026-02-22 08:00146226.2
2026-02-22 09:00151027.0
2026-02-22 10:00148827.6
2026-02-22 11:00145128.0
Tip: Add more rows to capture cycles and holidays.

Formula used

Smoothing and trend
SES: ℓₜ = αyₜ + (1−α)ℓₜ₋₁, forecast ŷₜ₊ₕ = ℓₜ.
Holt: ℓₜ = αyₜ + (1−α)(ℓₜ₋₁+bₜ₋₁), bₜ = β(ℓₜ−ℓₜ₋₁)+(1−β)bₜ₋₁.
Forecast: ŷₜ₊ₕ = ℓₜ + hbₜ.
Seasonality and regression
Holt-Winters (additive): ŷₜ₊ₕ = (ℓₜ + hbₜ) + sₜ₋ₘ₊(h mod m).
Regression: y = β₀ + β₁t + Σβₖxₖ. Optional season dummies represent cycle positions.
Metrics: MAE, RMSE, and MAPE on a held-out test slice.
Confidence band: ŷ ± z·RMSE·√h. It is heuristic, not a guarantee.

How to use this calculator

  1. Paste your historical rows using the example column order.
  2. Pick a model that matches your data pattern and season.
  3. Set horizon, step unit, and season length if needed.
  4. Adjust smoothing parameters or switch to regression for features.
  5. Review the test metrics, then download CSV or PDF.

Operational load patterns

Electric load usually contains ramps, peaks, and recovery periods. In hourly datasets, daily seasonality is often 24, while weekly is 168. Many utilities see weekend demand drop 5–20% versus weekdays, and summer peaks can exceed winter peaks by 10–40% in hot regions. The calculator lets you test both season lengths and choose the better error profile.

Data inputs and feature design

Paste columns as timestamp, load, and optional drivers such as temperature, humidity, solar output, tariffs, or occupancy. As a rule of thumb, use at least 2,000 hourly rows, or 300 daily rows, to learn seasonal structure. Include one or two strong drivers before adding many weak features. Missing values can be forward filled or linearly interpolated; outliers can be clipped using an IQR factor (commonly 1.5 to 3.0) to reduce sensor spikes.

Model selection by data regime

Moving averages provide fast smoothing when demand is stable. Simple exponential smoothing fits level-only behavior and reacts through α. Holt adds trend using α and β, which helps when demand grows or declines across months. Holt‑Winters adds seasonality and works well for repeating cycles, such as daily HVAC patterns. Regression combines time, season dummies, and feature variables, and is effective when temperature explains peaks or when policy changes shift baselines.

Accuracy metrics and validation

To reduce overfitting, hold out the last portion of history as a test slice. The calculator reports MAE for typical absolute error, RMSE to emphasize large misses, and MAPE for percentage error. With low-load periods, MAPE can inflate, so compare MAE and RMSE too. Use the chart to check bias: consistent under-forecasting near peaks suggests missing drivers or a longer season.

Export-ready decision support

Results include cleaned history, test forecasts, future point forecasts, and a heuristic confidence band using RMSE with horizon scaling. Use CSV for dashboards, simulations, or capacity planning sheets. Use PDF for audits, procurement notes, and executive summaries. Re-run scenarios across horizons, seasons, and features to quantify risk, reserve margins, and demand-response headroom.

For planning, convert forecasts to energy by summing intervals, then add contingency factors. Track model drift weekly, and refresh parameters after major outages or significant tariff revisions.

FAQs

What data frequency works best?

Works with hourly, daily, or weekly series. Keep intervals consistent; if timestamps are irregular, aggregate first. For hourly, provide several weeks to capture weekday structure. For daily, include at least one seasonal cycle.

When should I choose Holt‑Winters?

Use it when demand shows clear repeating seasonality and a gradual trend. Set season length to the cycle size, such as 24 or 168. If seasonality is weak or unstable, SES or Holt may generalize better.

How are missing values handled?

Select drop, forward fill, or linear interpolation. Dropping removes incomplete rows; fill methods replace missing loads and features. Linear suits short gaps, while forward fill can be safer for step changes or meter resets.

What does the confidence band mean?

It is a heuristic interval: forecast ± z·RMSE·√h. It reflects recent error scale and widens with horizon. It is not a guarantee and may be optimistic if errors change during extreme weather.

Can I include weather and calendar features?

Yes. Add numeric columns after load for temperature, humidity, solar, price, or engineered calendar flags. For categories, convert them to 0/1 indicators before pasting so regression can use them correctly.

Why is MAPE high but MAE reasonable?

MAPE divides by actual load, so small loads inflate percentages in off-peak periods. If MAE and RMSE are stable, treat MAPE cautiously and inspect errors around peaks and operational thresholds.

Related Calculators

ARIMA Forecast CalculatorGRU Forecast CalculatorMoving Average ForecastSeasonality Detection ToolTime Series DecompositionAuto ARIMA SelectorForecast Accuracy CalculatorMAPE Error CalculatorRMSE Forecast ErrorMAE Error Calculator

Important Note: All the Calculators listed in this site are for educational purpose only and we do not guarentee the accuracy of results. Please do consult with other sources as well.