计算机工程2026，Vol.52Issue(5)：404-417,14.DOI:10.19678/j.issn.1000-3428.0070165
LuffyNet:面向硬件感知的边缘智能
LuffyNet:Toward Hardware-Aware Edge Intelligence
摘要
Abstract
Edge intelligence faces challenges such as real-time computation,limited resources,and device variations.Typically,models are compressed to create lightweight networks for fast inference in edge environments.However,excessive compression reduces accuracy and does not always shorten the inference time,thereby affecting the performance of edge intelligence.To address these issues,this paper proposes a hardware-aware edge intelligence framework called LuffyNet.The framework uses a lookup table to estimate the inference performance.It applies constraints on the computational latency and device memory to make the model hardware-aware.LuffyNet aims to create high-accuracy networks that fit edge devices while satisfying latency limits.The framework optimizes the model accuracy,inference latency,and network size through gradient descent.To reduce the search time,LuffyNet uses best optimization and worst optimization strategies.This approach reduces unnecessary computation and saves time and resources.Comparison experiments evaluate LuffyNet networks against four advanced models.LuffyNet-A achieves 66.50％Top-1 accuracy with a 1.69 ms delay,approximately five times faster than ResNet50,and is only 6.58 MB in size.LuffyNet-B and LuffyNet-C exceed 73％Top-1 accuracy with a 2.65 ms delay.They outperform ResNet18,ResNet50,DenseNet121,and DenseNet169 in terms of accuracy and speed.Ablation experiments confirm that networks formed using the LuffyNet framework are not only suitable for edge devices but also reduce the search time by approximately 25％.关键词
边缘智能/硬件感知/网络架构搜索/推理时延/网络大小Key words
edge intelligence/hardware-aware/network architecture search/inference latency/network size分类
信息技术与安全科学引用本文复制引用
林海,王和钰,曹越,王丽园,王世杰..LuffyNet:面向硬件感知的边缘智能[J].计算机工程,2026,52(5):404-417,14.基金项目
湖北省重点研发计划项目(2023BAB022) （2023BAB022）
湖北省国际科技合作项目(2023EHA033) （2023EHA033）
国家重点研发计划(2022YFB3102100). （2022YFB3102100）
