Attention Boosted Autoencoder for Building Energy Anomaly Detection

2023/03/28 by Durga Prasad Pydi, Pydi, Durga Prasad, S. Advaith +1
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #Building Energy and Comfort Optimization #FOS: Computer and information sciences #Machine Learning (cs.LG) #Smart Grid Energy Management

paper · pdf · doi:10.48550/arxiv.2303.16097

openalex publication_date 2023/03/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Leveraging data collected from smart meters in buildings can aid in developing policies towards energy conservation. Significant energy savings could be realised if deviations in the building operating conditions are detected early, and appropriate measures are taken. Towards this end, machine learning techniques can be used to automate the discovery of these abnormal patterns in the collected data. Current methods in anomaly detection rely on an underlying model to capture the usual or acceptable operating behaviour. In this paper, we propose a novel attention mechanism to model the consumption behaviour of a building and demonstrate the effectiveness of the model in capturing the relations using sample case studies. A real-world dataset is modelled using the proposed architecture, and the results are presented. A visualisation approach towards understanding the relations captured by the model is also presented.

Related

• A Data Mining-Based Dynamical Anomaly Detection Method for Integrating with an Advance Metering System
• LEAD1.0: A Large-scale Annotated Dataset for Energy Anomaly Detection in Commercial Buildings
• ABODE-Net: An Attention-based Deep Learning Model for Non-intrusive Building Occupancy Detection Using Smart Meter Data
• A Real-time Anomaly Detection Using Convolutional Autoencoder with Dynamic Threshold
• Correlation-Driven Multi-Level Multimodal Learning for Anomaly Detection on Multiple Energy Sources