# DVFO: Learning-Based DVFS for Energy-Efficient Edge-Cloud Collaborative Inference

arXiv: https://arxiv.org/abs/2306.01811 · HTML: https://mlsanity.com/paper/2306.01811/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 75 references that are in the map.
- First posted on arXiv 2 Jun 2023.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [Deep Speech: Scaling up end-to-end speech recognition](https://mlsanity.com/paper/1412.5567/) (2014)
- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [ElasticFace: Elastic Margin Loss for Deep Face Recognition](https://mlsanity.com/paper/2109.09416/) (2021)
- [SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud](https://mlsanity.com/paper/2008.06402/) (2020)
- [Measuring the Carbon Intensity of AI in Cloud Instances](https://mlsanity.com/paper/2206.05229/) (2022)
- [Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors](https://mlsanity.com/paper/2001.02811/) (2020)
- [Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training](https://mlsanity.com/paper/2208.06102/) (2022)
- [Thinking While Moving: Deep Reinforcement Learning with Concurrent Control](https://mlsanity.com/paper/2004.06089/) (2020)
- [Predictive Exit: Prediction of Fine-Grained Early Exits for Computation- and Energy-Efficient Inference](https://mlsanity.com/paper/2206.04685/) (2022)
- [ShadowNet: A Secure and Efficient On-device Model Inference System for Convolutional Neural Networks](https://mlsanity.com/paper/2011.05905/) (2020)
- [AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference](https://mlsanity.com/paper/2105.04104/) (2021)
- [MLPerf Mobile Inference Benchmark](https://mlsanity.com/paper/2012.02328/) (2020)
- [Learning Compressed Embeddings for On-Device Inference](https://mlsanity.com/paper/2203.10135/) (2022)
- [R-TOD: Real-Time Object Detector with Minimized End-to-End Delay for Autonomous Driving](https://mlsanity.com/paper/2011.06372/) (2020)

## Built on by (most cited first, 14 of 14)

- [Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey](https://mlsanity.com/paper/2505.01821/) (2025)
- [Dissecting the Impact of Mobile DVFS Governors on LLM Inference Performance and Energy Efficiency](https://mlsanity.com/paper/2507.02135/) (2025)
- [FlowRL: Flow-Augmented Few-Shot Reinforcement Learning for Semi-Structured Sensor Data](https://mlsanity.com/paper/2409.14178/) (2024)
- [E4: Energy-Efficient DNN Inference for Edge Video Analytics Via Early-Exit and DVFS](https://mlsanity.com/paper/2503.04865/) (2025)
- [Joint Memory Frequency and Computing Frequency Scaling for Energy-efficient DNN Inference](https://mlsanity.com/paper/2509.17970/) (2025)
- [PELM: Power Efficient On-Device LLM Inference with Speculative Decoding and Dynamic Voltage Frequency Scaling](https://mlsanity.com/paper/2609.09662/) (2026)
- [Feature-Aware Task-to-Core Allocation in Embedded Multi-core Platforms via Statistical Learning](https://mlsanity.com/paper/2502.15716/) (2025)
- [Energy-Efficient GPU DVFS for Fine-Tuning of SLMs on Resource-constrained Embedded Devices](https://mlsanity.com/paper/2607.05933/) (2026)
- [Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment](https://mlsanity.com/paper/2411.00838/) (2024)
- [Fine-Grained AI Model Caching and Downloading With Coordinated Multipoint Broadcasting in Multi-Cell Edge Networks](https://mlsanity.com/paper/2509.19341/) (2025)
- [ZeroDVFS: Zero-Shot LLM-Guided Core and Frequency Allocation for Embedded Platforms](https://mlsanity.com/paper/2601.08166/) (2026)
- [Covariance-Guided Resource Adaptive Learning for Efficient Edge Inference](https://mlsanity.com/paper/2603.14577/) (2026)
- [TetraRL: A Self-Adaptive Runtime for On-Device Deep Reinforcement Learning Systems](https://mlsanity.com/paper/2606.13891/) (2026)
- [Joint Optimization of Memory and Computing Frequency for Energy-Efficient DNN Inference](https://mlsanity.com/paper/2608.13863/) (2026)

## Abstract (arXiv)

Due to limited resources on edge and different characteristics of deep neural network (DNN) models, it is a big challenge to optimize DNN inference performance in terms of energy consumption and end-to-end latency on edge devices. In addition to the dynamic voltage frequency scaling (DVFS) technique, the edge-cloud architecture provides a collaborative approach for efficient DNN inference. However, current edge-cloud collaborative inference methods have not optimized various compute resources on edge devices. Thus, we propose DVFO, a novel DVFS-enabled edge-cloud collaborative inference framework, which co-optimizes DVFS and offloading parameters via deep reinforcement learning (DRL). Specifically, DVFO automatically co-optimizes 1) the CPU, GPU and memory frequencies of edge devices, and 2) the feature maps to be offloaded to cloud servers. In addition, it leverages a thinking-while-moving concurrent mechanism to accelerate the DRL learning process, and a spatial-channel attention mechanism to extract DNN feature maps of secondary importance for workload offloading. This approach improves inference performance for different DNN models under various edge-cloud network conditions. Extensive evaluations using two datasets and six widely-deployed DNN models on three heterogeneous edge devices show that DVFO significantly reduces the energy consumption by 33% on average, compared to state-of-the-art schemes. Moreover, DVFO achieves up to 28.6%-59.1% end-to-end latency reduction, while maintaining accuracy within 1% loss on average.