ABSTRACT
In recent years, the advancement of Artificial Intelligence (AI) and Advanced Metering Infrastructure (AMI) has led to the development of data-driven methods for energy prediction and anomaly detection. These methods provide automated decision support to building operators in managing and preventing energy loss. Despite the advantages of having sophisticated data-driven models, one major drawback is their lack of transparency, which limits their widespread use. The paper explores the use of the SHapely Additive exPlanations (SHAP), an explainable AI algorithm, to enhance transparency in energy prediction and anomaly detection models. Energy prediction is treated as a regression task, while anomaly detection as a binary classification. The study employs LightGBM models for both anomaly detection and energy prediction, which are tested on a large dataset containing hourly smart metering data from over 200 real buildings. The energy prediction model achieves an R2 score of 0.975, while the anomaly detection model obtains an AUC-ROC score of 0.942. These models are augmented with SHAP value-based visualizations, which provide both local and global explanations of these models, offering valuable insights into the factors influencing their predictions. Additionally, the present study introduces a framework that seamlessly integrates feature transformations within the model, while SHAP operates on the interpretable feature space, enhancing the explanations provided by SHAP values.
- Manoj Gulati and Pandarasamy Arjunan. 2022. LEAD1. 0: a large-scale annotated dataset for energy anomaly detection in commercial buildings. In Proceedings of the Thirteenth ACM International Conference on Future Energy Systems. 485–488.Google ScholarDigital Library
- Srinivas Katipamula and Michael R Brambley. 2005. Methods for fault detection, diagnostics, and prognostics for building systems—a review, part I. Hvac&R Research 11, 1 (2005), 3–25.Google ScholarCross Ref
- Scott M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. Advances in neural information processing systems 30 (2017).Google Scholar
- R Machlev, L Heistrene, M Perl, KY Levy, J Belikov, S Mannor, and Y Levron. 2022. Explainable Artificial Intelligence (XAI) techniques for energy and power systems: Review, challenges and opportunities. Energy and AI 9 (2022), 100169.Google ScholarCross Ref
- Clayton Miller, Anjukan Kathirgamanathan, Bianca Picchetti, Pandarasamy Arjunan, June Young Park, Zoltan Nagy, Paul Raftery, Brodie W Hobson, Zixiao Shi, and Forrest Meggers. 2020. The building data genome project 2, energy meter data from the ASHRAE great energy predictor III competition. Scientific data 7, 1 (2020), 368.Google Scholar
- Saleh Seyedzadeh, Farzad Pour Rahimian, Ivan Glesk, and Marc Roper. 2018. Machine learning for estimation of building energy consumption and performance: a review. Visualization in Engineering 6 (2018), 1–20.Google ScholarCross Ref
Index Terms
- Explainable AI for Energy Prediction and Anomaly Detection in Smart Energy Buildings
Recommendations
A Survey on Explainable Anomaly Detection
In the past two decades, most research on anomaly detection has focused on improving the accuracy of the detection, while largely ignoring the explainability of the corresponding methods and thus leaving the explanation of outcomes to practitioners. As ...
Toward Explainable Deep Anomaly Detection
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data MiningAnomaly explanation, also known as anomaly localization, is as important as, if not more than, anomaly detection in many real-world applications. However, it is challenging to build explainable detection models due to the lack of anomaly-supervisory ...
Explainable contextual anomaly detection using quantile regression forests
AbstractTraditional anomaly detection methods aim to identify objects that deviate from most other objects by treating all features equally. In contrast, contextual anomaly detection methods aim to detect objects that deviate from other objects within a ...
Comments