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

2026-08-13

AI Summary

This study addresses the high energy consumption of mobile DNN inference by incorporating memory frequency into a joint optimization framework that coordinates computation, memory, and communication resources. We establish an accurate inference latency model to derive near-optimal closed-form solutions for both local and edge inference, complemented by a low-complexity heuristic algorithm. Experimental results demonstrate that the proposed near-optimal solution for local inference deviates from the global optimum by only 2.5%, while the overall algorithm reduces device energy consumption by up to 10.4%. These findings confirm the effectiveness of our approach in optimizing energy efficiency for deadline-constrained mobile inference, bridging a critical gap in existing research that has previously overlooked memory frequency scaling.

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 energy-efficient 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 energy-efficient 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 closed-form solution via convex optimization, while an optimal closed-form 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.

Problem

• DNN inference
• energy efficiency
• memory frequency
• joint optimization
• mobile devices

Innovation

• Joint Optimization
• Memory Frequency
• Energy-Efficient DNN Inference
• Closed-form Solution
• Low-complexity Heuristic