Search

Your search keyword '"Zhang, Geng"' showing total 109 results
Start Over Author "Zhang, Geng" Publisher ieee
109 results on '"Zhang, Geng"'

24. Blockchain and Federated Deep Reinforcement Learning Based Secure Cloud-Edge-End Collaboration in Power IoT.

Author

Zhang, Sunxuan, Wang, Zhao, Zhou, Zhenyu, Wang, Yang, Zhang, Hui, Zhang, Geng, Ding, Huixia, Mumtaz, Shahid, and Guizani, Mohsen

Abstract

Cloud-edge-end collaboration enables harmonious and efficient resource allocation for the Power Internet of Things (PIoT). However, the security and complexity issues of computation offloading evolve into the main obstacles. In this article, we first propose a blockchain and AI-based secure cloud-edge-end collaboration PIoT (BASE-PIoT) architecture to ensure data security and intelligent computation offloading. Its advantages in flexible resource allocation, secure data sharing, and differentiated service guarantee are elaborated. Then the adaptability of three typical blockchains with PIoT is analyzed, and some typical application scenes of BASE-PIoT including computation offloading, energy scheduling, and access authentication are illustrated. Finally, we propose a blockchain-empowered federated deep actor-critic-based task offloading algorithm to address the secure and low-latency computation offloading problem. The coupling between the long-term security constraint and short-term queuing delay optimization is decoupled by using Lyapunov optimization. Numerical results verify its excellent performance in total queuing delay and consensus delay. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

31. AI-Based Cloud-Edge-Device Collaboration in 6G Space-Air-Ground Integrated Power IoT.

Author

Wang, Zhao, Zhou, Zhenyu, Zhang, Hui, Zhang, Geng, Ding, Huixia, and Farouk, Ahmed

Abstract

Space-air-ground integrated communication networks and artificial intelligence (AI) play critical roles in future 6G wireless communication. The Power Internet of Things (PIoT) assisted by the space-air-ground integrated communication network, that is, space-air-ground integrated PIoT (SAG-PIoT), has emerged as a promising solution to provide seamless communication and computing services for PIoT devices with stringent QoS requirements. Cloud-edge-device collaboration is leveraged to enable intelligent resource management in SAG-PIoT. This article proposes an AI-based cloud-edge-device collaboration framework for SAG-PIoT to cope with multi-dimensional resource heterogeneity and network dynamics. Specifically, the SAG-PIoT application scenarios and research challenges are first introduced. Then we develop a hybrid and hierarchical cloud-edge-device collaboration architecture to adapt with different scenarios and domains, followed by the detailed implementation procedures. Next, a queue-aware deep actor-critic (Q-DAC)-based task offloading algorithm is proposed to facilitate decision making optimization under incomplete information. A case study is provided to validate the energy consumption and end-to-end queuing delay performance of Q-DAC. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

40. The Drivers' Individual Behavior Difference in Car-Following Model

Author

Zhang Geng, Zhou Tong, and Li Yuxuan

Subjects
Computer simulation, Mathematical analysis, Jamming, Linear analysis, Traffic flow, 01 natural sciences, Stability (probability), Car following, Critical point (mathematics), 010305 fluids & plasmas, Nonlinear system, 0103 physical sciences, 010306 general physics, Simulation, Mathematics
Abstract

Based on the full velocity difference car-following model, an extended car-following model is presented by considering drivers' timid or aggressive behavior. Applying linear analysis theory, the stability condition of the traffic flow is obtained. Through the nonlinear reductive perturbation method, the mKdV equation is derived to describe the propagating behavior of traffic density waves near the critical point. The good agreement between the numerical simulation and the analytical results shows that drivers' individual behavior difference play an important role in traffic jamming transition.

Published
2016

50. An improved cluster analysis algorithm using for network traffic flow

Author

Zhang Ran, Zhang Geng, Sun Zhen-Chao, Sun Yong, and Liu Shi-dong

Subjects
Training set, business.industry, Computer science, Reliability (computer networking), Correlation clustering, k-means clustering, computer.software_genre, Machine learning, Support vector machine, Traffic flow (computer networking), ComputingMethodologies_PATTERNRECOGNITION, Binary classification, Canopy clustering algorithm, Artificial intelligence, Data mining, business, Cluster analysis, Algorithm, computer
Abstract

With the rapid development of computer network and the network application, network has plays an increasingly important role in the social progress and economic development. Rapid development of information technology makes the network traffic behavior has become increasingly complex, and the reliability of the network becomes crucial. Cluster algorithm using for network traffic flow is an entry to analysis network status. Support Vector Machine (SVM) is a machine learning method to solve binary classification problem. An improved cluster analysis algorithm of combining SVM with supervised subset density clustering is proposed in this paper, and minimize the training set of SVM by means of clustering is researched. A supervised self-adaptive method for the improved density clustering is designed to make out multiple centers choosing and referring the samples to SVM. The experimental results show that the algorithm reduces the iteration time of the whole training process without compromising the accuracy and generalization capacity of the algorithm obviously.

Published
2015

Catalog

Books, media, physical & digital resources
See catalog results