Comparing statistical modeling techniques for heat loss coefficient estimation using in-situ data

Abstract The combination of in-situ collected data and statistical modelling techniques proved to be a promising approach in actual building energy performance assessments, such as heat loss coefficient (HLC) evaluation. In this study, based on datasets co-heating pseudo-random binary sequence heating tests portable site office, the three types models (i.e. multiple linear regression (MLR), autoregressive with exogenous terms (ARX), grey-box models) HLC-determination are examined. It is revealed that similar HLC estimation outcome (about 115 W/K) offered by aforesaid models, but different confidence intervals (CIs), where 95% CIs MLR (±3.1%) ARX (±2.4%) relatively narrow ones grey box somewhat wider (around ± 9%). Moreover, for current case study building, evenly orientation-wise distributed glazed envelope, integrating B-splines into model, characterize solar aperture (gA) gain dynamics more precisely, imposed insignificant effects corresponding CIs, compared model constant gA assumption.