Suppose I want to predict energy consumption for my building using regression analysis. What factors should I consider including in my model?

It depends a little bit on the way your model will be designed and what are the available data.

In one of the most simplest ways you will have a mean energy consumption per human/animal/anything and you simply multiply by the number of individuals.

But i think that is not your intention.

Probably you have a data set with dfferent independent variables and you want one final response, that is not as simply associated as in my example above.

There are a couple of standard software tools available for a multiple (linear/non-liniear) regression. I would prefer R and the models of the lm type. Pretty good manuals are found around the web. But you may choose whatever you want; results should be the same.

An interesting introduction to the math behind is given in a paper by the US Geological Survey:

https://pubs.usgs.gov/tm/tm4a8/pdf/TM4-A8.pdf

However, depending on the specification of your problem it might be interesting to have a closer look at some other statistics.

When you can define specific groups (like high energy consumption time, low energy consumption time, medium, extraordinary, ...) a linear discriminant function analysis might be an interesting choice. It allows identifying specific variables, being characteristic (high contribution) for a predefined group.

A factor analysis might also be a good choice to identify higher/lower variable contributions.

If you are not really in charge to present the contributions of the variables a random Forest analysis might be interesting. This machine leraning classifyier can be also run as a regression model. You have less impression about the variables contributions, but the results can be more precise...

Nevertheless, it depends a bit on the available data. Did you already prepare a pairs plot and the correlation among the variables? This may also give a first impression....

Jan

Santhakumar Aridoss

Predicting energy consumption for a building using regression analysis requires careful consideration of various factors that can influence energy usage. Here are some common factors that you may want to consider including in your regression model:

Building characteristics: Factors such as building size (square footage), building age, building type (e.g., residential, commercial, industrial), building construction materials, and building orientation (e.g., north-facing, south-facing) can impact energy consumption. Buildings with larger floor areas, older ages, and different construction materials may have different energy usage patterns.

Climate and weather data: Climate and weather conditions, such as outdoor temperature, humidity, solar radiation, and wind speed, can significantly impact building energy consumption. For example, buildings in colder climates may require more heating energy, while buildings in hotter climates may require more cooling energy.

Occupancy and usage patterns: The number of occupants in the building, their behavior, and usage patterns can impact energy consumption. Factors such as occupancy hours, occupancy density, and occupant behavior (e.g., thermostat settings, appliance usage) can influence energy usage.

Building systems and equipment: The efficiency and usage of building systems and equipment, such as heating, ventilation, and air conditioning (HVAC) systems, lighting systems, and appliances, can impact energy consumption. Factors such as equipment age, efficiency ratings, maintenance schedules, and usage patterns can affect energy usage.

Time-based variables: Time-based variables, such as day of the week, season, and time of day, can impact energy consumption. For example, energy usage may vary on weekdays versus weekends, during different seasons (e.g., winter, summer), and during different times of day (e.g., peak hours, off-peak hours).

Energy pricing and tariffs: Energy pricing and tariffs, such as electricity rates, demand charges, and time-of-use (TOU) rates, can influence energy consumption patterns. Higher energy prices during peak hours or different pricing structures can affect how energy is consumed in a building.

Building envelope and insulation: The quality and efficiency of the building envelope, including insulation levels, windows, and doors, can impact energy consumption. A well-insulated building with efficient windows and doors may require less heating or cooling energy compared to a poorly insulated building.

Renewable energy sources: If the building has renewable energy sources, such as solar panels or wind turbines, the generation and usage of renewable energy can impact energy consumption. For example, during periods of high solar radiation, a building with solar panels may generate excess energy, which could affect overall energy consumption.

Historical energy consumption data: Historical energy consumption data for the building can provide valuable insights into past energy usage patterns and serve as a predictor for future energy consumption. Including historical energy consumption data in your regression model can help identify trends and patterns that may impact future energy usage.

It's important to carefully select and include relevant factors in your regression model based on your specific building and its usage patterns. You may also need to consider data availability, data quality, and statistical significance of the factors in your analysis. Regular model evaluation and refinement may be necessary to ensure accurate predictions of energy consumption in your building. Consulting with domain experts or energy professionals can also provide valuable insights and guidance in developing an effective regression model for energy consumption prediction.

James R Knaub

Dinesh Kumar -

As Jan Schulz noted, "...it depends ... on the available data." That's unfortunate because building an accurate model would be an elusive task, even if you had good quality data for anything you might want. You don't want to miss vital information which would bias your results, yet you don't want extraneous or redundant (collinear) information which increases variance. [I've noted that without having the perfect set of variables, not too many, not too few, and just the right ones, one will not see the 'essential heteroscedasticity' that one should see.*]

Perhaps you should contact the US Energy Information Administration (EIA). They collect a building energy consumption survey. You could find that on their website. You could ask for suggestions there: See https://www.eia.gov/ and https://www.eia.gov/about/contact/.

By the way, by "predict" with regression, that would mean "estimation" for a finite population, as regression is for a random variable. If you actually mean "forecast" instead, you should make that clear when you ask the EIA for suggestions.

Cheers - Jim

*Knaub, J.R., Jr.(2021), "When Would Heteroscedasticity in Regression Occur?" Pak. J. Statist., Vol. 37(4), 315-367, https://www.pakjs.com/,

http://www.pakjs.com/wp-content/uploads/2021/07/37401-1.pdf,

https://www.researchgate.net/publication/354854317_WHEN_WOULD_HETEROSCEDASTICITY_IN_REGRESSION_OCCUR

Which is the most efficient etching solution for nickel based alloys?

Which is the most convenient manufacturing software for Additive Manufacturing?

Which is the best place in the world for the plant biotechnology research?

Which SAR dataset to use for generating coherency matrix and performing target decomposition (Description) ?

How does one access the Cranet survey data on HRM practices?

Genome-wide gene identification protocol ?

Can the problems of overfitting be solved without cross validation?

Research Gate Does it help researches to publicize their scientific work ?

How to Study a proton NMR of Graphene prepared by Electrochemical Exfoliation technique?

How to classify and recognize unseen image class in document sorting?

How to compare two groups with only two measurements?

Enhanced Yellow Fluorescent Protein (Aequorea victoria) DNA sequence?

What kind of fluid could I use for a pitfall trap that also does not invalidate molecular testing?

What's the best way to measure growth rates in House sparrow chicks from day 2 to day 10?

After a reference from Int J Body Compos Res, can any body help?

Irradiation data for JAPAN?

Logistical regression using SPSS for a dichotomous dependent variable, with an independent variable of 1, 2, 5 and 10 seconds?

Do we need to write protocol for a second study of a systematic review that has been registered and published?

How to increase a model accuracy ?

Do I need to do linear regression before running mediation analysis using PROCESS MACRO by Hayes ?