Development and application of a machine learning supported methodology for measurement and verification (M&V) 2.0

Abstract

The foundations of all methodologies for the measurement and verification (M&V) of energy savings are based on the same five key principles: accuracy, completeness, conservatism, consistency and transparency. The most widely accepted methodologies tend to generalise M&V so as to ensure applicability across the spectrum of energy conservation measures (ECM's). These do not provide a rigid calculation procedure to follow. This paper aims to bridge the gap between high-level methodologies and the practical application of modelling algorithms, with a particular focus on the industrial buildings sector. This is achieved with the development of a novel, machine learning supported methodology for M&V 2.0 which enables accurate and reliable quantification of savings.A novel and computationally efficient feature selection algorithm and powerful machine learning regression algorithms are employed to maximise the effectiveness of available data. The baseline period energy consumption is modelled using artificial neural networks, support vector machines, k-nearest neighbours and multiple ordinary least squares regression. Improved knowledge discovery and an expanded boundary of analysis allow more complex energy systems be analysed, thus increasing the applicability of M&V. A case study in a large biomedical manufacturing facility is used to demonstrate the methodology's ability to accurately quantify the savings under real-world conditions. The ECM was found to result in 604,527 kWh of energy savings with 57% uncertainty at a confidence interval of 68%. 20 baseline energy models are developed using an exhaustive approach with the optimal model being used to quantify savings. The range of savings estimated with each model are presented and the acceptability of uncertainty is reviewed. The case study demonstrates the ability of the methodology to perform M&V to an acceptable standard in challenging circumstances.

Prediction mapping of human leptospirosis using ANN, GWR, SVM and GLM approaches

“…VIF measures the intensity of multicollinearity amongst independent parameters [74]. Confirmed by statistical studies, VIF values of input parameters that are less than 10 are acceptable for entering the model [75]. Table 3 presents that the maximum calculated VIF values of parameters belong to vegetation parameter (2.71), and the minimum is acquired for precipitation parameter (1.17).…”

State-of-the-art on research and applications of machine learning in the building life cycle

“…Table 9 summarizes the machine learning algorithms used in papers that are reviewed in this section. [132], [140] Clustering and ANN [19] Clustering [133] Random Forest [134] Linear Regression [135] Linear Regression and PCA [136] Gradient Boosting [137] Linear Regression and Clustering [138] Gradient Boosting and Clustering [139] ANN [141] Evaluate energy conservation measures ANN, SVM, K-Nearest Neighbors, and Linear Regression [143] ANN [144] Gradient Boosting and Linear Regression [145] Characterize buildings Random Forest [150] SVM [151] CNN [152] Boosted Decision Trees [153] SVM [154] 6.1 Identify retrofit potential Usually, building retrofit planning requires detailed energy audits, which are time-consuming. As the audit data accumulates, machine learning methods will be feasible to explore the underlying patterns of the data to support the generalization of the retrofit planning to large building stocks.…”

“…The term "M&V 2.0" is being used in recent years to describe the automated and streamlined approach that uses large datasets and computational automation for the M&V process, where machine learning models are playing an increasingly important role [142]. Colm et al [143] develop a platform using machine learning methods to enable automated, accurate, and reliable quantifications of energy savings in the M&V process. A mixed model using ANN, SVM, k-nearest neighbors, and multiple ordinary least squares regression was adopted to model the baseline energy consumption.…”

A Machine Learning Pipeline for Demand Response Capacity Scheduling

“…The ML based building load forecast models have been extensively reviewed in [8][9][10][11][12][13]. Some of these models are developed for specific application areas such as building performance measurement and verification [14][15][16][17], building control [18][19][20] and demand-side management [21,22], whereas a significant number of studies are application agnostic. Literature demonstrates the capability of supervised ML algorithms such as artificial neural networks (ANN) [23], support vector machines (SVM) [24], decision trees [25,26], Gaussian processes [27][28][29] and nearest neighbours [30], among others, in developing reliable building load forecast models.…”