Explaining deep learning-based anomaly detection in energy consumption data by focusing on contextually relevant data
Open accessAbstract
Detecting anomalies in energy consumption data is crucial for identifying energy waste, equipment malfunction, and overall, for ensuring efficient energy management. Machine learning, and specifically deep learning approaches, have been greatly successful in anomaly detection; however, they are black-box approaches that do not provide transparency or explanations. SHAP and its variants have been proposed to explain these models, but they suffer from high computational complexity (SHAP) or instability and inconsistency (e.g., Kernel SHAP). To address these challenges, this paper proposes an explainability approach for anomalies in energy consumption data that focuses on context-relevant information. The proposed approach leverages existing explainability techniques, focusing on SHAP variants, together with global feature importance and weighted cosine similarity to select background dataset based on the context of each anomaly point. By focusing on the context and most relevant features, this approach mitigates the instability of explainability algorithms. Experimental results across 10 different machine learning models, five datasets, and five XAI techniques, demonstrate that our method reduces the variability of explanations providing consistent explanations. Statistical analyses confirm the robustness of our approach, showing an average reduction in variability of approximately 38\% across multiple datasets.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Deep Learning and Reinforcement Learning often function as black boxes, making their internal logic inaccessible to human operators.
“While Deep Learning and Reinforcement Learning (RL) offer superior performance in handling non-linear energy patterns, they often function as”
From Explainable AI and Multi-Agent Systems for Energy Management in IoT-Edge Environments: A State of the Art Review (2026) · cites this paper as [5]
Ensemble variants such as gradient boosting regression trees improve accuracy compared to single-tree solutions at the expense of transparency unless complemented by XAI tools such as SHAP or LIME.
“Ensemble variants such as gradient boosting regression trees iteratively correct residual errors, improving accuracy compared to single-tree solutions at the expense of transparency unless complemented by XAI tools such as SHAP or LIME [5].”
From Explainable AI and Multi-Agent Systems for Energy Management in IoT-Edge Environments: A State of the Art Review (2026) · cites this paper as [5]
Linear regression baselines serve as benchmarks against which more advanced ML regressors are evaluated.
“Linear regression baselines serve as benchmarks against which more advanced ML regressors are evaluated [5].”
From Explainable AI and Multi-Agent Systems for Energy Management in IoT-Edge Environments: A State of the Art Review (2026) · cites this paper as [5]
XAI tools applied post hoc on MARL-derived decisions can trace causal relationships between observed states and collective responses, validating alignment with operational rulesets.
“XAI tools applied post hoc on MARL-derived decisions can trace causal relationships between observed states (e.g., forecast deficits) and collective responses (e.g., ramp-up of reserve units), thereby validating alignment with operational rulesets [5].”
From Explainable AI and Multi-Agent Systems for Energy Management in IoT-Edge Environments: A State of the Art Review (2026) · cites this paper as [5]
Context-aware XAI frameworks are emerging that select background datasets based on specific anomaly contexts to stabilize explanations and reduce variance.
“Additionally, context-aware XAI frameworks are emerging that select background datasets based on specific anomaly contexts (e.g., distinguishing between holidays and workdays) to stabilize explanations and reduce the variance often observed in standard SHAP implementations [5].”
From Explainable AI and Multi-Agent Systems for Energy Management in IoT-Edge Environments: A State of the Art Review (2026) · cites this paper as [5]
Perturbing one time-step without adjusting its neighbors creates unrealistic input sequences that the model never encountered during training, leading to unreliable attribution scores.
“Perturbing one time-step without adjusting its neighbors creates unrealistic input sequences (out-of-distribution samples) that the model never encountered during training, leading to unreliable attribution scores [5,7].”
From Explainable AI and Multi-Agent Systems for Energy Management in IoT-Edge Environments: A State of the Art Review (2026) · cites this paper as [5]
Cites
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · see citing works
European Union Regulations on Algorithmic Decision Making and a “Right to Explanation”
Goodman, B., & Flaxman, S. (2017) · AI Magazine · doi:10.1609/aimag.v38i3.2741 · Cited by 2,131 · see citing works
Properties of Sufficiency and Statistical Tests
Bartlett, M. S. (1992) · Springer series in statistics · doi:10.1007/978-1-4612-0919-5_8 · Cited by 1,897 · see citing works
Can we open the black box of AI?
