Journal Article10.1145/3548687
Deep Q Network–Driven Task Offloading for Efficient Multimedia Data Analysis in Edge Computing–Assisted IoV
31
TL;DR: An optimized Fuzzy C-means algorithm is employed to cluster vehicles and other edge devices according to their respective service quality requirements and a task offloading algorithm based on Deep Q-Network (DQN) is proposed to acquire an optimal task offload scheme.
read more
Abstract: With the prosperity of Industry 4.0, numerous emerging industries continue to gain popularity and their market scales are expanding ceaselessly. The Internet of Vehicles (IoV), one of the thriving intelligent industries, enjoys bright development prospects. However, at the same time, the reliability and availability of IoV applications are confronted with two major bottlenecks of time delay and energy consumption. To make matters worse, massive heterogeneous and multi-dimensional multimedia data generated on the IoV present a huge obstacle to effective data analysis. Fortunately, the advent of edge computing technology enables tasks to be offloaded to edge servers, which significantly reduces total overhead of IoV systems. Deep reinforcement learning (DRL), equipped with its excellent perception and decision-making capability, is undoubtedly a dominant technology to solve task offloading problems. In this article, we first employ an optimized Fuzzy C-means algorithm to cluster vehicles and other edge devices according to their respective service quality requirements. Then, we employ an election algorithm to assist in maintaining the stability of the IoV. Last, we propose a task-offloading algorithm based on the Deep Q Network (DQN) to acquire an optimal task offloading scheme. Massive simulation experiments demonstrate the superiority of our method in minimizing time delay and energy consumption.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A distributed game theoretical approach for credibility-guaranteed multimedia data offloading in MEC
TL;DR: In this article , a game-based credible data offloading (GCDO) method was proposed to obtain the Nash equilibrium offloading strategy in a distributed way, and the proposed GCDO method was compared with various approximation methods, and a series of experimental results were given.
19
Cooperative Spectrum Sensing Deployment for Cognitive Radio Networks for Internet of Things 5G Wireless Communication
Thulasiraman Balachander,Kadiyala Ramana,R. Mohana,Gautam Srivastava,Thippa Reddy Gadekallu +4 more
TL;DR: This paper proposes an optimal Cooperative Spectrum Sensing (CSS) deployment for Cognitive Radio Networks (CRN) in 5G IoT wireless communication, utilizing OQAM/UFMC/NOMA methodologies, to improve bandwidth utilization, latency, SNR, and capacity while reducing PAPR and enhancing QoS.
14
CSI-Former: Pay More Attention to Pose Estimation with WiFi
TL;DR: In this paper , the authors proposed a CSI-former architecture to integrate the multi-head attention in the WiFi-based pose estimation network, which can significantly improve the performance in wireless pose estimation.
Customer Centric Service Caching for Intelligent Cyber-Physical Transportation Systems with Cloud-Edge Computing Leveraging Digital Twins
Hanzhi Yan,Xiaolong Xu,Muhammad Bilal,Xiaoyu Xia,Wanchun Dou,Huihui Wang +5 more
TL;DR: This study proposes SFT-SCAR, a digital twin-based service caching framework for Intelligent Cyber-Physical Transportation Systems, leveraging graph attention networks and asynchronous advantage actor-critic algorithms to improve hit rates by 1.11%-13.27%.
10
Digital Twin-Assisted Edge Service Caching for Consumer Electronics Manufacturing
Wei Liu,Xiaolong Xu,Lianyong Qi,Xiaokang Zhou,Hanzhi Yan,Xiaoyu Xia,Wanchun Dou +6 more
TL;DR: This paper proposes a digital twin-assisted edge service caching scheme, SCRD, using deep reinforcement learning to optimize caching strategy for IoT devices in consumer electronics manufacturing, outperforming baseline schemes in experimental results.
10
References
•Posted Content
Playing Atari with Deep Reinforcement Learning
Volodymyr Mnih,Koray Kavukcuoglu,David Silver,Alex Graves,Ioannis Antonoglou,Daan Wierstra,Martin Riedmiller +6 more
TL;DR: This work presents the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning, which outperforms all previous approaches on six of the games and surpasses a human expert on three of them.
Deep reinforcement learning with double Q-learning
H Van Hasselt,Arthur Guez,David Silver +2 more
- 01 Jan 2015
TL;DR: In this article, the authors show that the DQN algorithm suffers from substantial overestimation in some games in the Atari 2600 domain, and they propose a specific adaptation to the algorithm and show that this algorithm not only reduces the observed overestimations, but also leads to much better performance on several games.
7.9K
Edge Computing: Vision and Challenges
TL;DR: The definition of edge computing is introduced, followed by several case studies, ranging from cloud offloading to smart home and city, as well as collaborative edge to materialize the concept of edge Computing.
7.1K
FCM: The fuzzy c-means clustering algorithm
TL;DR: A FORTRAN-IV coding of the fuzzy c -means (FCM) clustering program is transmitted, which generates fuzzy partitions and prototypes for any set of numerical data.
6.4K
The expected contribution of Industry 4.0 technologies for industrial performance
Lucas Santos Dalenogare,Guilherme Brittes Benitez,Néstor Fabián Ayala,Alejandro Germán Frank +3 more
TL;DR: In this article, the authors studied how the adoption of different Industry 4.0 technologies is associated with expected benefits for product, operations and side-effects aspects in the Brazilian industry.
1.7K