☆ 4.8 Article

Reliability-Aware Online Scheduling for DNN Inference Tasks in Mobile-Edge Computing

IEEE INTERNET OF THINGS JOURNAL (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Automation & Control Systems

DNN Deployment, Task Offloading, and Resource Allocation for Joint Task Inference in IIoT

Wenhao Fan et al.

Summary: In this paper, a novel joint resource management scheme is proposed to enhance the performance of deep neural network (DNN) inference services in the industrial internet of things (IIoT) applications. The scheme includes DNN deployment, data size control, task offloading, computing resource allocation, and wireless channel allocation. By leveraging Lyapunov optimization and DDPG algorithm, the near optimal solution is achieved and compared with other schemes through experiments.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2023)

添加到收藏夹

Article Automation & Control Systems

Accuracy-Guaranteed Collaborative DNN Inference in Industrial IoT via Deep Reinforcement Learning

Wen Wu et al.

Summary: Collaboration among industrial IoT devices and edge networks is crucial for supporting computation-intensive DNN inference services with low delay and high accuracy. Sampling rate adaption plays a key role in minimizing service delay by dynamically configuring the sampling rates of IoT devices according to network conditions. The proposed deep RL-based algorithm, which transforms CMDP into MDP and incorporates an optimization subroutine, significantly reduces average service delay while maintaining long-term inference accuracy.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

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

Weiting Zhang et al.

Summary: This study introduces an end-edge-cloud orchestration architecture to tackle the challenges of performing deep neural network inference in resource-limited industrial Internet of things networks. By flexibly coordinating inference task assignment and DNN model placement, as well as implementing a resource management scheme based on deep reinforcement learning, efficient DNN inference and improved accuracy can be achieved.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2021)

添加到收藏夹

Article Computer Science, Information Systems

Unconstrained Submodular Maximization with Modular Costs: Tight Approximation and Application to Profit Maximization

Tianyuan Jin et al.

Summary: This paper introduces ROI-Greedy, an algorithm for solving the unconstrained submodular maximization with modular costs problem, which provides a strong approximation guarantee and outperforms competing methods in terms of efficiency and solution quality. Extensive experiments on benchmark datasets demonstrate the efficacy of ROI-Greedy in finding near-optimal solutions.

PROCEEDINGS OF THE VLDB ENDOWMENT (2021)

添加到收藏夹

Proceedings Paper Telecommunications

Energy-Constrained Online Matching for Satellite-Terrestrial Integrated Networks

Jingye Wang et al.

Summary: In this paper, the problem of task matching in satellite-terrestrial integrated networks is addressed, and a TRDBL scheme based on data-driven bandit learning is proposed to tackle this issue. The theoretical analysis and simulation results confirm the effectiveness of the proposed scheme in terms of task latency reduction and energy efficiency.

IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2021) (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

Online Learning Based Computation Offloading in MEC Systems With Communication and Computation Dynamics

Kun Guo et al.

Summary: This paper proposes online computation offloading mechanisms to minimize the task execution delay in mobile edge computing systems, leveraging Lyapunov optimization framework and multi-armed bandit framework for two different MEC server selection algorithms. Theoretical analyses and extensive simulations demonstrate the near-optimality and feasibility of the proposed algorithms, showcasing their ability to balance communication and computation dynamics for enriched user experience and reduced energy consumption.

IEEE TRANSACTIONS ON COMMUNICATIONS (2021)

添加到收藏夹

Review Computer Science, Information Systems

Applications of Artificial Intelligence and Machine learning in smart cities

Zaib Ullah et al.

COMPUTER COMMUNICATIONS (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing

En Li et al.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2020)

添加到收藏夹

Article Computer Science, Information Systems

A Fast Algorithm for Energy-Saving Offloading With Reliability and Latency Requirements in Multi-Access Edge Computing

Haolin Liu et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Event driven and semantic based approach for data processing on IoT gateway devices

Mahmud Al-Osta et al.

JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING (2019)

添加到收藏夹

Article Engineering, Electrical & Electronic

Dynamic Task Offloading and Resource Allocation for Ultra-Reliable Low-Latency Edge Computing

Chen-Feng Liu et al.

IEEE TRANSACTIONS ON COMMUNICATIONS (2019)

添加到收藏夹

Proceedings Paper Computer Science, Hardware & Architecture

Intelligence Beyond the Edge: Inference on Intermittent Embedded Systems

Graham Gobieski et al.

TWENTY-FOURTH INTERNATIONAL CONFERENCE ON ARCHITECTURAL SUPPORT FOR PROGRAMMING LANGUAGES AND OPERATING SYSTEMS (ASPLOS XXIV) (2019)

添加到收藏夹

Article Computer Science, Information Systems

Survey on Multi-Access Edge Computing for Internet of Things Realization

Pawani Porambage et al.

IEEE COMMUNICATIONS SURVEYS AND TUTORIALS (2018)

添加到收藏夹

Article Environmental Sciences

Predicting Infectious Disease Using Deep Learning and Big Data

Sangwon Chae et al.

INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH (2018)

添加到收藏夹

Article Computer Science, Hardware & Architecture

Efficient Multi-User Computation Offloading for Mobile-Edge Cloud Computing

Xu Chen et al.

IEEE-ACM TRANSACTIONS ON NETWORKING (2016)

添加到收藏夹

Article Engineering, Electrical & Electronic

DREAM: Dynamic Resource and Task Allocation for Energy Minimization in Mobile Cloud Systems

Jeongho Kwak et al.

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS (2015)

添加到收藏夹

Article Computer Science, Hardware & Architecture

Exploiting Social Ties for Cooperative D2D Communications: A Mobile Social Networking Case

Xu Chen et al.

IEEE-ACM TRANSACTIONS ON NETWORKING (2015)

添加到收藏夹

Article Computer Science, Theory & Methods

Reliable workflow scheduling with less resource redundancy

Laiping Zhao et al.

PARALLEL COMPUTING (2013)

添加到收藏夹

Article Computer Science, Hardware & Architecture

A Large-Scale Study of Failures in High-Performance Computing Systems

Bianca Schroeder et al.

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING (2010)

添加到收藏夹

Article Computer Science, Information Systems

Impact of human mobility on opportunistic forwarding algorithms

Augustin Chaintreau et al.

IEEE TRANSACTIONS ON MOBILE COMPUTING (2007)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.