Castelvecchi, D. (2016) · Nature · doi:10.1038/538020a · Cited by 1,773 · see citing works
Optuna: A Next-generation Hyperparameter Optimization FrameworkPreprint
Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019) · arXiv (Cornell University) · doi:10.4230/oasics.dx.2024.30 · Cited by 1,513 · see citing works
Aas, K., Jullum, M., & Løland, A. (2021) · Artificial Intelligence · doi:10.1016/j.artint.2021.103502 · Cited by 1,159 · see citing works
The revival of the Gini importance?
Nembrini, S., König, I. R., & Wright, M. N. (2018) · Bioinformatics · doi:10.1093/bioinformatics/bty373 · Cited by 764 · see citing works
Analysis of regression in game theory approach
Lipovetsky, S., & Conklin, M. (2001) · Applied Stochastic Models in Business and Industry · doi:10.1002/asmb.446 · Cited by 677 · see citing works
Himeur, Y., Ghanem, K., Alsalemi, A., Bensaali, F., & Amira, A. (2021) · Applied Energy · doi:10.1016/j.apenergy.2021.116601 · Cited by 660 · see citing works
Algorithms to estimate Shapley value feature attributions
Chen, H., Covert, I., Lundberg, S., & Lee, S. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00657-x · Cited by 510 · see citing works
Explaining anomalies detected by autoencoders using Shapley Additive Explanations
Antwarg, L., Miller, R. M., Shapira, B., & Rokach, L. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115736 · Cited by 496 · see citing works
Modelling and experimental performance analysis of solar-assisted ground source heat pump system
Esen, H., Esen, M., & Özsolak, O. (2015) · Journal of Experimental & Theoretical Artificial Intelligence · doi:10.1080/0952813x.2015.1056242 · Cited by 445 · see citing works
Deterministic Local Interpretable Model-Agnostic Explanations for Stable Explainability
Zafar, M. R., & Khan, N. (2021) · Machine Learning and Knowledge Extraction · doi:10.3390/make3030027 · Cited by 408 · see citing works
Artificial neural network and wavelet neural network approaches for modelling of a solar air heater
Esen, H., Özgen, F., Esen, M., & Şengür, A. (2009) · Expert Systems with Applications · doi:10.1016/j.eswa.2009.02.073 · Cited by 367 · see citing works
Li, G., & Jung, J. J. (2022) · Information Fusion · doi:10.1016/j.inffus.2022.10.008 · Cited by 365 · see citing works
Shapley values for feature selection: the good, the bad, and the axioms
Fryer, D., Strumke, I., & Nguyen, H. (2021) · IEEE Access · doi:10.1109/access.2021.3119110 · Cited by 347 · see citing works
Miller, C., Kathirgamanathan, A., Picchetti, B., Arjunan, P., Park, J. Y., Nagy, Z., Raftery, P., Hobson, B. W., Shi, Z., & Meggers, F. (2020) · Scientific Data · doi:10.1038/s41597-020-00712-x · Cited by 312 · see citing works
Fan, C., Xiao, F., Zhao, Y., & Wang, J. (2017) · Applied Energy · doi:10.1016/j.apenergy.2017.12.005 · Cited by 293 · see citing works
Artificial neural networks and adaptive neuro-fuzzy assessments for ground-coupled heat pump system
Esen, H., İnallı, M., Şengür, A., & Esen, M. (2007) · Energy and Buildings · doi:10.1016/j.enbuild.2007.10.002 · Cited by 270 · see citing works
Towards A Rigorous Evaluation Of XAI Methods On Time Series
Schlegel, U., Arnout, H., El‐Assady, M., Oelke, D., & Keim, D. A. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00516 · Cited by 218 · see citing works
An experimental study of the intrinsic stability of random forest variable importance measures
Wang, H., Yang, F., & Luo, Z. (2016) · BMC Bioinformatics · doi:10.1186/s12859-016-0900-5 · Cited by 215 · see citing works
