Machine Learning Models with Neutrosophic Numbers for Cloud  Security Analysis and Smart Grid Control of Renewable Energy

Ahmed E Fakhry; Mamdouh Gomaa; Ahmed A. Metwaly; Ahmed Abdelhafeez

Authors

Ahmed E Fakhry Computer Science Department, Faculty of Information Systems and Computer Science, October 6th University, Giza, 12585, Egypt
Mamdouh Gomaa Department of Computer Science, Faculty of Information Technology, Amman Arab University, 11953, Amman
Ahmed A. Metwaly Department of Computer Science, Faculty of Computers and Informatics, Zagazig University, Zagazig 44519, Egypt
Ahmed Abdelhafeez Computer Science Department, Faculty of Information Systems and Computer Science, October 6th University, Giza, 12585, Egypt

Keywords:

Neutrosophic Sets; Uncertainty; Renewable Energy; Cloud Security; Smart Grid.

Abstract

Machine learning (ML) enables difficult tasks to be completed independently. In a smart grid
(SG), computers and mobile devices may make it easier to monitor security, control interior
temperature, and perform routine maintenance. The ability of smart grids to identify cyberattacks
is essential for assessing the operation's reliability and availability. This essay emphasizes the
integrity of cyberattacks using fake data in the physical layers of smart grids (SGs). This paper
analyzes data transmission security and proposes a novel approach to smart grid energy
management. Here, renewable energy sources are used to assess the smart grid network's energy
efficiency, and the network has been monitored for cloud computing security assessments. We
use an interval trapezoidal neutrosophic number model to deal with uncertainty information and
rank the best ML model under different evaluation matrices. We use the k-nearest neighbor with
k= 3 to 12. The CoCoSo method is used to rank ML models.

DOI: 10.5281/zenodo.15399855