[This article was first published on James Keirstead » Rstats, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.
One of the historic difficulties of doing research on urban energy systems has been the limited availability of data at sufficiently detailed spatial resolutions. Without this data, you might end up relying on aggregate information about the built environment, building occupants, and local geography that doesn't apply to the specifics of a particular neighbourhood or street.
Fortunately things are gradually improving and the UK government has a major initiative in this area: NEED, the National Energy Efficiency Data Framework. The project website has recently been updated with a series of data sets, mainly consisting of cross-tabulated statistics comparing insulation, dwelling size, income, dwelling age, and other factors.
I haven't had a chance to do anything meaningful with this data, but I thought a good starting point would be to write some functions to extract the necessary information from the provided Excel spreadsheets. So the analysis is purely exploratory, examining electricity and gas assumption measured at the level of individual English local authorities and grouped by dwelling floor area. The full code for parsing the data and making the plots is available at the bottom of the post, but here’s the main result.
Energy consumption by floor area for English local authorities
As you would expect, both the mean and the variance of gas consumption increase with larger dwellings. In electricity consumption, the effect is less noticeable with less distinction between consumption levels in small dwellings.
Let's hope that DECC makes more NEED data available quickly.