Liu, X., Ding, Y., Tang, H., & Xiao, F. (2020) · Energy and Buildings · doi:10.1016/j.enbuild.2020.110601 · Cited by 181 · see citing works
Zhang, K., Xu, P., & Zhang, J. J. (2020) · IEEE Conference on Energy Internet and Energy System Integration (EI2) · doi:10.1109/ei250167.2020.9347147 · Cited by 100 · see citing works
Roshan, K., & Zafar, A. (2021) · International journal of Computer Networks & Communications · doi:10.5121/ijcnc.2021.13607 · Cited by 96 · see citing works
Xu, C., & Chen, H. (2020) · Energy and Buildings · doi:10.1016/j.enbuild.2020.109864 · Cited by 77 · see citing works
Qu, Z., Liu, H., Wang, Z., Xu, J., Zhang, P., & Zeng, H. (2021) · Energy and Buildings · doi:10.1016/j.enbuild.2021.111193 · Cited by 76 · see citing works
Explainable Anomaly Detection Framework for Maritime Main Engine Sensor Data
Kim, D., Antariksa, G., Handayani, M. P., Lee, S.-B., & Lee, J. (2021) · Sensors · doi:10.3390/s21155200 · Cited by 70 · see citing works
Explainable AI for Event and Anomaly Detection and Classification in Healthcare Monitoring Systems
Abououf, M., Singh, S., Mizouni, R., & Otrok, H. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3296809 · Cited by 69 · see citing works
Freeborough, W., & van Zyl, T. L. (2022) · Applied Sciences · doi:10.3390/app12031427 · Cited by 65 · see citing works
Moon, J., Rho, S., & Baik, S. W. (2022) · Sustainable Energy Technologies and Assessments · doi:10.1016/j.seta.2022.102888 · Cited by 60 · see citing works
On TinyML and Cybersecurity: Electric Vehicle Charging Infrastructure Use Case
Dehrouyeh, F., Yang, L., Ajaei, F. B., & Shami, A. A. (2024) · IEEE Access · doi:10.1109/access.2024.3437192 · Cited by 57 · see citing works
Yepmo, V., Smits, G., & Pivert, O. (2022) · Data & Knowledge Engineering · doi:10.1016/j.datak.2021.101946 · Cited by 52 · see citing works
Pan, H., Yin, Z., & Jiang, X. (2022) · Energies · doi:10.3390/en15176139 · Cited by 45 · see citing works
Chung, W. J., & Liu, C. (2022) · Energy and Buildings · doi:10.1016/j.enbuild.2022.112521 · Cited by 43 · see citing works
2023 International Conference on Machine Learning and Applications (ICMLA)
Barakat, B., & Huang, Q. (2023) · doi:10.1109/icmla58977.2023 · Cited by 32 · see citing works
Leveraging explainable AI for informed building retrofit decisions: Insights from a survey
Leuthe, D., Mirlach, J., Wenninger, S., & Wiethe, C. (2024) · Energy and Buildings · doi:10.1016/j.enbuild.2024.114426 · Cited by 30 · see citing works
Shaping Up SHAP: Enhancing Stability through Layer-Wise Neighbor Selection
Kelodjou, G., Rozé, L., Masson, V., Galárraga, L. A., Gaudel, R., Tchuenté, M., & Termier, A. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i12.29208 · Cited by 23 · see citing works
A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI
Schlegel, U., & Keim, D. A. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-44070-0_9 · Cited by 19 · see citing works
Smart Meter Data Anomaly Detection Using Variational Recurrent Autoencoders with Attention
Dai, W., Liu, X., Heller, A., & Nielsen, P. S. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-10525-8_25 · Cited by 17 · see citing works
Explainable Artificial Intelligence
Keppeler, V., Lederer, M., & Leucht, U. (2023) · IGI Global eBooks · doi:10.4018/978-1-7998-9220-5.ch100 · Cited by 17 · see citing works
2022 IEEE International Symposium on Advanced Control of Industrial Processes (AdCONIP)
Collective (2022) · doi:10.1109/adconip55568.2022 · Cited by 17 · see citing works
