Time series forecasting; Time series foundation models; Time series data imputation
Abstract :
[en] The integrity of time series data in smart grids is often compromised by missing values due to sensor failures, transmission errors, or disruptions. Gaps in smart meter data can bias consumption analyses and hinder reliable predictions, causing technical and economic inefficiencies. As smart meter data grows in volume and complexity, conventional techniques struggle with its nonlinear and nonstationary patterns. In this context, Generative Artificial Intelligence offers promising solutions that may outperform traditional statistical methods. In this paper, we evaluate two general-purpose Large Language Models and five Time Series Foundation Models for smart meter data imputation, comparing them with conventional Machine Learning and statistical models. We introduce artificial gaps (30 minutes to one day) into an anonymized public dataset to test inference capabilities. Results show that Time Series Foundation Models, with their contextual understanding and pattern recognition, could significantly enhance imputation accuracy in certain cases. However, the trade-off between computational cost and performance gains remains a critical consideration.
Research center :
Interdisciplinary Centre for Security, Reliability and Trust (SnT) > FINATRAX - Digital Financial Services and Cross-organizational Digital Transformations
Disciplines :
Computer science Engineering, computing & technology: Multidisciplinary, general & others Energy Management information systems
Author, co-author :
SARTIPI, Amir ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > FINATRAX
DELGADO FERNANDEZ, Joaquin ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > FINATRAX
FNR17886330 - DELPHI - Data Driven Electricity Load Prediction For Households And Small Industry, 2023 (01/10/2023-30/09/2025) - Gilbert Fridgen FNR13342933 - DFS - Paypal-fnr Pearl Chair In Digital Financial Services, 2019 (01/01/2020-31/12/2024) - Gilbert Fridgen
This research was funded in part by the Luxembourg National Research Fund (FNR) and PayPal, PEARL grant reference 13342933/Gilbert Fridgen, by FNR grant reference HPC BRIDGES/2022_Phase2/17886330/DELPHI and by the Luxembourgish Ministry of Economy with grant reference 20230227RDI170010375846. For the purpose of open access and in fulfillment of pen access and fulfilling the obligations arising from the grant agreement, the author has applied a Creative Commons Attribution 4.0 International (CC BY 4.0) license to any Author Accepted Manuscript version arising from this submission. This paper has been supported by Enovos.
M. L. Di Silvestre, S. Favuzza, E. Riva Sanseverino, and G. Zizzo, "How decarbonization, digitalization and decentralization are changing key power infrastructures," Renewable and Sustainable Energy Reviews, vol. 93, pp. 483-498, 2018.
M. C, olak and E. Irmak, "A state-of-The-Art review on electric power systems and digital transformation," Electric Power Components and Systems, vol. 51, no. 11, pp. 1089-1112, 2023.
Smart Grids Task Force, "Interoperability, standards and functionalities applied in the large scale roll out of smart metering," tech. rep., Standards and Interoperability for Smart Grids Deployment (EG1) within the European Smart Grids Task Force, 2015.
Y. Wang, Q. Chen, T. Hong, and C. Kang, "Review of smart meter data analytics: Applications, methodologies, and challenges," IEEE Transactions on Smart Grid, vol. 10, no. 3, pp. 3125-3148, 2019.
E. Ebeid, R. Heick, and R. H. Jacobsen, "Presenting user behavior from main meter data," in 2016 IEEE International Conference on Smart Grid Communications (SmartGridComm), pp. 594-599, 2016.
J. Wu, A. Koirala, and D. V. Hertem, "Review of statistics based coping mechanisms for smart meter missing data in distribution systems," 2022 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe), pp. 1-6, 2022.
D. Jeong, C. Park, and Y. M. Ko, "Missing data imputation using mixture factor analysis for building electric load data," Applied Energy, vol. 304, p. 117655, 2021.
H. Tang, C. Zhang, M. Jin, Q. Yu, Z. Wang, X. Jin, Y. Zhang, and M. Du, "Time series forecasting with llms: Understanding and enhancing model capabilities," arXiv preprint arXiv:2402.10835, 2024.
J. Wang, W. Du, W. Cao, K. Zhang, W. Wang, Y. Liang, and Q. Wen, "Deep Learning for Multivariate Time Series Imputation: A Survey," Feb. 2024. ArXiv:2402.04059 [cs].
J. Pei, J. Ma, K. L. Man, C. Zhao, and Z. Tian, "A Cross-Dimensional Attention Discriminating Masked Method for Building Energy Time-Series Data Imputation," in 2024 9th International Conference on Smart and Sustainable Technologies (SpliTech), (Bol and Split, Croatia), pp. 1-6, IEEE, June 2024.
J. Hwang and D. Suh, "CC-GAIN: Clustering and classification-based generative adversarial imputation network for missing electricity consumption data imputation," Expert Systems with Applications, vol. 255, p. 124507, Dec. 2024.
D. Vasenin, M. Pasetti, D. Astolfi, N. Savvin, S. Rinaldi, and A. Berizzi, "Incorporating Seasonal Features in Data Imputation Methods for Power Demand Time Series," IEEE Access, vol. 12, pp. 103520-103536, 2024. Conference Name: IEEE Access.
Y. Wang, H. Wu, J. Dong, Y. Liu, M. Long, and J. Wang, "Deep time series models: A comprehensive survey and benchmark," 2024.
