Understanding Forecast Parameters in Detail

Key Parameters for the Forecast App

In Eliona's Forecast App, three parameters determine the quality and meaningfulness of your time series predictions. Below you will find a compact description of the most important settings for each:

---

1. Forecast Length

Definition: The number of time steps the model should predict into the future.

• Calculation of the time distance: The app automatically determines the average time interval of your most recently saved data points in Eliona.

• Examples:

  • With 5-minute intervals and [forecast_length] = 3, the forecast corresponds to a horizon of 15 minutes.

  • With daily measured values and [forecast_length] = 5, five days are predicted.

Pay attention to regular data intervals. With irregular storage, the timeline cannot be derived correctly. It is recommended to activate the "always" trending option in the attribute.

---

2. Context Length

Definition: The number of past data points that the model uses as historical context.

• Short-term patterns: Small values (e.g., 24) are suitable for daily cycles or hourly trends.

• Long-term effects: Larger values (e.g., 168 or more) are useful when seasonal or weekly patterns are to be recognized.

• LSTM advantage: Thanks to the Long Short-Term Memory architecture, the model remembers relevant information even beyond the selected window, which usually means a moderate window size is sufficient.

Longer context windows dramatically increase the computing effort and memory requirements.

---

3. Feature Attributes

Definition: Feature Attributes are additional input variables that the model uses to calculate the forecast. They expand the context and thus improve the accuracy of the prediction.

Automatic Time Features:

If no other feature is selected, the Forecast App automatically adds the following time-based attributes:

• minute_of_hour

• hour_of_day

• day_of_week

• month_of_year

These fields automatically appear in the form when a forecast item is created and provide the model with cyclical information about the current time structure.

The actual model processing is done internally via the transformed variants of these values (_sin/_cos), e.g.:

• hour_of_day_sin / hour_of_day_cos

• day_of_week_sin / day_of_week_cos

• month_of_year_sin / month_of_year_cos

This transformation ensures that cyclical time patterns (e.g., the transition from hour 23 to 0) are correctly mapped mathematically.

Optional: Asset-related Features

You can add other attributes of the same asset, e.g.:

• Temperature

• Humidity

• Energy consumption

These help the model recognize relationships between different measured variables.

Best Practices:

• Do not use meter readings directly. Instead, insert differentiated or relative values.

• Create your own features: Use the Eliona Calculator to generate combined or derived values (e.g., area calculation, growth rates).

• Secure data quality: Use filters to remove outliers or smooth noisy signals.