An explainable unsupervised learning framework for scalable machine fault detection in Industry 4.0
Asutkar, S., & Tallur, S. G. (2023) · Measurement Science and Technology · doi:10.1088/1361-6501/ace640 · Cited by 15 · see citing works
Outlier Detection Using the Range Distribution
Dallah, D., & Sulieman, H. (2024) · Trends in mathematics · doi:10.1007/978-3-031-41420-6_57 · Cited by 15 · see citing works
Explainable Fault Diagnosis Model using Stacked Autoencoder and Kernel SHAP
Choi, S. H., & Lee, J. M. (2022) · International Symposium on Advanced Control of Industrial Processes · doi:10.1109/adconip55568.2022.9894124 · Cited by 14 · see citing works
General Frameworks for Anomaly Detection Explainability: Comparative Study
Ravi, A., Yu, X., Santelices, I. B., Karray, F. O., & Fi̇dan, B. (2021) · IEEE International Conference on Autonomous Systems (ICAS) · doi:10.1109/icas49788.2021.9551129 · Cited by 12 · see citing works
Explaining Bad Forecasts in Global Time Series Models
Rožanec, J. M., Trajkova, E., Kenda, K., Fortuna, B., & Mladenić, D. (2021) · Applied Sciences · doi:10.3390/app11199243 · Cited by 10 · see citing works
Real-Time, Model-Agnostic and User-Driven Counterfactual Explanations Using Autoencoders
Labaien, J., Zugasti, E., & Carlos, X. D. (2023) · Applied Sciences · doi:10.3390/app13052912 · Cited by 8 · see citing works
Tan, B., Zhao, J., Su, T., Huang, Q., Zhang, Y. Y. C., & Zhang, H. (2022) · IEEE Power Engineering Society General Meeting · doi:10.1109/pesgm48719.2022.9916892 · Cited by 7 · see citing works
Intelligent Technologies and Applications
(2022) · Communications in computer and information science · doi:10.1007/978-3-031-10525-8 · Cited by 6 · see citing works
Advances in Mathematical Modeling and Scientific Computing
Kamalov, F., Sivaraj, R., & Leung, H.-H. (2024) · Trends in mathematics · doi:10.1007/978-3-031-41420-6 · Cited by 6 · see citing works
Martin-Hoyo, I., Bouly, F., Gandolfo, N., Joly, C., Paparella, R., Biarrotte, J.-L., & Martín‐Sánchez, J. M. (2018) · IEEE Control Systems · doi:10.1109/mcs.2017.2786420 · Cited by 5 · see citing works
Advances in Intelligent Data Analysis XXII
Miliou, I., Piatkowski, N., & Papapetrou, P. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-58547-0 · Cited by 5 · see citing works
Exploring local explanations of nonlinear models using animated linear projections
Spyrison, N., Cook, D., & Biecek, P. (2024) · Computational Statistics · doi:10.1007/s00180-023-01453-2 · Cited by 3 · see citing works
Mueller, J., Czekalla, L., Schuchter, F., & Frey, G. (2023) · International Conference on Machine Learning and Applications · doi:10.1109/icmla58977.2023.00031 · Cited by 2 · see citing works
FLocalX - Local to Global Fuzzy Explanations for Black Box Classifiers
Fernández, G., Guidotti, R., Giannotti, F., Setzu, M., Aledo, J. A., Gámez, J. A., & Puerta, J. M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-58553-1_16 · Cited by 1 · see citing works
Flagged first, then by citations
2 of the 60 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Álvarez-López, C., González-Briones, A., & Li, T. (2026) · Electronics · doi:10.3390/electronics15020385 · Cited by 23 · see citing works
Anastasiadou, M., Santos, V., & Dias, M. S. (2025) · Energy and Buildings · doi:10.1016/j.enbuild.2025.116522 · Cited by 13 · see citing works
A Novel Hybrid Deep Learning-Based Framework for Intelligent Anomaly Detection in Smart Meters
Kaur, S., Chowhan, P., & Sharma, A. (2025) · IEEE Access · doi:10.1109/access.2025.3581257 · Cited by 12 · see citing works
