An Intelligent Big Data Security Framework Based on AEFS-KENN Algorithms for the Detection of Cyber-Attacks from Smart Grid Systems

Abstract

Big data has the ability to open up innovative and ground-breaking prospects for the electrical grid, which also supports to obtain a variety of technological, social, and financial benefits. There is an unprecedented amount of heterogeneous big data as a consequence of the growth of power grid technologies, along with data processing and advanced tools. The main obstacles in turning the heterogeneous large dataset into useful results are computational burden and information security. The original contribution of this paper is to develop a new big data framework for detecting various intrusions from the smart grid systems with the use of AI mechanisms. Here, an AdaBelief Exponential Feature Selection (AEFS) technique is used to efficiently handle the input huge datasets from the smart grid for boosting security. Then, a Kernel based Extreme Neural Network (KENN) technique is used to anticipate security vulnerabilities more effectively. The Polar Bear Optimization (PBO) algorithm is used to efficiently determine the parameters for the estimate of radial basis function. Moreover, several types of smart grid network datasets are employed during analysis in order to examine the outcomes and efficiency of the proposed AdaBelief Exponential Feature Selection- Kernel based Extreme Neural Network (AEFS-KENN) big data security framework. The results reveal that the accuracy of proposed AEFS-KENN is increased up to 99.5% with precision and AUC of 99% for all smart grid big datasets used in this study.

Keywords

• smart grid
• big data analytics
• machine learning (ml)
• adabelief exponential feature selection (aefs)
• polar bear optimization (pbo)
• kernel extreme neural network (kenn)