Entropy-Based Anomaly Detection in Household Electricity Consumption

Energy efficiency is one of the most important current challenges, and its impact at a global level considerable. To solve it critical that consumers are able to control their energy consumption. In this paper, we propose using time series window-based entropy detect anomalies in electricity consumption household when pattern behavior exhibits change. We compare accuracy approach with two machine learning approaches, random forest neural networks, statistical approach, ARIMA model. study whether these approaches same anomalous periods. These different techniques have been evaluated real dataset obtained from households profiles Madrid Region. The entropy-based algorithm detects more days classified as according context information compared other algorithms. This has advantages does not require training period adapts dynamically changes, except vacation periods drops drastically requires some for adapting new situation.