Systematic Review of Models Usedto Handle Class Imbalance in Anomaly Detection for Energy Consumption

Abstract

The widespread integration of Smart technologies into energy consumption systems has brought about a transformative shift in monitoring and managing electricity usage. The imbalanced nature of anomaly data often results in suboptimal performance in detecting rare anomalies. This literature review analyzes models designed to address this challenge. The methodology involves a systematic literature review based on the five-step framework proposed by Khan, encompassing framing research questions, identifying relevant literature, assessing article quality, conducting a critical review, and interpreting results. The findings show that classical machine learning models like Support Vector Machines (SVM) and Random Forests (RF) are commonly used. In conclusion, classical machine learning models like SVM and RF struggle to recognize rare anomalies, while deep learning models, notably Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM), show promise for automatically learning elaborate representations and improving performance while dealing with class imbalance.