Differential privacy-based low-voltage power utilization data security mining analysis method and device

• Main Authors: FENG YUN, LIN CHENHAN, ZHANG CHEN, LIANG XIAOBING, ZHAO YINGJIE, XIE JINGYI, XU BIN, LI HONGFA, LI ZHIHU, ZHAI FENG, QIN YU, CHEN HAO, PAN WEIHONG, LI BAOFENG, XU MENG, FU YILUN, ZHENG ANGANG, GAO BO
• Format: Patent
• Language: Chinese; English
• Published: 06.02.2024
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a differential privacy-based low-voltage power consumption data security mining analysis method and device, and the method comprises the steps: carrying out the clustering of a collected low-voltage power consumption data set through employing a K clustering algorithm, and determining the initial clustering center and initial classification results of a plurality of clusters; carrying out noise addition on the low-voltage power utilization data set by adopting a Laplacian noise mechanism, generating an effective sample noise addition data set to update the initial clustering center, and determining a noise addition clustering center; the weight of each sample is calculated according to the similarity degree of the samples in each set, and the relative distance between each sample and the corresponding noise adding clustering center is solved; according to the weight and the relative distance of each sample, the multiple clusters are re-divided, and an updated clustering center is deter