ANOMALY DETECTION FOR ELECTRIC ENERGY CONSUMPTION IN SMART FARMS

Abstract

Efficient energy management is crucial for achieving cost savings and sustainability in smart farms, as anomalies in electric energy consumption often indicate equipment malfunctions or unnecessary energy waste. This project presents a machine learning–based anomaly detection system designed to identify irregular patterns in both historical and real-time energy consumption data. By leveraging the Isolation Forest algorithm, the system effectively detects deviations from normal usage behavior. A user-friendly visualization dashboard provides real-time insights and alerts, enabling farm operators to take timely corrective actions. The results demonstrate that the proposed approach significantly improves anomaly detection accuracy compared to traditional methods, making it a reliable and efficient solution for smart farm energy management.