A5057445936- Cloud Computing and Resource Management
- IoT and Edge/Fog Computing
- Distributed and Parallel Computing Systems
- Multimedia Communication and Technology
- Data Mining Algorithms and Applications
- Complex Network Analysis Techniques
- Peer-to-Peer Network Technologies
- Caching and Content Delivery
- Big Data and Business Intelligence
- Topic Modeling
- Age of Information Optimization
- Opinion Dynamics and Social Influence
- Recommender Systems and Techniques
- Software-Defined Networks and 5G
- Advanced Text Analysis Techniques
- Image Retrieval and Classification Techniques
- Rough Sets and Fuzzy Logic
Xidian University
2019-2023
Human Computer Interaction (Switzerland)
2021
Dalian University of Technology
2014
Harbin Institute of Technology
2007
Virtual machine migration and consolidation technologies can reduce the number of active physical machines (PMs) in cloud platform, which effectively power consumption platform. However, virtual (VMs) requires a suitable time to perform. When VMs' are not performed, how minimize platform through task scheduling is still one major challenge. Existing methods mainly aimed at load balancing or minimizing execution time, without considering optimization heterogeneous server cluster during...
As social networks play an increasingly important role in people's lives, people are more likely to discuss hot topics on networks. Predicting the spread of topics, known as topic propagation prediction is task. Due unpredictability users and networks, predicting trend still a major challenge. Different different roles propagation. However, existing studies have not utilized user analysis. In this paper, we propose method (TPP) based analysis dynamic probability model. First, describe our...
High energy consumption has become a major problem of cloud platform. Most the current task scheduling methods neglect heterogeneity platform, which may consume more power heterogeneous In this paper, we propose power-aware strategy (PASS) for multiple DAGs workflow in with goal minimizing consumption. First, predict PM considering VM status after tasks, and then formulate as NP-hard problem, tries to minimize Second, algorithm solve formulated problem. We consider combination coarse-grained...
Given the problems of high energy consumption and unreasonable resource utilization in current heterogeneous cloud computing platforms, this paper proposes an energy-efficient task scheduling strategy. First, by analyzing relationship between physical machines rate CPU-GPU resources, we can establish model model. Second, a method HCGTS (Heterogeneous Task Scheduling) for optimization platform is proposed. Different from traditional subtasks, divide multi-task data flows into CPU tasks, GPU...
According to the problems that current computer lab resource utilization is low, large maintenance workload, update cost high Etc. In this paper, application of cloud computing and virtualization technology, a model laboratory construction based on virtual machine technology are given, good results obtained through practical application.In recent years, in our country has achieved great development, Nearly all colleges Universities have built many labs. However, these completed labs,...
With the development of cloud computing, energy consumption is getting bigger and bigger, optimization has become one research focuses. Task scheduling an efficient way to reduce cloud. Most previous works ignored heterogeneity physical machines (PMs) configured with different CPUs GPUs, which may result in high heterogeneous In this paper, energy-efficient Scheduling Strategy based on Improved Fireworks Algorithm (TSS-IFWA) proposed CPU/GPU First, a task model constructed, GPUs are...
Semi-online task scheduling in the edge computing platform refers to a scenario where there exists unknown performance nodes system. Existing online and offline methods may lead long makespan or transmission time due influence of nodes, existing semi-online are not fully applicable discussed this paper, which aggravates problem high energy consumption plat-form. To solve problem, paper proposes Mapping-based Dynamic Scheduling(MDSS) strategy for platform. Firstly, we consider three main...
This paper explores the relation between genetic algorithm and network data, so as to summarize advantages disadvantages of this information search technology. Besides, a brief discussion is given new tendency China’s computer market.