Research Article
Coordinated Placement of Meteorological Workflows and Data with Privacy Conflict Protection
@INPROCEEDINGS{10.1007/978-3-030-48513-9_44, author={Tao Huang and Shengjun Xue and Yumei Hu and Qing Yang and Yachong Tian and Dan Zeng}, title={Coordinated Placement of Meteorological Workflows and Data with Privacy Conflict Protection}, proceedings={Cloud Computing, Smart Grid and Innovative Frontiers in Telecommunications. 9th EAI International Conference, CloudComp 2019, and 4th EAI International Conference, SmartGIFT 2019, Beijing, China, December 4-5, 2019, and December 21-22, 2019}, proceedings_a={CLOUDCOMP}, year={2020}, month={6}, keywords={Meteorological Coordinated placement NSDE Data access time Resource utilization Data conflict}, doi={10.1007/978-3-030-48513-9_44} }- Tao Huang
Shengjun Xue
Yumei Hu
Qing Yang
Yachong Tian
Dan Zeng
Year: 2020
Coordinated Placement of Meteorological Workflows and Data with Privacy Conflict Protection
CLOUDCOMP
Springer
DOI: 10.1007/978-3-030-48513-9_44
Abstract
Cloud computing is cited by various industries for its powerful computing power to solve complex calculations in the industry. The massive data of meteorological department has typical big data characteristics. Therefore, cloud computing has been gradually applied to deal with a large number of meteorological -services. Cloud computing increases the computational speed of meteorological services, but data transmission between nodes also generates additional data transmission time. At the same time, based on cloud computing technology, a large number of computing tasks are cooperatively processed by multiple nodes, so improving the resource utilization of each node is also an important evaluation indicator. In addition, with the increase of data confidentiality, there are some data conflicts between some data, so the conflicting data should be avoided being placed on the same node. To cope with this challenge, the meteorological application is modeled and a collaborative placement method for tasks and data based on Differential Evolution algorithm (CPDE) is proposed. The Non-dominated Sorting Differential Evolution (NSDE) algorithm is used to jointly optimize the average data access time, the average resource utilization of nodes and the data conflict degree. Finally, a large number of experimental evaluations and comparative analyses verify the efficiency of our proposed CPDE method.
