kW Engineering | Sustainable Buildings & Energy Efficiency Consulting

sustainable building energy consulting kw engineering logo

Meera Sharma

NMEC Baseline Model Predictability: Data Science Deep Dive

Normalized metered energy consumption (NMEC) methods offer many benefits to energy efficiency utility programs and their participants, but care must be used. NMEC programs rely on baseline models for pre-screening and energy savings calculations following implementation. The results of each of these steps determine program eligibility and the size of a participant’s incentive check. So, […]

NMEC Baseline Model Predictability: Data Science Deep Dive Read More »

How to Accurately Predict Energy Savings Using Linear Regression and High Frequency Energy Data

We, in the energy industry, have long used engineering calculations, aided by simple linear regression models, to estimate the energy saving potential of proposed interventions. However, as data sensors become increasingly ubiquitous and data storage costs continue to decline year over year, a shift away from this engineering calculation-based approach to a more data-centric approach

How to Accurately Predict Energy Savings Using Linear Regression and High Frequency Energy Data Read More »

How to Assess a Regression’s Predictive Power for Energy Use

You created a regression model of your building’s energy use and now want to use its predictive capabilities. How do you go about assessing your model’s predictive power? As I mentioned in an earlier post, you want to steer away from focusing on a singular metric and build a comprehensive understanding of the model. Let’s

How to Assess a Regression’s Predictive Power for Energy Use Read More »

Data science deep dive: Moving beyond R-squared to p-value for better energy analysis.

We use regression analysis frequently in our energy engineering analysis, but results can be less than ideal for many cases. Now with big data and the current technology of faster computing, we can use a comprehensive understanding of statistics, hypothesis testing, and principles of inference to better predict and verify energy savings, and mitigate the

Data science deep dive: Moving beyond R-squared to p-value for better energy analysis. Read More »

How to overcome energy management barriers for commercial & industrial customers

More often than not, commercial and industrial firms’ primary business objective is to drive a high volume of sales. Commercial facilities are focused on ensuring high comfort level for the occupants and the industrial facilities care about their Key Volume Indicators; so energy management is not a business goal. While reducing energy waste can help

How to overcome energy management barriers for commercial & industrial customers Read More »