Improving user interaction in mobile-cloud database query processing

When running queries on a database, choosing an optimal query execution plan to minimize query costs is crucial for the query optimizer. This is especially true in mobile-cloud database systems, where there are multiple costs to execute a query plan such as money, time and energy. In order to fulfill different cost objectives for different users, some query optimizers allow users to select the query execution plan from a Pareto Set based on Skyline queries. The users must select from a potentially large quantity of options, and these options present the values of costs. It is not straightforward to the users how to compare these values in such a way to choose the option that suits their needs best. This increases the possibility for users to choose in-optimal options, and the amount of time spent to make that choice. However, the existing user interaction model during multi-objective query processing is unable to solve this issue. To fill this gap, this paper presents a new user interaction model in multi-objective query processing. This model introduces the administrators, or super users, to the user interaction process, allowing them to preset Weight Profiles and their logical descriptions. Weight Profiles contain objective preferences for the users before the query is executed. By using this model, the users can select a Weight Profile that will obtain their optimal query execution plan, and the process of choosing will be more accurate and efficient.

[1]  Wolf-Tilo Balke,et al.  User Interaction Support for Incremental Refinement of Preference-Based Queries , 2007, RCIS.

[2]  M. Fay,et al.  Wilcoxon-Mann-Whitney or t-test? On assumptions for hypothesis tests and multiple interpretations of decision rules. , 2010, Statistics surveys.

[3]  Jan Chomicki,et al.  Skyline with presorting , 2003, Proceedings 19th International Conference on Data Engineering (Cat. No.03CH37405).

[4]  Alfred Inselberg,et al.  Parallel Coordinates: Visual Multidimensional Geometry and Its Applications , 2003, KDIR.

[5]  I. Y. Kim,et al.  Adaptive weighted-sum method for bi-objective optimization: Pareto front generation , 2005 .

[6]  Bernhard Seeger,et al.  Progressive skyline computation in database systems , 2005, TODS.

[7]  Barzan Mozafari,et al.  DBSeer: Pain-free Database Administration through Workload Intelligence , 2015, Proc. VLDB Endow..

[8]  Le Gruenwald,et al.  Time-, Energy-, and Monetary Cost-Aware Cache Design for a Mobile-Cloud Database System , 2015, Big-O/DMAH@VLDB.

[9]  Ken Friis Larsen,et al.  SkyView: a user evaluation of the skyline operator , 2013, CIKM.

[10]  Jarek Gryz,et al.  Maximal Vector Computation in Large Data Sets , 2005, VLDB.

[11]  Ignacio Alvarez,et al.  Skyline: a rapid prototyping driving simulator for user experience , 2015, AutomotiveUI.

[12]  Bernhard Seeger,et al.  An optimal and progressive algorithm for skyline queries , 2003, SIGMOD '03.

[13]  Seung-won Hwang,et al.  Personalized top-k skyline queries in high-dimensional space , 2009, Inf. Syst..

[14]  Dimitris Papadias,et al.  Collaborative Filtering with Personalized Skylines , 2011, IEEE Transactions on Knowledge and Data Engineering.

[15]  Seung-won Hwang,et al.  Toward efficient multidimensional subspace skyline computation , 2013, The VLDB Journal.

[16]  Ilaria Bartolini,et al.  SaLSa: computing the skyline without scanning the whole sky , 2006, CIKM '06.

[17]  Richard J. Lipton,et al.  Regret-minimizing representative databases , 2010, Proc. VLDB Endow..

[18]  Donald Kossmann,et al.  Shooting Stars in the Sky: An Online Algorithm for Skyline Queries , 2002, VLDB.

[19]  Seung-won Hwang,et al.  MSSQ: Manhattan Spatial Skyline Queries , 2011, SSTD.

[20]  Le Gruenwald,et al.  Weighted Sum Model for Multi-Objective Query Optimization for Mobile-Cloud Database Environments , 2016, EDBT/ICDT Workshops.