Prediction of False Data Injection Attacks in Smart Grid using AdaBoost, Deep Learning, and KNN

Bishwajeet Pandey, Nurkhat Zhakiyev, Madhu S Gaur, Fariza Tumenbayeva, Sanjeev Kumar, Pushpanjali Pandey

2025

Closed access Metadata (CSL-JSON)
DOI 10.1109/icaic63015.2025.10849233
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

With the advancement and application of computing in electrical infrastructure, all traditional electrical grids are transforming into Smart Grid. Modern Smart Grid are more efficient than traditional electrical grids but also prone to cyber-attacks due to presence of computing devices and communication protocols. In this work, we are finding a better machine learning algorithm to predict false data injection attacks in smart Grid. We have taken the Smart Grid dataset from Kaggle. In our research, we used AdaBoost, Deep Learning (DL), and K Nearest Neighbor (KNN) machine learning classifier. We observed that KNN is better than Deep Learning, and AdaBoost in all parameters of accuracy, precision, recall, and f1-score.