Using Machine Learning to Enrich Building Databases—Methods for Tailored Energy Retrofits

Abstract

Building databases are important assets when estimating and planning for national energy savings from energy retrofitting. However, databases often lack information on building characteristics needed to determine the feasibility of specific energy conservation measures. In this paper, machine learning methods are used to enrich the Swedish database of Energy Performance Certificates with building characteristics relevant for a chosen set of energy retrofitting packages. The study is limited to the Swedish multifamily building stock constructed between 1945 and 1975, as these buildings are facing refurbishment needs that advantageously can be combined with energy retrofitting. In total, 514 ocular observations were conducted in Google Street View of two building characteristics that were needed to determine the feasibility of the chosen energy retrofitting packages: (i) building type and (ii) suitability for additional façade insulation. Results showed that these building characteristics could be predicted with an accuracy of 88.9% and 72.5% respectively. It could be concluded that machine learning methods show promising potential to enrich building databases with building characteristics relevant for energy retrofitting, which in turn can improve estimations of national energy savings potential.

Machine Learning Techniques Focusing on the Energy Performance of Buildings: A Dimensions and Methods Analysis

“…Moreover, referring to the RQ2, several authors used GA (7) [23,27,38,39,42,48] to predict cost-optimal energy retrofit solutions. Some approaches used artificial neural networks (ANN) [35,40,48,50,52,56]. Most papers in this category are case studies using a single building or a representative building sample to collect the necessary data to serve their experiments.…”

“…Ultimately, some (2) applied manual classification [47,49]. As a prediction of EP and cost-optimal retrofit solutions techniques, some approaches (7) employed ANN and GA [40,47,49,50,52,56,57]. Others implemented different ML algorithms, such as random forest (RF) [59].…”

“…The remaining SLR papers used similar dimensions: building geometry, building envelope, other building properties, climate and weather, HVAC systems, and energy consumption (EC) [16,18,20,21,. A total of 19 out of 35 papers used a residential building as the case study [28][29][30][33][34][35][36][37]39,[41][42][43][45][46][47][53][54][55][56][57]. Some of them combine different types of buildings.…”

“…Furthermore, only the most recent papers utilized building EPC data for their analysis [28,29,31,34,[50][51][52][53][54]56,57,60,61]. This aspect is surprising since the first directive on building energy performance, "the Energy Performance of Building Directive (EPBD)," was introduced by the European Parliament in 2002.…”

“…The most-used techniques for predicting EP and retrofitting were energy performance simulation techniques, statistical-based approaches, genetic algorithms, and ANN. Few studies use only ML methods, namely ( 13) studies [28,29,31,[33][34][35]40,45,48,50,52,56,59]. The most common clustering and classification techniques were K-means (7), statistical methods (6), Latin hypercube sampling (2), other manual groupings (2), decision tree (2), and probability density function (1) [23,25,[28][29][30][31][32][33][34]47,[50][51][52]54,55,57,59].…”