Period Total: Forecast Monthly Energy & Usage

Period Total answers the question a budget asks: how much by the end of the period? The model forecasts the metric for the rest of the period, adds what has been measured so far, and reports the total, peak, average, or minimum for the whole period next to the same figure for the previous period.

Use Period Total when you need one number for a whole period, such as a month, rather than the curve.

Use case	What Period Total predicts	What you do with it
Check the energy bill	Total energy of each site for this month	See the bill before the invoice arrives, and compare it with last month
Estimate fuel spend	Total fuel each vehicle of a fleet will use this month	See which vehicles will go over the monthly fuel budget
Report water use	Total water use of each building for this quarter	Report the change against the previous quarter before the quarter ends

Period Total raises no alarms. To be warned when a metric crosses a limit, use Time to Threshold. To track a goal with a risk score and alarms, use Hit Target. For the plain curve over a horizon, use Forecast.

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

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

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 total 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 chosen here is the default of the Result tab, where all four are available without rebuilding.

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 the period the model totals, how much history it learns from, and how fine the result is.

Prediction period — choose the calendar period to total. Pick Day, Week, Month, or Quarter, or Custom and type the number of units. The info block splits the period into the part already measured and the part still to be forecast:

Training period — choose how much history the model learns from. A one-month period wants at least three months of history, so a ratio below three is graded as weak:

Prediction granularity — pick the length of one bucket. The forecast that fills the rest of the period has the same step:

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 period 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 card on the left shows the period of the selected item:

Part	What it shows
Sum, Maximum, Average, Minimum	Tabs that switch the aggregation. All four come from the same forecast
Predicted total	The value for the whole period, measured part plus forecast
Actual	The measured part, from the start of the period to the latest reading
Predicted	The forecast part, from the latest reading to the end of the period
vs Previous	The same value for the previous period, and the change in percent

A rise shows as good news in green. For a metric where less is better, such as energy, turn on Reverse comparison colors on the Properties tab.

The chart shows the selected item over the whole period: Actual, Forecast, and Previous period, with a Now marker at the latest reading.

Two buttons above the chart switch what it draws. They open as set in Result page settings; click one to switch it.

Button	On	Off
Cumulative	Each point adds up everything from the start of the period, so the line climbs toward the period total	Each point shows only its own hour or day, for example the energy used from 14:00 to 15:00
Compare	The previous period is drawn over the current one	Only the current period

The table under the chart lists every item in the model’s scope. Select a row to switch the card and the chart to that item.

Column	Meaning
Item	The device or asset name
Predicted total	The value for the whole period, measured part plus forecast
Actual	The measured part, from the start of the period to the latest reading
Predicted	The forecast part, from the latest reading to the end of the period
Previous	The same value for the previous period
Δ %	The change against the previous period
Last refresh, Refresh status, Training	The item’s refresh and training state

Each column header shows the dates it covers. The names follow the selected tab, so with Maximum selected the first value column reads Predicted peak.

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. Without a periodic refresh, the measured part of the period stops growing at the last refresh.

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

The Result page card on the Properties tab sets how the Result tab opens for everyone. The Cumulative and Compare buttons on the chart change the view only for your session.

Setting	Effect
Units	Printed after the values on the card and in the table
Default aggregation	The tab the card opens on: Sum, Maximum, Average, or Minimum
Enable comparison	Master switch for the previous period. Off hides vs Previous, the Compare button, and the Δ % column
Cumulative by default	Whether the chart opens on the running aggregate
Compare by default	Whether the previous period is overlaid when the tab opens
Reverse comparison colors	Colors a fall as good news, for metrics where less is better, such as energy

None of them rebuilds the model. Click Apply changes and the Result tab follows.

• Forecast

  Predict the next values of a metric, like the energy of the next 7 days.

• Time to Threshold

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

• 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.