Joint Optimization of Memory and Computing Frequency for Energy-Efficient DNN Inference

Abstract

Deep neural network (DNN) inference on mobile devices often incurs high latency and energy consumption due to limited computing and memory resources. To enable energyefficient DNN inference, most existing studies focus on dynamic voltage and frequency scaling (DVFS) for adjusting the computing frequency, while the impact of memory frequency on the inference performance has been greatly overlooked. In this paper, we consider the impact of memory frequency and computing frequency on DNN inference time, and jointly optimize these two frequencies together with communication resources for energyefficient DNN inference. Based on a realistic inference time model, we formulate an optimization problem to minimize the energy consumption of all mobile devices under the deadline constraint. For local inference, we derive a near-optimal closedform solution via convex optimization, while an optimal closedform solution for transmission power is obtained for edge inference with the given bandwidth. Furthermore, we propose a low-complexity heuristic algorithm to effectively solve the overall problem with polynomial time complexity. Simulation results based on measured data show that the proposed near-optimal solution for local inference can achieve optimal performance under strict deadline constraints, with a performance gap of up to 2.5% compared with the optimal solution. Meanwhile, our proposed algorithm significantly reduces the energy consumption of devices by up to 10.4% compared to other methods.