Purpose of this article
This article explains how Scaler estimates missing energy meter data using a transparent, weighted methodology, and how estimated values are used in analytics, exports, and reporting.
What is estimation in Scaler?
Estimation fills missing or incomplete portions of energy meter data to create a continuous and consistent dataset.
Estimation is applied when:
- A meter reading covers only part of a month
- One or more months of consumption data are missing
- Data is delayed or partially reported
Estimated values are modeled, not measured, and are clearly identified in analytics and exports.
Important: Estimation is different from normalization. Estimation fills data gaps; normalization adjusts data for comparability.
Where estimation is used
Analytics Portal
Location: Analytics Portal → Portfolio → Analytics → Energy
How to view estimates:
- Select View → Estimated (Scaler algorithm)
- Estimated values appear alongside actual data
- Asset-level charts show estimated portions as stacked bars
Data Collection Portal exports
Location: Data Collection Portal → Portfolio → Meter List → Download
Export column: estimated_linear_extrapolation_consumption
Purpose: Complements actual_monthly_consumption to provide a complete time series
Estimated values are included to support:
- Continuous analytics
- Benchmarking and scoring
- External reporting workflows that expect uninterrupted time series
How the estimation model works
Scaler uses a linear, history-weighted estimation model based on each meter's actual past consumption.
The model follows these steps:
- Detects missing periods: Identifies incomplete months at the meter level, even if only a few days are missing.
- References recent history: Looks back up to 6 months of valid historical consumption for the same meter.
- Normalizes to daily averages: Converts historical monthly values into average daily consumption.
- Applies weighted logic: More recent months are weighted more heavily using a decay function.
- Estimates the gap: Missing days or months are filled using the weighted daily average.
- Assigns a confidence score: Each estimate is scored based on data availability and proximity to actual readings.
Confidence scoring
Each estimated value includes a confidence score to help assess reliability.
The confidence score considers:
- Amount of historical data available: More recent, complete history results in higher confidence.
- Distance from known data: Estimates closer to actual readings have higher confidence than those further away.
Note: Confidence scores are guidance indicators, not guarantees of accuracy.
Key benefits of Scaler’s estimation approach
- Avoids flat or arbitrary assumptions
- Uses real, meter-specific historical data
- Supports like-for-like scoring and benchmarking
- Improves portfolio comparability
- Aligns with expectations of external reporting frameworks
Limitations to consider
- Does not adjust for seasonality
- Assumes recent consumption patterns remain relevant
- Uses a fixed 6-month lookback window
- Estimated values should not replace measured data when actual readings are available
- Occupancy rates (
Average vacancy rate) are not directly factored into estimation calculations. However, occupancy is implicitly reflected in the consumption data itself. Since Scaler estimates missing months using the past six months of actual consumption (with greater weight on recent months), any occupancy-related usage patterns are already captured in the historical data that drives the estimates.
How estimation differs from normalization
Estimation | Normalization |
Fills missing or unreported consumption | Adjusts reported consumption to a common basis |
Creates modelled values where data is missing | Scales existing values without inventing new usage |
Uses historical patterns to estimate gaps | Uses structural factors (time, occupancy, weather) |
Focused on data continuity | Focused on comparability |
Answers: “What likely happened when data is missing?” | Answers: “How would this data compare under equal conditions?” |
Note: Time-based normalization adjusts reported consumption to a full-year equivalent but does not estimate unreported usage; estimation is only applied when data is missing at the meter level.
See Normalization methodologies in Scaler for details on normalization logic.