Javaid, N., Hasnain, M., & Ammar, M. (2025) · Applied Energy · doi:10.1016/j.apenergy.2025.126632 · Cited by 11 · see citing works
Bhuiyan, T. (2025) · Journal of Computer Science and Technology Studies · doi:10.32996/jcsts.2025.7.8.136 · Cited by 8 · see citing works
Ammar, M., Javaid, N., & Arishi, A. (2025) · Alexandria Engineering Journal · doi:10.1016/j.aej.2025.07.040 · Cited by 7 · see citing works
Dehrouyeh, F., Shaer, I., Nikan, S., Ajaei, F. B., & Shami, A. A. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3645564 · Cited by 3 · see citing works
Chen, H., Gao, T., Wang, L., & Guo, P. (2025) · Scientific Reports · doi:10.1038/s41598-025-27285-2 · Cited by 2 · see citing works
Ma, G., Tian, S., Tian, W., Yue, H., & Lei, J. (2026) · Energy and Buildings · doi:10.1016/j.enbuild.2026.117360 · Cited by 2 · see citing works
Islam, M. R., Begum, S., & Ahmed, M. U. (2025) · Applied Sciences · doi:10.3390/app151810080 · Cited by 2 · see citing works
Liao, F., Ran, R., & Zhang, J. (2025) · Sustainable Energy Research · doi:10.1186/s40807-025-00172-0 · Cited by 1 · see citing works
Alwaz, N., Bashir, M. M., Rehman, A. U., Ullah, I., & Galea, M. (2025) · Sustainability · doi:10.3390/su172411193 · Cited by 1 · see citing works
Explainable AI for Renewable Energy Project Prefeasibility Analysis
Moses, S. S., & Thornburg, J. (2025) · Asia-Pacific Power and Energy Engineering Conference (APPEEC) · doi:10.1109/appeec66370.2025.11382138 · Cited by 1 · see citing works
METHODS AND ALGORITHMS FOR ANOMALY DETECTION
Skakovskyi, V. O., Savitskyi, R. S., & Fant, М. О. (2025) · Computer Science and Applied Mathematics · doi:10.26661/2786-6254-2025-1-10
Zaman, M., Mondal, A. H., Alam, M. S., Upadhyay, D., & Naik, K. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5383666
Liu, W., Huang, S., & Bing, L. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114768
Artificial Intelligence Methods for Anomaly Detection in Energy Consumption
Méndez, A. L. P., Gordillo, R. M., Bazán-Prieto, C., Guillén, A. B., Pérez, R. E. B., & Igartua, M. A. (2025) · ACM International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems (MSWiM) · doi:10.1109/mswim67937.2025.11308730
Kumar, G. K., & Sankar, P. (2026) · Water Resources Management · doi:10.1007/s11269-025-04359-4
AI-Powered Cooperative Fleet Management Through Explainable Context-Aware Anomaly Detection
Iftikhar, N., Raita, C.-S., Kadem, A., Trinh, M., Lin, Y., Buncek, D., Vestergaard, A. K., & Belle, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-15538-2_28
Explainable appliance-level energy consumption imbalance for smart home security
Ambat, A., & Sahoo, J. (2026) · Journal of Building Engineering · doi:10.1016/j.jobe.2026.115939
Fakhri, S. A., & Satari, M. (2026) · International Journal of Earth Sciences · doi:10.1007/s00531-026-02572-z
Linear Lens: A human-centered, non-interventional mechanistic approach to explainable AI
Danish, M. U., Aziz, M., Rehman, U., & Grolinger, K. (2026) · Machine Learning with Applications · doi:10.1016/j.mlwa.2026.100897
Self-citationWang, B., Chen, F., He, G., & Li, W. (2026) · Energy Reports · doi:10.1016/j.egyr.2026.109408
de Andrade, C. D. Q., do Valle, E. M., & Dias, E. M. S. (2026) · Cuadernos de Educación y Desarrollo · doi:10.55905/cuadv18n6-013
Fang, Y., Yao, Y., Yang, W., Lin, X., & Sheng, C. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115294
Nogay, H. S., & Akinci, T. C. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-44163-9.00004-2
