Building energy performance is difficult and costly to measure and existing metrics are prone to vagueness and inaccuracy. A more direct way to measure a buildings energy performance is to examine consumption using detailed monitoring. With the advent of real-time automatic meter reading (AMR) systems (often referred to as Smart Meters) we have the ability to capture vast quantities of energy consumption data. Unfortunately, it is not clear how this data is actually going to be used.
This project aims to reduce the requirement of significant intervention from a domain expert. Through use of Computational Intelligence (CI) techniques applied to consumption data we have demonstrated that much of the analysis needed to gain the full benefit from the data can be undertaken automatically saving time and money.
References to the research
Z. Yang, X. Li, C. P. Bowers, T. Schnier, K. Tang, and X. Yao. An efficient evolutionary approach to parameter identification in a building thermal model. Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on, 42(6):957–969, 2012.
X. Li, , C. P. Bowers, and T. Schnier. Classification of energy consumption in buildings with outlier detection. Industrial Electronics, IEEE Transactions on, 57(11):3639–3644, 2010.