학술논문
Evolutionary Dynamic Database Partitioning Optimization for Privacy and Utility
Document Type
Periodical
Source
IEEE Transactions on Dependable and Secure Computing IEEE Trans. Dependable and Secure Comput. Dependable and Secure Computing, IEEE Transactions on. 21(4):2296-2311 Aug, 2024
Subject
Language
ISSN
1545-5971
1941-0018
2160-9209
1941-0018
2160-9209
Abstract
Distributed database system (DDBS) technology has shown its advantages with respect to query processing efficiency, scalability, and reliability. Moreover, by partitioning attributes of sensitive associations into different fragments, DDBSs can be used to protect data privacy. However, it is complex to design a DDBS when one has to optimize privacy and utility in a time-varying environment. This article proposes a distributed prediction-randomness framework for the evolutionary dynamic multiobjective partitioning optimization of databases. In the proposed framework, two sub-populations contain individuals representing database partitioning solutions. One sub-population utilizes a Markov chain-based predictor to predict discrete-domain solutions for database partitioning when the environment changes, and the other sub-population utilizes the random initialization operator to maintain population diversity. In addition, a knee-driven migration operator is utilized to exchange information between two sub-populations. Experimental results show that the proposed algorithm outperforms the competing solutions with respect to accuracy, convergence speed, and scalability.