TY - GEN
T1 - A cloud computing approach to on-demand and scalable CyberGIS analytics
AU - Riteau, Pierre
AU - Gao, Yizhao
AU - Hwang, Myunghwa
AU - Liu, Yan
AU - Wang, Shaowen
AU - Padmanabhan, Anand
AU - Keahey, Kate
PY - 2014
Y1 - 2014
N2 - Spatial data analysis has become ubiquitous as geographic information systems (GIS) are widely used to support scientific investigations and decision making in many fields of science, engineering, and humanities (e.g., ecology, emergency management, environmental engineering and sciences, geosciences, and social sciences). Tremendous data and computational capabilities are needed to handle and analyze massive quantities of spatial data that are collected across multiple spatiotemporal scales and used for diverse purposes. CyberGIS has emerged as a new-generation GIS based on advanced cyberinfrastructure to seamlessly integrate such capabilities into scalable geospatial analytics and modeling tools. One of the key challenges and opportunities of CyberGIS research is to build an on-demand service framework that can manage underlying cyberinfrastructure resources dynamically, in order to provide responsive support for interactive online CyberGIS analytics for which users can generate massive service requests in a short amount of time. This paper presents a cloud computing approach to implementing CyberGIS analytics using cloud computing services in the CyberGIS Gateway, a multiuser and collaborative online problem-solving environment. The primary purpose of this research is to address the question of how to achieve on-demand and scalable CyberGIS analytics that provide a stable response time to the user. We do that through integration with the Nimbus Phantom cloud platform. We then investigate how the cloud platform is able to adaptively handle fluctuating requests for analytics while providing a stable response time.
AB - Spatial data analysis has become ubiquitous as geographic information systems (GIS) are widely used to support scientific investigations and decision making in many fields of science, engineering, and humanities (e.g., ecology, emergency management, environmental engineering and sciences, geosciences, and social sciences). Tremendous data and computational capabilities are needed to handle and analyze massive quantities of spatial data that are collected across multiple spatiotemporal scales and used for diverse purposes. CyberGIS has emerged as a new-generation GIS based on advanced cyberinfrastructure to seamlessly integrate such capabilities into scalable geospatial analytics and modeling tools. One of the key challenges and opportunities of CyberGIS research is to build an on-demand service framework that can manage underlying cyberinfrastructure resources dynamically, in order to provide responsive support for interactive online CyberGIS analytics for which users can generate massive service requests in a short amount of time. This paper presents a cloud computing approach to implementing CyberGIS analytics using cloud computing services in the CyberGIS Gateway, a multiuser and collaborative online problem-solving environment. The primary purpose of this research is to address the question of how to achieve on-demand and scalable CyberGIS analytics that provide a stable response time to the user. We do that through integration with the Nimbus Phantom cloud platform. We then investigate how the cloud platform is able to adaptively handle fluctuating requests for analytics while providing a stable response time.
KW - Auto-scaling
KW - Cloud computing
KW - CyberGIS
KW - Geographic information systems (GIS)
UR - http://www.scopus.com/inward/record.url?scp=84904572595&partnerID=8YFLogxK
U2 - 10.1145/2608029.2608032
DO - 10.1145/2608029.2608032
M3 - Conference contribution
AN - SCOPUS:84904572595
SN - 9781450329118
T3 - ScienceCloud 2014 - Proceedings of the 2014 ACM International Workshop on Scientific Cloud Computing, Co-located with HPDC 2014
SP - 17
EP - 24
BT - ScienceCloud 2014 - Proceedings of the 2014 ACM International Workshop on Scientific Cloud Computing, Co-located with HPDC 2014
PB - Association for Computing Machinery
T2 - 5th ACM Workshop on Scientific Cloud Computing, ScienceCloud 2014
Y2 - 23 June 2014 through 27 June 2014
ER -