Forecast: Predict Future Telemetry Values

Forecast predicts the future values of one metric for every device or asset in a profile. Trendz learns each item’s own history and extends it over a prediction horizon: the next 24 hours, 7 days, 30 days, or a range of your own. Ten energy meters give ten forecasts, each refreshed as new readings arrive.

Use Forecast when you need the predicted values themselves, for each device or asset.

Use case	What Forecast predicts	What you do with it
Buy electricity	Hourly consumption of each store for tomorrow	Order the right amount of power a day ahead
Plan production load	Hourly power use of each production line for next week	Spread heavy jobs so the plant stays under its contracted capacity
Plan parking capacity	Hourly occupancy of each parking lot for next week	Open overflow lots and set prices before the busy days

Forecast raises no alarms and has no countdown of its own. To learn when a value crosses a limit, use Time to Threshold. For a total, peak, or average over a period, use Period Total. To track a goal, use Hit Target.

Two entry points are available on the Prediction models page:

• Create model — button in the top-right corner, visible on both tabs.
• + Create — inline button on any profile row of the Profile coverage table. Opens the wizard with that profile pre-selected.

The wizard opens on What do you want to predict?:

• Select the Forecast card (1).
• Click Next (2).
• The intent decides what the model reports and cannot be changed later.
• The other three intents are described in Time to Threshold, Period Total, and Hit Target.

The Inputs configuration step defines the items the model trains on and the metric it predicts.

Entity selection — select the entity type and the profile to predict:

Item selection — choose which items of the profile train the model:

Mode	Behavior
All items	Includes every item in the profile, including devices added to it later.
Manual selection	Pick specific items from a searchable list.

Predicted metric — pick the telemetry key to forecast and the aggregation applied to it during training:

Aggregation	Use for
SUM	Counters such as energy, water, or produced units.
AVG	Levels such as temperature, pressure, or humidity.
MAX, MIN	Peaks and troughs, for example the highest demand of an hour.

The aggregation turns every reading inside one bucket into a single value, so it decides what the forecast actually means.

Additional metrics — optional extra telemetry that may explain the predicted one, each with its own aggregation. Type to search the keys of the profile:

Data Readiness — grades the choice as you go: items selected, the predicted metric, how many telemetry points they hold, and the average spacing between them.

The Configure forecast step sets how far ahead the model predicts, how much history it learns from, and how fine the result is.

Prediction horizon — choose how far ahead the model predicts. Pick one of the presets, or Custom and type the number of units to predict:

Training period — choose how much history the model learns from. A model needs several horizons of history to find a pattern, and the readiness panel grades a ratio below three as weak:

Prediction granularity — pick the length of one bucket. The forecast has the same step, so an hourly model predicts one value per hour:

Data Readiness — check the status before you train. The better it is, the better the resulting forecast:

Advanced settings — optional. Opens the prediction method and the forecast bounds. Leaving the method on Auto lets Trendz pick one per item:

Every setting of this step is described in Wizard advanced settings.

Build model — trains one model per item and opens the Result tab when the run finishes:

The Result tab shows the forecast of one item at a time. Pick the item in the table below the chart; the cards on the right show the monitoring settings and the data status of the model.

The chart draws the selected item: measured history as a solid line and the forecast as a dashed line.

The table under the chart lists every item in the model’s scope. Select a row to point the chart at that item.

Column	Meaning
Item	The device or asset name
Latest telemetry	The item’s last measured value and its time
Latest prediction point	The last forecast value and how far ahead it lies
Last refresh	When a refresh last selected this item
Refresh status	Never, In progress, Success, or Failed
Training	Training, Trained, Failed, Insufficient data, or Cancelled

Insufficient data is a state, not a failure: the item has less history than the horizon and is trained on the next run that finds enough.

The ⋯ button at the end of each item row — Refresh, Retrain, and Delete for one item — works the same for every intent. See Interface Overview.

The Continuous monitoring card shows the monitoring status of this model. What each setting does and how to configure it is described in Monitoring & Alarms.

The Data status card and its Refresh item, Refresh all, and Retrain all failed buttons work the same for every intent. See Interface Overview.

• Time to Threshold

  Predict when a metric crosses a limit, and raise an alarm before it happens.

• Period Total

  Predict the total, peak, or average of a period, such as the energy of this month.

• Hit Target

  Predict whether a goal is reached by the end of a period, and how far off it is.

• Explore Interface

  Find your way around the models list, the model page, and its tabs.

• Monitoring & alarms

  Refresh and retrain on a schedule, save forecasts to ThingsBoard, and raise alarms.

• Show on dashboards

  Chart history and forecast together in Trendz views and ThingsBoard dashboards.

• Models & accuracy

  How a model learns, its settings, and how accurate its forecasts are.