Probabilistic Forecast Combination for Anomaly Detection in Building Heat Load Time Series

2021/07/22 by Mario Beykirch, Beykirch, Mario, Tim Janke +5
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Applications (stat.AP) #Energy Load and Power Forecasting #FOS: Computer and information sciences #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.2107.10828

openalex publication_date 2021/07/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We consider the problem of automated anomaly detection for building level heat load time series. An anomaly detection model must be applicable to a diverse group of buildings and provide robust results on heat load time series with low signal-to-noise ratios, several seasonalities, and significant exogenous effects. We propose to employ a probabilistic forecast combination approach based on an ensemble of deterministic forecasts in an anomaly detection scheme that classifies observed values based on their probability under a predictive distribution. We show empirically that forecast based anomaly detection provides improved accuracy when employing a forecast combination approach.

Related

• Data-Driven Model For Heat Load Prediction In Buildings Connected To District Heating Networks
• A Data Mining-Based Dynamical Anomaly Detection Method for Integrating with an Advance Metering System
• One-class anomaly detection through color-to-thermal AI for building envelope inspection
• LEAD1.0: A Large-scale Annotated Dataset for Energy Anomaly Detection in Commercial Buildings
• Preparing Weather Data for Real-Time Building Energy Simulation