Performance Analysis of Machine Learning Techniques for Anomaly Detection in Indian Electricity Consumption Data

Abstract

Anomalies in electricity consumption can have a significant impact on the efficiency and dependability of power systems. Therefore, precise and prompt anomaly detection is essential for ensuring efficient system operation. This research paper presents an in-depth analysis of various machine-learning approaches for detecting abnormalities in Indian electricity consumption data. Specifically, the performance of three widely used machine learning algorithms, namely eXtreme Gradient Boosting, (XGBoost) Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU), is evaluated. The efficacy of each technique is assessed using performance indicators, including mean absolute error (MAE), mean squared error (MSE), and coefficient of determination (R2). The findings of this study provide valuable insights into the most effective machine-learning methods for identifying anomalies in Indian energy usage data. Moreover, this research contributes to the advancement of power grid anomaly detection technologies, leading to more effective systems. The anticipated outcome of this effort is an increase in the dependability and efficiency of the electrical supply system, benefiting both power system operators and end users.