From M&V to M&T: An artificial intelligence-based framework for real-time performance verification of demand-side energy savings

Abstract

The European Union's Energy Efficiency Directive is placing an increased focus on the measurement and verification (M&V) of demand side energy savings. The objective of M&V is to quantify energy savings with minimum uncertainty. M&V is currently undergoing a transition to practices, known as M&V 2.0, that employ automated advanced analytics to verify performance. This offers the opportunity to effectively manage the transition from short-term M&V to long-term monitoring and targeting (M&T) in industrial facilities. The original contribution of this paper consists of a novel, robust and technology agnostic framework that not only satisfies the requirements of M&V 2.0, but also bridges the gap between M&V and M&T by ensuring persistence of savings. The approach features a unique machine learning-based energy modelling methodology, model deployment and an exception reporting system that ensures early identification of performance degradation. A case study demonstrates the effectiveness of the approach. Savings from a real-world project are found to be 177,962 +/- 12,334 kWh with a 90% confidence interval. The uncertainty associated with the savings is 8.6% of the allowable uncertainty, thus highlighting the viability of the framework as a reliable and effective tool.