Abstract
Measurement and Verification (M&V) aims to quantify savings achieved as part of energy efficiency and energy management projects. M&V depends heavily on metered energy data, modelling parameters and uncertainties that govern the energy system under consideration. M&V therefore requires a stringent handle on the inherent uncertainties in the calculated savings. The Bayesian framework of data analysis in the form of non-parametric, nonlinear Gaussian Process (GP) regression provides a mechanism by which these uncertainties can be quantified thoroughly, and is therefore an attractive alternative to the more traditional frequentist approach. It is important to select appropriate kernels to construct the prior when performing GP regression. This paper aims to construct a guideline for a practical GP regression within the energy M&V framework. It does not attempt to quantify energy losses or savings, but rather presents a case study that could act as a road map for energy managers and M&V professionals to apply the GP regression as a Bayesian alternative to base-line adjustment. Special attention will be given to the selection of appropriate kernels for the application of baseline adjustment and energy savings quantification in a model-independent manner.
Highlights
Energy saving measures (ESMs) usually aim to lower greenhouse gas (GHG) emissions in an attempt to mitigate climate change [1,2]
Notice that the Gaussian Process (GP) converged on hyper-parameters that can be linked directly to the physical nature of the energy system under consideration
The case study presented in this paper acts as an example of Bayesian alternatives (GP regression) for standard Measurement and Verification (M&V) analysis
Summary
Energy saving measures (ESMs) usually aim to lower greenhouse gas (GHG) emissions in an attempt to mitigate climate change [1,2]. In order to accurately quantify energy savings, accurate measurements and agreed upon methodologies are needed. The International Performance Measurement and Verification Protocol (IPMVP, see [3]), serve as industry-standards for energy M&V [1]. Accurate quantification of savings is important when considering tax-based incentives [1]. A very important factor to consider when interpreting savings is the inherent uncertainty in the data. The IPMVP highlights instrumentation and modelling error as two quantifiable sources of inaccuracy in the M&V process and stresses the importance of reporting possible savings as well as a well-defined uncertainty [3]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
