Energy and Performance Efficient Computation Offloading for Deep Neural Networks in a Mobile Cloud Computing Environment.

In today's computing technology scene, mobile devices are considered to be computationally weak, while large cloud servers are capable of handling expensive workloads, therefore, intensive computing tasks are typically offloaded to the cloud. Recent advances in learning techniques have enabled Deep Neural Networks (DNNs) to be deployed in a wide range of applications. Commercial speech based intelligent personal assistants (IPA) like Apple's Siri, which employs DNN as its recognition model, operate solely over the cloud. The cloud-only approach may require a large amount of data transfer between the cloud and the mobile device. The mobile-only approach may lack performance efficiency. In addition, the cloud server may be slow at times due to the congestion and limited subscription and mobile devices may have battery usage constraints. In this paper, we investigate the efficiency of offloading only some parts of the computations in DNNs to the cloud. We have formulated an optimal computation offloading framework for forward propagation in DNNs, which adapts to battery usage constraints on the mobile side and limited available resources on the cloud. Our simulation results show that our framework can achieve 1.42x on average and up to 3.07x speedup in the execution time on the mobile device. In addition, it results in 2.11x on average and up to 4.26x reduction in mobile energy consumption.