☆ 4.7 Article

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

IEEE TRANSACTIONS ON MOBILE COMPUTING (2023)

Related references

Note: Only part of the references are listed.

Article Computer Science, Theory & Methods

Maximizing User Service Satisfaction for Delay-Sensitive IoT Applications in Edge Computing

Jing Li et al.

Summary: The Internet of Things technology has the potential to enhance interconnection among human beings, but the challenges of unstable wireless networks and limited resources on IoT devices hinder efficient user experience. This paper proposes the integration of Mobile Edge Computing with remote clouds as a promising platform to provide delay-sensitive service provisioning for IoT applications. The paper presents novel optimization problems and efficient algorithms to address these issues.

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS (2022)

Add to Collection

Article Computer Science, Information Systems

A Near-Optimal Approach for Online Task Offloading and Resource Allocation in Edge-Cloud Orchestrated Computing

Tong Liu et al.

Summary: In this paper, an online task offloading and resource allocation approach is proposed for edge-cloud orchestrated computing. By leveraging the cooperation between edge computing and cloud computing, the approach aims to reduce the latency of computation tasks and minimize the average latency over time. The approach decomposes the problem into subproblems using Lyapunov optimization and duality theory, and can achieve near-optimal performance.

IEEE TRANSACTIONS ON MOBILE COMPUTING (2022)

Add to Collection

Article Computer Science, Information Systems

Mobility-Aware and Delay-Sensitive Service Provisioning in Mobile Edge-Cloud Networks

Yu Ma et al.

Summary: Mobile edge computing (MEC) is a promising technology that brings cloud services to the network edge, providing network services for mobile users. Virtualized network services improve user experience and simplify network service deployment and resource management. However, providing reliable and seamless virtualized network services for mobile users in an MEC network is a challenging task.

IEEE TRANSACTIONS ON MOBILE COMPUTING (2022)

Add to Collection

Article Computer Science, Information Systems

Multi-Objective Computation Sharing in Energy and Delay Constrained Mobile Edge Computing Environments

Arash Bozorgchenani et al.

Summary: In a mobile edge computing network, mobile devices offload computations to edge servers for reduced transmission delays. Task offloading is optimized to minimize energy consumption and processing delays, a challenge addressed through a constrained multi-objective optimization problem that is solved using an evolutionary algorithm to find the best trade-offs between energy consumption and task processing delay.

IEEE TRANSACTIONS ON MOBILE COMPUTING (2021)

Add to Collection

Article Computer Science, Theory & Methods

Energy-Aware Inference Offloading for DNN-Driven Applications in Mobile Edge Clouds

Zichuan Xu et al.

Summary: With the increasing focus on AI applications, DNNs have been successfully used in various areas, requiring significant computational resources. The advancement in 5G and mobile edge computing provides new possibilities for DNN-driven AI applications.

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS (2021)

Add to Collection

Article Computer Science, Hardware & Architecture

CoEdge: Cooperative DNN Inference With Adaptive Workload Partitioning Over Heterogeneous Edge Devices

Liekang Zeng et al.

Summary: Recent advances in artificial intelligence have led to the growth of intelligent applications at the network edge. To deploy computationally intensive Deep Neural Networks (DNNs) on resource-constrained edge devices, the cooperative execution mechanism offers a new paradigm for achieving high-performance edge intelligence.

IEEE-ACM TRANSACTIONS ON NETWORKING (2021)

Add to Collection

Article Computer Science, Information Systems

Joint Multiuser DNN Partitioning and Computational Resource Allocation for Collaborative Edge Intelligence

Xin Tang et al.

Summary: Mobile-edge computing (MEC) serves as a promising architecture supporting edge intelligence services by providing resources to the network edge. Optimizing DNN partitioning and resource allocation in a multiuser resource-constrained environment is a key research area.

IEEE INTERNET OF THINGS JOURNAL (2021)

Add to Collection

Proceedings Paper Computer Science, Hardware & Architecture

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

Jing Li et al.

Summary: Mobile Edge Computing (MEC) is a promising paradigm that offloads compute-intensive tasks to MEC networks, while edge intelligence accelerates DNN inference through partitioning and multi-threading. This study presents a novel approach to maximize DNN service requests by exploring DNN model partitioning and multi-thread parallelism, showing the problem is NP-hard and proposing a constant approximation algorithm with promising experimental results.

PROCEEDINGS OF THE IEEE 46TH CONFERENCE ON LOCAL COMPUTER NETWORKS (LCN 2021) (2021)

Add to Collection

Article Computer Science, Theory & Methods

Reliability-Aware Network Service Provisioning in Mobile Edge-Cloud Networks

Jing Li et al.

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS (2020)

Add to Collection

Proceedings Paper Computer Science, Hardware & Architecture

Distributed Inference Acceleration with Adaptive DNN Partitioning and Offloading

Thaha Mohammed et al.

IEEE INFOCOM 2020 - IEEE CONFERENCE ON COMPUTER COMMUNICATIONS (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing

Zhi Zhou et al.

PROCEEDINGS OF THE IEEE (2019)

Add to Collection

Proceedings Paper Computer Science, Information Systems

Pipelined Data-Parallel CPU/GPU Scheduling for Multi-DNN Real-Time Inference

Yecheng Xiang et al.

2019 IEEE 40TH REAL-TIME SYSTEMS SYMPOSIUM (RTSS 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Hardware & Architecture

Dynamic Adaptive DNN Surgery for Inference Acceleration on the Edge

Chuang Hu et al.

IEEE CONFERENCE ON COMPUTER COMMUNICATIONS (IEEE INFOCOM 2019) (2019)

Add to Collection

Article Engineering, Electrical & Electronic

EMM: Energy-Aware Mobility Management for Mobile Edge Computing in Ultra Dense Networks

Yuxuan Sun et al.

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS (2017)

Add to Collection

Proceedings Paper Computer Science, Software Engineering

Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge

Yiping Kang et al.

ACM SIGPLAN NOTICES (2017)

Add to Collection

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)

Add to Collection

Article Computer Science, Information Systems

An efficient approximation for the Generalized Assignment Problem

Reuven Cohen et al.

INFORMATION PROCESSING LETTERS (2006)

Add to Collection

Article Computer Science, Artificial Intelligence

An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision

Y Boykov et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2004)

Add to Collection

© Peeref 2019-2024. All rights reserved.