A Differentially Private Big Data Nonparametric Bayesian Clustering Algorithm in Smart Grid

• Published in: IEEE transactions on network science and engineering Vol. 7; no. 4; pp. 2631 - 2641
• Main Authors: Guan, Zhitao, Lv, Zefang, Sun, Xianwen, Wu, Longfei, Wu, Jun, Du, Xiaojiang, Guizani, Mohsen
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.10.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Bayes methods; Bayesian analysis; Big Data; Cluster analysis; Clustering; Clustering algorithms; Customer satisfaction; Data analysis; Differential privacy; Internet of Things; Machine learning; Nonparametric Bayesian Method; Nonparametric statistics; Performance evaluation; Privacy; Probabilistic models; Smart grid; Smart grids; Systems stability
• ISSN: 2327-4697; 2334-329X
• DOI: 10.1109/TNSE.2020.2985096

Smart systems, including smart grid (SG) and Internet of Things (IoT), have been playing a critical role in addressing contemporary issues. Taking full advantage of the big data generated by the smart grid can enhance the system stability and reliability, increase asset utilization, and offer better customer experience. To better support the data-driven smart grid, the machine learning technologies such as cluster analysis can be applied to process the massive data generated in smart grid. However, the process of cluster analysis may cause the disclosure of personal private information. In this paper, to achieve privacy-preserving cluster analysis in smart grid, we propose IDPC, a Differentially Private Clustering algorithm based on the Infinite Gaussian mixture model (IGMM). IDPC uses a combination of nonparametric Bayesian method and differential privacy. The nonparametric Bayesian method allows certain parameters to change along with the data and it is usually adopted in a clustering algorithm without a fixed number of clusters. The Laplace mechanism is used in data releasing process to make IDPC differentially private. We present how to make the nonparametric Bayesian clustering algorithm differentially private by adding Laplace noise. By security analysis and performance evaluation, IDPC is proved to be privacy-preserving as well as efficient.