Piscitelli, M. S., Buscemi, G., Roselli, C., Marrasso, E., Pallotta, G., & Capozzoli, A. (2026) · Energy and Buildings · doi:10.1016/j.enbuild.2026.117829
An Explainable Machine Learning Framework for Healthcare Building Energy Demand Forecasting
Gbadegesin, N. (2026) · British Journal of Computer Networking and Information Technology · doi:10.52589/bjcnit-uxutld
TraceX: Central Finite-Difference Explainability for AI-Based Financial Credit Evaluation
Aziz, M., Danish, M. U., Grolinger, K., & Rehman, U. (2026) · IEEE International Conference on AI and Data Analytics (ICAD) · doi:10.1109/icad69378.2026.11609091
Self-citationNasrallah, E., Almazam, K. A., Bashir, F. M., Mounir, S., Dodo, Y. A., Garo, O. O., & Lagebo, M. L. (2026) · International Journal of Low-Carbon Technologies · doi:10.1093/ijlct/ctag089
Masdzarif, N. D. I., Asmai, S. A., Kumar, Y. J., & Fauadi, M. H. F. M. (2026) · IAES International Journal of Artificial Intelligence · doi:10.11591/ijai.v15.i4.pp3103-3119
ÖZÜPAK, Y., Alpsalaz, F., Aslan, E., Uzel, H., ЗАЙЦЕВ, Є. О., & Lemeshko, A. (2026) · Scientific Reports · doi:10.1038/s41598-026-67295-2
Jayanthi, K., Jayasudha, V., K, A. S., Jothi Arunachalam, S., & Ashok, N. (2026) · Research Square · doi:10.21203/rs.3.rs-10340447/v1
Smart Grid Voltage Stabilization and Anomaly Detection using Reinforcement Learning
Srinivasa Vrushith Kumar, B., Maheswari, B. U., & Saravanan, S. (2026) · International Conference on Smart Systems and Inventive Technology (ICSSIT) · doi:10.1109/icssit69151.2026.11656453
Prasad, E. S., Rameshkumar, T., Ramaswamy, Y., Joginpelly, S. K., Mutharasan, A., & Jalaja.P (2026) · doi:10.1109/icsmartgrid70882.2026.11680790
Optimized Ensemble Deep Learning for User Load Forecasting and Residual-Based Anomaly Detection
Gupta, T., Bhatia, R., & Sharma, R. (2026) · IEEE Access · doi:10.1109/access.2026.3733104
Hu, X., Yin, T., Tian, P., Zhao, J., Wang, X., Chen, J., Zhang, H., Sun, J., Qian, Y., & Di, F. (2026) · Applied Sciences · doi:10.3390/app16189207
Xiong, W., & Guo, Y. (2026) · International Conference on Electrical Engineering and Mechatronics Technology (ICEEMT) · doi:10.1109/iceemt71099.2026.11686350
Moon, J. (2026) · Eng—Advances in Engineering · doi:10.3390/eng7100515
Uncertainty-aware explainable multi-horizon building load forecasting with reservoir computing
Serra, A., Ortiz, A., & Canals, V. (2026) · Energy and Buildings · doi:10.1016/j.enbuild.2026.118389
- Authors
- Noorchenarboo, M., & Grolinger, K.
- Affiliations
- Western University (CA)
- Corresponding author
- Grolinger, Katarina
- Venue
- Energy and Buildings
- Publisher
- Elsevier BV
- Published
- 2025-02
- Volume
- 328
- Pages
- 115177
- ISSN
- 0378-7788 (ISSN-L)
- OpenAlex
- W4405363817
- Cited by
- 38
- References
- 60
- Citations by year
- 2026: 24 · 2025: 14
- FWCI
- 5.63
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Energy and Buildings (publishedVersion, cc-by-nc-nd)
- SSRN Electronic Journal (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- Scholarship@Western (Western University) (submittedVersion, cc-by-nc-nd)
- Scholarship@Western (Western University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Alliance de recherche numérique du Canada
- Natural Sciences and Engineering Research Council of Canada (ALLRP 571890 - 21)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
- Keywords
- anomaly detection, energy consumption data, explainable AI, SHAP, KernelSHAP, feature importance, weighted cosine similarity, energy management, black-box models
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
