Service Function Chaining in Industrial Internet of Things With Edge Intelligence: A Natural Actor-Critic Approach

Li, Junhuai; Wang, Ruijie; Wang, Kan

doi:10.1109/tii.2022.3177415

Cited by 25 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The purpose of the virtual link is to request transmission bandwidth from the base link. Therefore, for the virtual link l f ∈ L f , the requested resource occupation applied for is [23] point out that the SFC for achieving complete wireless access functionality for the industrial Internet of things should include a wireless access node WAP f and industrial Internet of things equipment I IE f , as shown in Figure 1. In this paper, we assume that all UAV nodes have wireless access functions to enable random access of Internet of things equipment.…”

Section: Service Function Chain Modelmentioning

confidence: 99%

“…Our particle swarm optimization algorithm uses the parameters that satisfy this condition to ensure the stability of convergence. Although the parameter selection conditions that make the algorithm in this paper converge can be analyzed from the above content, an important decision of whether the particle swarm converges still depends on the fitness function with Equation (23). The fitness function determines the movement direction of the particle and affects the process of particle searching for the optimal solution, while the design of learning factors and weights ensures the asymptotic stability of the particle adjustment process.…”

Section: Analysis Of Convergence Of Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Research on Service Function Chain Embedding and Migration Algorithm for UAV IoT

Wang,

Shi,

2024

Drones

View full text Add to dashboard Cite

This paper addresses the challenge of managing service function chaining (SFC) in an unmanned aerial vehicle (UAV) IoT, a dynamic network that integrates UAVs and IoT devices for various scenarios. To enhance the service quality and user experience of the UAV IoT, network functions must be flexibly configured and adjusted based on varying service demands and network situations. This paper presents a model for calculating benefits and an agile algorithm for embedding and migrating SFC based on particle swarm optimization (PSO). The model takes into account multiple factors such as SFC quality, resource utilization, and migration cost. It aims to maximize the SFC benefit and minimize the migration times. The algorithm leverages PSO’s global search and fast convergence to identify the optimal or near-optimal SFC placement and update it when the network state changes. Simulation experiments demonstrate that the proposed method improves network resource efficiency and outperforms existing methods. This paper presents a new idea and method for managing SFC in UAV IoT.

show abstract

Section: Service Function Chain Modelmentioning

confidence: 99%

Section: Analysis Of Convergence Of Algorithmmentioning

confidence: 99%

Research on Service Function Chain Embedding and Migration Algorithm for UAV IoT

Wang,

Shi,

2024

Drones

View full text Add to dashboard Cite

show abstract

“…The traditional LEO satellite network is usually limited by the finite onboard capacity. Fortunately, emerging mobile edge computing (MEC) can provide services with low latency, high reliability, high security, and high flexibility by deploying computing and storage resources closer to users [ 20 , 21 , 22 ]. Assisted by the MEC, LEO satellite edge networks are expected to deploy MEC servers on satellites and cooperate with cloud computing data centers to further reduce energy consumption and task response latency, forming an end-edge-cloud multi-level processing architecture for different business types.…”

Section: Introductionmentioning

confidence: 99%

Computation Offloading and Resource Allocation Based on P-DQN in LEO Satellite Edge Networks

Yang,

Fang,

Gao

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Traditional low earth orbit (LEO) satellite networks are typically independent of terrestrial networks, which develop relatively slowly due to the on-board capacity limitation. By integrating emerging mobile edge computing (MEC) with LEO satellite networks to form the business-oriented “end-edge-cloud” multi-level computing architecture, some computing-sensitive tasks can be offloaded by ground terminals to satellites, thereby satisfying more tasks in the network. How to make computation offloading and resource allocation decisions in LEO satellite edge networks, nevertheless, indeed poses challenges in tracking network dynamics and handling sophisticated actions. For the discrete-continuous hybrid action space and time-varying networks, this work aims to use the parameterized deep Q-network (P-DQN) for the joint computation offloading and resource allocation. First, the characteristics of time-varying channels are modeled, and then both communication and computation models under three different offloading decisions are constructed. Second, the constraints on task offloading decisions, on remaining available computing resources, and on the power control of LEO satellites as well as the cloud server are formulated, followed by the maximization problem of satisfied task number over the long run. Third, using the parameterized action Markov decision process (PAMDP) and P-DQN, the joint computing offloading, resource allocation, and power control are made in real time, to accommodate dynamics in LEO satellite edge networks and dispose of the discrete-continuous hybrid action space. Simulation results show that the proposed P-DQN method could approach the optimal control, and outperforms other reinforcement learning (RL) methods for merely either discrete or continuous action space, in terms of the long-term rate of satisfied tasks.

show abstract

“…The merging of Internet of Things (IoTs) with industrial manufacturing, i.e., industrial IoTs (IIoTs), has drawn great interest from both academia and industry, especially in the data collection from IIoT devices [1,2]. Among the rich industrial IoT applications, the ultra high-definition video surveillance in the field deserves special attention due to its advantages in better understanding the field operation and alerting for possible failures.…”

Section: Introductionmentioning

confidence: 99%

Edge Intelligence-Assisted Asymmetrical Network Control and Video Decoding in the Industrial IoT with Speculative Parallelization

Yang,

Zhang,

Xia

et al. 2023

Symmetry

View full text Add to dashboard Cite

Industrial Internet of Things (IIoTs) has drawn significant attention in the industry. Among its rich applications, the field’s video surveillance deserves particular interest due to its advantage in better understanding network control. However, existing decoding methods are limited by the video coding order, which cannot be decoded in parallel, resulting in low decoding efficiency and the inability to process the massive amount of video data in real time. In this work, a parallel decoding framework based on the speculative technique is proposed. In particular, the video is first speculatively decomposed into data blocks, and then a verification method is designed to ensure the correctness of the decomposition. After verification, the data blocks having passed the validation can be decoded concurrently in the parallel computing platform. Finally, the concurrent decoding results are concatenated in line with the original encoding order to form the output. Experiments show that compared with traditional serial decoding ones, the proposed method can improve the performance by 9 times on average in the parallel computing environment with NVIDIA Tegra 4 chips, thus significantly enhancing the real-time video data’s decoding efficiency with guaranteed accuracy. Furthermore, proposed and traditional serial methods obtain almost the same peak signal-to-noise ratio (PSNR) and mean square error (MSE) metrics at different bit rates and resolutions, showing that the introduction of the speculative technique does not degrade the decoding accuracy.

show abstract

Service Function Chaining in Industrial Internet of Things With Edge Intelligence: A Natural Actor-Critic Approach

Cited by 25 publications

References 34 publications

Research on Service Function Chain Embedding and Migration Algorithm for UAV IoT

Research on Service Function Chain Embedding and Migration Algorithm for UAV IoT

Computation Offloading and Resource Allocation Based on P-DQN in LEO Satellite Edge Networks

Edge Intelligence-Assisted Asymmetrical Network Control and Video Decoding in the Industrial IoT with Speculative Parallelization

Contact Info

Product

Resources

About