Review of data-driven energy modelling techniques for building retrofit

In order to meet the ambitious emission-reduction targets of Paris Agreement, energy efficient transition building sector requires retrofit methodologies as a critical part greenhouse-gas (GHG) emissions mitigation plan, since in 2050 high proportion current global stock will still be use. This paper reviews with focus on contrast between data-driven approaches that utilize measured data, acquired through either 1) on-site sensor deployment or 2) from pre-aggregated national repositories data. Differentiating bottom-up can divided into white-, grey- and black-box modelling, top-down analytical methods clustering regression, this presents state-of-the-art methodologies; outlines their strengths weaknesses; briefly highlights challenges implementation concludes by identifying hybrid approach - lean in-situ measurements supplemented modelling for verification potential strategy develop implement more robust stock.