Smart Meter Data Analytics – Load Identification and Abnormality Detection using Computational Algorithms: A Case Study

Smart meters have become increasingly popular replacing the conventional electricity meter. Smart meters produce a large amount of data, thereby, making it difficult to analyze the data efficiently and effectively. To improve the analysis of smart meter data, computational algorithms must be utilized. In this paper, decision trees, and neural networks were used to analyze smart meter data for load identification and abnormality detection. Data utilized in this study were collected from a real smart meter from used for a residential apartment of a metro city. From the results, it was observed that decision trees produced more accurate results for load identification and abnormality detection when compared to results produced when utilizing neural networks.