Short-term forecasting of residential and commercial building energy consumption is widely used in power systems and continues to grow in importance. Data-driven short-term load forecasting (STLF), although promising, has suffered from a lack of open, large-scale datasets with high building diversity. This has hindered exploring the pretrain-then-fine-tune paradigm for STLF. To help address this, we present BuildingsBench, which consists of: 1) Buildings-900K, a large-scale dataset of 900K simulated buildings representing the U.S. building stock; and 2) an evaluation platform with over 1,900 real residential and commercial buildings from 7 open datasets. BuildingsBench benchmarks two under-explored tasks: zero-shot STLF, where a pretrained model is evaluated on unseen buildings without fine-tuning, and transfer learning, where a pretrained model is fine-tuned on a target building. The main finding of our benchmark analysis is that synthetically pretrained models generalize surprisingly well to real commercial buildings. An exploration of the effect of increasing dataset size and diversity on zero-shot commercial building performance reveals a power-law with diminishing returns. We also show that fine-tuning pretrained models on real commercial and residential buildings improves performance for a majority of target buildings. We hope that BuildingsBench encourages and facilitates future research on generalizable STLF. All datasets and code can be accessed from https://github.com/NREL/BuildingsBench.

Mobile devices offer much potential to support older adults (age 65+). However, older adults have been relatively slow to adopt mobile devices. Although much ongoing HCI research has examined usability problems to address this issue, little work has looked at whether existing graphical icons are harder to use for this population compared with younger adults. We conducted a qualitative exploratory study and a follow-up experimental study to determine which icon characteristics help initial icon usability for older adults. We found that our older participants did have more problems using existing mobile device icons, but that particular icon characteristics – semantically close meaning (i.e. natural, close link between depicted objects and associated function), familiar, labelled and concrete (i.e. those depicting real-world objects) – improved icon usability for them. We discuss how these findings can help icon designers to create mobile device icons that are more suited to the abilities and technology experience of older adults.