Skip to Content
ForecastingForecasting
  • Article
  • Open Access

21 November 2026

42 Pages

Does Synthetic Data Help Building Energy Analytics with Short Metering Histories? A Matched-Origin Evaluation with Structure-Free Controls and Simple Baselines

,
,
,
,
and
1
Coimbra Business School (ISCAC), Polytechnic University of Coimbra, Rua da Misericórdia, Lagar dos Cortiços, S. Martinho do Bispo, 3045-093 Coimbra, Portugal
2
School of Management and Technology, Santarém Polytechnic University, 2001-904 Santarém, Portugal
3
School of Technology and Management of Viseu, Polytechnic University of Viseu, Campus Politécnico, 3504-510 Viseu, Portugal
4
Research Center for Arts and Communication (CIAC), Santarém Polytechnic University, 2001-904 Santarém, Portugal
Forecasting2026, 8(6), 113;https://doi.org/10.3390/forecast8060113 
(registering DOI)
This article belongs to the Collection Energy Forecasting

Abstract

Synthetic data are often used to complete short building metering histories. We re-evaluate a transparent hour-of-week, temperature and AR(1) generator, calibrated on held-out buildings, completing 5–20% real training windows of 82 education buildings from the Building Data Genome Project 2 over 20 random splits. With the real window over a year before the test period, the supplement cut Prophet’s median paired error by 205.1 percentage points at 5%. With a matched forecast origin the reduction fell to 51.6, 15.1 and 3.1 points at 5, 10 and 20%, reversed over the first week, and did not differ detectably from white-noise, dispersion-matched or fully permuted complements (equivalence within ±3 points in only 4 of 18 comparisons). Real-only Prophet improved sharply when the same calendar weeks moved a year nearer the test period; season effects were imprecise. Flat-trend Prophet and a time-of-week profile on real data alone beat every supplemented model at five origins, suggesting the supplement mainly regularises Prophet’s trend. Supplements lowered Isolation Forest F1 through the contamination threshold, not average precision, and gave a profile-residual detector no supported advantage over regularising it without added data. Supplements should be tested with matched origins, structure-free controls, simple baselines and regularised models, per task and model.

Article Metrics

Citations

Article Access Statistics

Article metric data becomes available approximately 24 hours after publication online.