Edge Intelligence: A Computational Task Offloading Scheme for Dependent IoT Application

Xiao, Han; Xu, Changqiao; Ma, Yunxiao; Yang, Shujie; Zhong, Lujie; Muntean, Gabriel‐Miro

doi:10.1109/twc.2022.3156905

Cited by 74 publications

(38 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Swarup et al 29 focused on the task scheduling problem of cloud‐based applications and proposed a clipped double deep Q‐ learning algorithm which is applied target network and experience replay techniques. Xiao et al 30 proposed an intelligent task offloading scheme called Computational Offloading scheme for Dependent IoT Application and leveraged an Actor–Critic‐based algorithm to achieve low latency and high efficiency. Cui et al 31 proposed a DRL‐based task offloading algorithm name LSTM‐TD3 (a deep reinforcement learning based task offloading algorithm which incorporates the long short‐term memory [LSTM] and twin delayed deep deterministic policy gradient algorithm [TD3]) to solve the formulated problem.…”

Section: Background and Related Workmentioning

confidence: 99%

DDDQN‐TS: A task scheduling and load balancing method based on optimized deep reinforcement learning in heterogeneous computing environment

Sun

Yang

Lei

2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Task scheduling and load balancing problem of heterogeneous computing environment (HCE) is getting more and more attention these days and has become a research hotspot in this field. The task scheduling and load balancing problem of heterogeneous environment, which refers to assigning a set of tasks to a specific set of machines with different hardware and different computing performance with the goal of minimizing task processing time and keeping load balance among machines, has been proved to be an NP-complete problem. The development of artificial intelligence provides new ideas to solve this problem. In this paper, we propose a novel task scheduling and load balancing method based on optimized deep reinforcement learning in HCE. First, we formulate task scheduling problem as a Markov decision process and then adopt a dueling double deep Q-learning network to search the optimal task allocation solution. Then we use two well-known large-scale cluster data sets Google Cloud Jobs data set and Alibaba Cluster Trace data set to validate our approach. The experimental results show that compared with other existing solutions, our proposed method can achieve much shorter task response time and better load balancing effect.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

DDDQN‐TS: A task scheduling and load balancing method based on optimized deep reinforcement learning in heterogeneous computing environment

Sun

Yang

Lei

2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

show abstract

“…In addition, Zhang et al 43 used integer linear programming to optimize the memory footprint. Xiao et al 44 proposed an application‐level offloading model and multi‐queue priority scheduling algorithm to reduce the latency for IoT applications with edge intelligence.…”

Section: Background and Literature Surveymentioning

confidence: 99%

Memory optimization at Edge for Distributed Convolution Neural Network

Naveen

Kounte

2022

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Internet of Things (IoT) edge intelligence has emerged by optimizing the deep learning (DL) models deployed on resource‐constraint devices for quick decision‐making. In addition, edge intelligence reduces network overload and latency by bringing intelligent analytics closer to the source. On the other hand, DL models need a lot of computing resources. As a result, they have high computational workloads and memory footprint, making it impractical to deploy and execute on IoT edge devices with limited capabilities. In addition, existing layer‐based partitioning methods generate many intermediate results, resulting in a huge memory footprint. In this article, we propose a framework to provide a comprehensive solution that enables the deployment of convolutional neural networks (CNNs) onto distributed IoT devices for faster inference and reduced memory footprint. This framework considers a pretrained YOLOv2 model, and a weight pruning technique is applied to the pre‐trained model to reduce the number of non‐contributing parameters. We use the fused layer partitioning method to vertically partition the fused layers of the CNN and then distribute the partition among the edge devices to process the input. In our experiment, we have considered multiple Raspberry Pi as edge devices. Raspberry Pi with a neural computing stick is a gateway device to combine the results from various edge devices and get the final output. Our proposed model achieved inference latency of 5 to ∼$$ \sim $$7 seconds for 3prefix×3$$ 3\times 3 $$ to 5prefix×5$$ 5\times 5 $$ fused layer partitioning for five devices with a 9% improvement in memory footprint.

show abstract

“…Xiao et al [47] proposed an innovative solution with Edge Intelligence for computational tasks offloading for dependent IoT applications (CODIA) with better robustness and efficiency in terms of convergence, latency and energy consumption. Chen et al [48] proposed a game theoretic approach for the computation offloading decision making problem among multiple mobile device users for mobile-edge cloud computing and also designed a distributed computation offloading algorithm with excellent computation offloading performance.…”

Section: Task Offloadingmentioning

confidence: 99%

Application and Research of IoT Architecture for End-Net-Cloud Edge Computing

Zhang

Zhou

et al. 2022

Electronics

View full text Add to dashboard Cite

At the edge of the network close to the source of the data, edge computing deploys computing, storage and other capabilities to provide intelligent services in close proximity and offers low bandwidth consumption, low latency and high security. It satisfies the requirements of transmission bandwidth, real-time and security for Internet of Things (IoT) application scenarios. Based on the IoT architecture, an IoT edge computing (EC-IoT) reference architecture is proposed, which contained three layers: The end edge, the network edge and the cloud edge. Furthermore, the key technologies of the application of artificial intelligence (AI) technology in the EC-IoT reference architecture is analyzed. Platforms for different EC-IoT reference architecture edge locations are classified by comparing IoT edge computing platforms. On the basis of EC-IoT reference architecture, an industrial Internet of Things (IIoT) edge computing solution, an Internet of Vehicles (IoV) edge computing architecture and a reference architecture of the IoT edge gateway-based smart home are proposed. Finally, the trends and challenges of EC-IoT are examined, and the EC-IoT architecture will have very promising applications.

show abstract

Edge Intelligence: A Computational Task Offloading Scheme for Dependent IoT Application

Cited by 74 publications

References 54 publications

DDDQN‐TS: A task scheduling and load balancing method based on optimized deep reinforcement learning in heterogeneous computing environment

DDDQN‐TS: A task scheduling and load balancing method based on optimized deep reinforcement learning in heterogeneous computing environment

Memory optimization at Edge for Distributed Convolution Neural Network

Application and Research of IoT Architecture for End-Net-Cloud Edge Computing

Contact Info

Product

Resources

About