ABSTRACT
We aim to detect and diagnose code misbehavior that wastes energy,
which we call energy bugs. This talk describes a method and
implementation, called Carat, for performing such diagnosis on mobile
devices. Carat takes a collaborative, black-box approach. A
non-invasive client app sends intermittent, coarse-grained
measurements to a server, which identifies correlations between higher
expected energy use and client properties like the running apps,
device model, and operating system. Carat successfully detected all
energy bugs in a controlled experiment and, during a deployment to a
community of more than a quarter of a million users, detected (and
sometimes diagnosed) thousands of instances of buggy apps running in
the wild.
BIO
Adam Oliner is a postdoc in the EECS Department at UC Berkeley, working in
the AMP Lab. Before coming to Berkeley, he earned PhD in computer
science from Stanford University, where he was a DOE High Performance
Computer Science Fellow and Honorary Stanford Graduate Fellow. He
received a MEng in EECS from MIT, where he also earned undergraduate
degrees in computer science and mathematics. His research focuses on
understanding complex systems.