Research on Privacy Protection Based on Joint Learning in Power Industry Big Data Analysis

Autor: Feilu Hang, Linjiang Xie, Zhenhong Zhang, Wei Guo, Hanruo Li
Rok vydání: 2022
Předmět:
Zdroj: Distributed Generation & Alternative Energy Journal.
ISSN: 2156-6550
2156-3306
DOI: 10.13052/dgaej2156-3306.3759
Popis: In the era of big data, protecting the privacy of smart grid data is critical in ensuring the integrity and confidentiality of that data. Utilizing large amounts of energy data to gain insight into electricity consumers’ consumption patterns helps develop power supply strategies. This article presents a Big Data-assisted Joint learning process (BDA-JLP), taking data security issues posed by big data in the electric power industry into consideration for privacy protection using K-anonymity and L-diversity as a foundation. A blockchain with JLP electric utility investigation is being conducted, part of the existing trading model split into phases. To begin, an attribute is chosen to categorize the input database. The comparable class number K and sensitive attribute value category L are limited by the number of original predecessors in the source data table, simplifying the calculation. A mathematical equation is then developed to determine the distance between first cousins multiplied by their combined weight. Linear and clustering with binary K are used to categorize data tables. Cluster and generalize initial data sets, considering how the attribute values’ internal range changes. The asymmetric encryption method uses two distinct keys for encryption and decryption ensuring that the blockchain system is completely secure. Simulated data show that the BDA-JLP mechanism proposed here has a privacy ratio of 98.3 percent, scalability of 97.0%, improved data management and data protection ratio of 98.2 percent, customer satisfaction ratio of 98.4 percent, and a low energy consumption ratio of 23.9% when compared to other methods currently available.
Databáze: OpenAIRE
Externí odkaz: