Lightweight Measurement and Estimation of Mobile Ad Energy Consumption

Mobile ads are an important component of the app ecosystem. Typically, developers use ads to generate revenue and, in return, end users get a “free” app. However, recent work has shown that apps with ads actually have significant hidden costs to end users in terms of energy, network usage, and performance. These can affect the ratings and reviews an app receives. Therefore, it is desirable for developers to balance the usage of ads with these potential negative costs. However, for energy, developers lack techniques to help them measure ad costs to their apps. To address thisproblem, we propose and evaluate several lightweight statistical approaches for measuring and predicting ad related energy consumption. We evaluate our approaches on real-world market apps and find that they are able to accurately and quickly estimate the energy cost without requiring expensive infrastructure or extensive developer effort.