A5018646081- IoT and Edge/Fog Computing
- Metallurgical Processes and Thermodynamics
- Cloud Computing and Resource Management
- Metallurgy and Material Forming
- Caching and Content Delivery
- Age of Information Optimization
- Bauxite Residue and Utilization
- Metal Extraction and Bioleaching
- Mechanical stress and fatigue analysis
- Extraction and Separation Processes
- Powder Metallurgy Techniques and Materials
- Privacy-Preserving Technologies in Data
- Molten salt chemistry and electrochemical processes
- Electronic Packaging and Soldering Technologies
- Metal Forming Simulation Techniques
- Molecular Communication and Nanonetworks
- Metal and Thin Film Mechanics
- Structural Engineering and Vibration Analysis
- High-Temperature Coating Behaviors
- Retinal Imaging and Analysis
- Metal Alloys Wear and Properties
- Opportunistic and Delay-Tolerant Networks
- Cloud Data Security Solutions
- IoT Networks and Protocols
- Iron and Steelmaking Processes
Central South University
2007-2024
Hunan University
2023
Nanchang Institute of Technology
2023
China National Offshore Oil Corporation (China)
2015
Horological Research Institute of Light Industry
2014
Beijing Research Institute of Mechanical and Electrical Technology
2011
South China University of Technology
2008
Zhongyuan University of Technology
2005
With the large-scale deployment of cloud datacenters, high energy consumption and serious service level agreement (SLA) violations in datacenters have become an increasingly urgent problem to be addressed. Implementing effective virtual machine (VM) consolidation methods is great significance reduce SLA violations. The VM a well-known NP-hard problem. Meanwhile, efficient should consider multiple factors synthetically, including quality service, consumption, migration overhead, which...
Collaborative cloud-edge-end computing is a promising solution to support computation-intensive and latency-sensitive tasks by utilizing rich resources of cloud datacenters low access delay mobile edge (MEC) servers. Compared with traditional MEC, the cloud-edge environment has stronger heterogeneity servers networks, resulting in significant differences between computation speed delay. However, few studies on task offloading focused characteristic 5G heterogeneous networks environment. In...
The use of flying platforms such as unmanned aerial vehicles (UAVs), popularly known drones, is rapidly growing. UAVs can greatly support data collecting and processing for Internet Things devices (IoTDs) in mobile edge computing (MEC) systems due to their advantages high environmental flexibility. This paper focuses on the scenario where multiple heterogeneous rotary-wing complete collection missions cooperatively. introduces an energy minimization problem UAV-assisted MEC system which...
Abstract Mobility is a fundamental feature of mobile edge computing. Due to the mobility users, contextual attributes cloudlets such as server resources and network state will dynamically change with time during offloading, showing time-varying fuzzy characteristics. To this end, how make efficient offloading decision provide low-latency, low-power highly reliable services in MEC has become critical issue. In paper, we propose context-aware cloudlet algorithm based on neutrosophic set,...
In recent years, since edge computing has improved the performance of transportation systems, research on edge-computing-enabled systems received widespread attention. However, most previous studies overlooked that task requests in are unevenly distributed time and space, which easily causes overloading servers, resulting high response latency. To this end, we present a novel offloading scheme based graph neural network (GNN) deep reinforcement learning (DRL) (TransEdge). Specifically, first...
Recently, the Industrial Internet of Things (IIoT) has shown great application value in environmental monitoring. However, it suffers from serious bottlenecks energy and computing capability. To address them, researchers have made lots effort. Nevertheless, they neglect either edge–end collaboration or impact task queue backlog, resulting low system revenue. this end, we design a queue-aware computation offloading method based on DRL (QDRL). Specifically, represent long-term operation as...
End fitting is one of the most important equipment flexible pipe with function terminating all layers, sealing and venting gas. Seal system weakest component end which easy to fail under functional environmental load. This paper addresses seal performance used in deep waters. The finite element model for established software ABAQUS perform parameter sensitivity analysis on different parameters nonlinear contact analysis. rules mechanical performances key conditions are studied. technique...
The optimization of caching mechanisms has long been a crucial research focus in cloud–edge collaborative environments. Effective strategies can substantially enhance user experience quality these settings. Deep reinforcement learning (DRL), with its ability to perceive the environment and develop intelligent policies online, widely employed for designing strategies. Recently, federated learning, when combined DRL, gaining popularity optimizing protecting data training privacy from...
Abstract Residential side flexible load participation in demand response (DR) has been widely used recent years. However, there are uncertainties the willingness and volume of residential customers, which have a non‐negligible impact on security economic dispatch power sector. This paper analyzes uncertainty factors process users from equipment layer–user layer, establishes for first time refined model users' DR perspectives uncertainty, further constructs grid optimal considering...
Replication technology is a very important data management in cloud storage. Traditional replication control methods cannot usefully solve the load imbalance caused by hotspot access. This paper proposed dynamic algorithm based on access popularity called APDRA. Replicas were created and deleted dynamically according to of data, situation system nodes, effectively solving problem local overload hot spot recovery idle replicas. In end, superiority APDRA was verified experiment.
With the number of connected devices increasing rapidly, access latency issue increases drastically in edge cloud environment. Massive low time-constrained and data-intensive mobile applications require efficient replication strategies to decrease retrieval time. However, determination replicas is not reasonable many previous works, which incurs high response delay. To this end, a correlation-aware replica prefetching (CRP) strategy based on file correlation principle proposed, can prefetch...