K. Lee, H. Lim, J. Hwang, and D. Lee, "Evaluating missing data handling methods for developing building energy benchmarking models," Energy, vol. 308, p. 132979, 2024.
W. Du, J. Wang, L. Qian, Y. Yang, F. Liu, Z. Wang, Z. Ibrahim, H. Liu, Z. Zhao, Y. Zhou, W. Wang, K. Ding, Y. Liang, B. A. Prakash, and Q. Wen, "TSI-Bench: Benchmarking Time Series Imputation," June 2024. ArXiv:2406.12747 [cs].
A. Harman, L. Baur, and A. Sauer, "Systematic comparison of imputation models for automatized gap filling on electrical load data of compressor composites in the industrial sector," Energy Proceedings, 2024.
M. Meyer, D. Zapata, S. Kaltenpoth, and O. Müller, "Benchmarking time series foundation models for short-Term household electricity load forecasting," 2024.
M. Tan, M. A. Merrill, V. Gupta, T. Althoff, and T. Hartvigsen, "Are language models actually useful for time series forecasting?," arXiv preprint arXiv:2406.16964, 2024.
A. Garza and M. Mergenthaler-Canseco, "Timegpt-1," 2023.
X. Shi, S. Wang, Y. Nie, D. Li, Z. Ye, Q. Wen, and M. Jin, "Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts," Oct. 2024. ArXiv:2409.16040.
G. Woo, C. Liu, A. Kumar, C. Xiong, S. Savarese, and D. Sahoo, "Unified Training of Universal Time Series Forecasting Transformers," May 2024. ArXiv:2402.02592.
A. F. Ansari, L. Stella, C. Turkmen, X. Zhang, P. Mercado, H. Shen, O. Shchur, S. S. Rangapuram, S. Pineda Arango, S. Kapoor, J. Zschiegner, D. C. Maddix, H. Wang, M. W. Mahoney, K. Torkkola, A. Gordon Wilson, M. Bohlke-Schneider, and Y. Wang, "Chronos: Learning the language of time series," arXiv preprint arXiv:2403.07815, 2024.
A. Das, W. Kong, R. Sen, and Y. Zhou, "A decoder-only foundation model for time-series forecasting," Apr. 2024. ArXiv:2310.10688.
U. P. Networks, "SmartMeter Energy Consumption Data in London Households," 2014.
J. Domingo-Ferrer and V. Torra, "Ordinal, continuous and heterogeneous k-Anonymity through microaggregation," Data Mining and Knowledge Discovery, vol. 11, pp. 195-212, 2005.
G. Box, "Box and Jenkins: Time Series Analysis, Forecasting and Control," in A Very British Affair: Six Britons and the Development of Time Series Analysis During the 20th Century (T. C. Mills, ed.), pp. 161-215, London: Palgrave Macmillan UK, 2013.
R. E. Kalman, "A new approach to linear filtering and prediction problems," Transactions of the ASME-Journal of Basic Engineering, vol. 82, no. Series D, pp. 35-45, 1960.
R. L. McLaughlin, "Forecasting models: Sophisticated or naive?," Journal of Forecasting (pre-1986), vol. 2, no. 3, p. 274, 1983.
K. Bandara, R. Hyndman, and C. Bergmeir, "MSTL: A Seasonal-Trend Decomposition Algorithm for Time Series with Multiple Seasonal Patterns," International Journal of Operational Research, vol. 1, no. 1, p. 1, 2022.
C. Chatfield, "The Holt-Winters Forecasting Procedure," Journal of the Royal Statistical Society. Series C (Applied Statistics), vol. 27, no. 3, pp. 264-279, 1978. Publisher: [Royal Statistical Society, Oxford University Press].
T. Chen and C. Guestrin, "XGBoost: A Scalable Tree Boosting System," in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, (San Francisco California USA), pp. 785-794, ACM, Aug. 2016.
G. Ke, Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, and T.-Y. Liu, "LightGBM: A Highly Efficient Gradient Boosting Decision Tree," in Advances in Neural Information Processing Systems, vol. 30, Curran Associates, Inc., 2017.
E. Fix and J. L. Hodges, "Discriminatory Analysis. Nonparametric Discrimination: Consistency Properties," International Statistical Review/Revue Internationale de Statistique, vol. 57, no. 3, pp. 238-247, 1989. Publisher: [Wiley, International Statistical Institute (ISI)].
L. Breiman, "Random forests," Machine Learning, vol. 45, pp. 5-32, Oct 2001.
"Introducing Llama 3.1: Our most capable models to date-Ai.meta.com." https://ai.meta.com/blog/meta-llama-3-1/. [Accessed 14-10-2024].
J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F. L. Aleman, D. Almeida, J. Altenschmidt, S. Altman, S. Anadkat, et al., "Gpt-4 technical report," arXiv preprint arXiv:2303.08774, 2023.
"Nixtla/nixtla: TimeGPT-1: Production ready pre-Trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points."
K. G. Olivares, C. Challú, F. Garza, M. M. Canseco, and A. Dubrawski, "NeuralForecast: User friendly state-of-The-Art neural forecasting models." PyCon Salt Lake City, Utah, US 2022, 2022.
F. Garza, M. M. Canseco, and K. G. O. Cristian Challú, "StatsForecast: Lightning fast forecasting with statistical and econometric models." PyCon Salt Lake City, Utah, US 2022, 2022.
F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, vol. 12, no. 85, pp. 2825-2830, 2011.
