• Home
  • Search
  • Murmuration: On-the-fly DNN Adaptation for SLO-Aware Distributed Inference in Dynamic Edge Environments
  • Cite Icon1
  • https://doi.org/10.1145/3673038.3673154Copy DOI Icon

Murmuration: On-the-fly DNN Adaptation for SLO-Aware Distributed Inference in Dynamic Edge Environments

  • Aug 12, 2024
  • Jieyu Lin +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

The proliferation of Virtual and Augmented Reality (VR/AR) and the Internet of Things (IoT) applications is driving the demand for efficient Deep Neural Network (DNN) inference at the edge. These applications often impose stringent Service Level Objectives (SLOs), such as latency or accuracy, that must be met under the constraints of limited resources and dynamic network conditions. In this study, we explore a novel approach to DNN inference across multiple edge devices, incorporating both model customization and partitioning dynamically, to better align with these constraints and SLOs. Unlike conventional methods that employ a single fixed DNN network, our system, termed Murmuration, combines one-shot Neural Architecture Search (NAS) and Reinforcement Learning (RL) to dynamically customize and partition DNN models. This approach adapts in real-time to the capabilities of the edge devices, network conditions, and varying SLO requirements. The design of Murmuration allows it to effectively navigate the large search space defined by DNN models, network delays, and bandwidth, offering a significant improvement in managing trade-offs between accuracy and latency.

Similar Papers
  • Conference Article
  • Citations2

Model Parallelism Optimization for Distributed DNN Inference on Edge Devices

  • Nov 24, 2023
  • Meng Wang +4
  • Research Article
  • Citations20

Split computing: DNN inference partition with load balancing in IoT-edge platform for beyond 5G

  • Aug 18, 2022
  • Measurement: Sensors
  • Jyotirmoy Karjee +3
  • Research Article
  • Citations26

Stochastic Cumulative DNN Inference With RL-Aided Adaptive IoT Device-Edge Collaboration

  • Oct 15, 2023
  • IEEE Internet of Things Journal
  • Kaige Qu +6
  • Conference Article
  • Citations15

EdgeLD: Locally Distributed Deep Learning Inference on Edge Device Clusters

  • Dec 01, 2020
  • Feng Xue +5
  • Research Article
  • Citations146

Deep Reinforcement Learning Based Resource Management for DNN Inference in Industrial IoT

  • Mar 24, 2021
  • IEEE Transactions on Vehicular Technology
  • Weiting Zhang +6
  • Conference Article
  • Citations3

Towards Ultra-Efficient DNN Inference Acceleration on Edge Devices for Wellbeing Applications

  • Jun 19, 2020
  • Yanzhi Wang
  • Research Article
  • Citations7

Low Latency and Accuracy-Guaranteed DNN Inference for Drone-Assisted IoT Networks

  • Dec 01, 2025
  • IEEE Transactions on Cognitive Communications and Networking
  • Jiaqi Xu +4
  • Research Article
  • Citations113

Throughput Maximization of Delay-Aware DNN Inference in Edge Computing by Exploring DNN Model Partitioning and Inference Parallelism

  • May 01, 2023
  • IEEE Transactions on Mobile Computing
  • Jing Li +5
  • Research Article
  • Citations3

ChipAI: A scalable chiplet-based accelerator for efficient DNN inference using silicon photonics

  • Nov 26, 2024
  • Journal of Systems Architecture
  • Hao Zhang +3
  • Conference Article
  • Citations10

Delay-Aware DNN Inference Throughput Maximization in Edge Computing via Jointly Exploring Partitioning and Parallelism

  • Oct 04, 2021
  • Jing Li +4
  • Research Article
  • Citations6

PMP: A partition-match parallel mechanism for DNN inference acceleration in cloud–edge collaborative environments

  • Aug 18, 2023
  • Journal of Network and Computer Applications
  • Zhuofan Liao +3
  • Conference Article

Understanding information leakage of distributed inference with deep neural networks: overview of information, theoretic approach, and initial results

  • May 04, 2018
  • Shiqiang Wang +3
  • PDF
  • Research Article

Optimal deep neural network architecture design with improved generalization for data-driven cooling load estimation problem

  • May 02, 2025
  • Neural Computing and Applications
  • Baris Baykant Alagoz +4
  • PDF
  • Research Article
  • Citations6

Auto-Tiler: Variable-Dimension Autoencoder with Tiling for Compressing Intermediate Feature Space of Deep Neural Networks for Internet of Things

  • Jan 29, 2021
  • Sensors (Basel, Switzerland)
  • Jeongsoo Park +2
  • Research Article
  • Citations8

PLAYS: Minimizing DNN Inference Latency in Serverless Edge Cloud for Artificial Intelligence of Things

  • Dec 01, 2024
  • IEEE Internet of Things Journal
  • Hongmin Geng +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.