Predicting Energy Demands of Retail Stores—Can Deep Learning Help?

In the context of the energy and climate crises, it is crucial for organizations to utilize advanced methods to reduce energy consumption and energy costs. This study explores the application of deep learning models for predicting energy demands in retail stores, which can enhance market efficiency and contribute to grid stability. We analyze a detailed electricity consumption dataset from a hypermarket in Hungary, focusing on 48-hour forecasts at 15-minute intervals. Our methodology includes the implementation of classical models such as ARIMA and linear regression, as well as state-of-the-art deep learning models like TiDE and foundational models such as Lag-Llama in a “zero shot prediction” as well as a “finetuning” scenario.

Ansari, A. F., Stella, L., Turkmen, C., Zhang, X., Mercado, P., Shen, H., Shchur, O., Rangapuram, S. S., Arango, S. P., Kapoor, S., Zschiegner, J., Maddix, D. C., Wang, H., Mahoney, M. W., Torkkola, K., Wilson, A. G., Bohlke-Schneider, M., & Wang, Y. (2024). Chronos: Learning the language of time series.

Biber, A., Felder, M., Wieland, C., & Spliethoff, H. (2022). Negative price spiral caused by renewables? electricity price prediction on the german market for 2030. The Electricity Journal, 35(8), 107188. https://doi.org/https://doi.org/ 10.1016/j.tej.2022.107188

Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., Brynjolfsson, E., Buch, S., Card, D., Castellon, R., Chatterji, N. S., Chen, A. S., Creel, K. A., Davis, J., Demszky, D., . . . Liang, P. (2021). On the opportunities and risks of foundation models. ArXiv. https://crfm.stanford.edu/assets/report.pdf

Box, G. E. P., & Jenkins, G. M. (1970). Time series analysis: Forecasting and control (1st). Holden-Day. contributors, W. (2024). Makridakis competitions [Accessed: 2024-05-16]. https://en. wikipedia.org/wiki/Makridakis Competitions

Das, A., Kong, W., Leach, A., Mathur, S., Sen, R., & Yu, R. (2023). Long-term forecasting with tide: Time-series dense encoder.

Das, A., Kong, W., Sen, R., & Zhou, Y. (2024). A decoder-only foundation model for time-series forecasting.

Developers, D. (2022a). Autoarima [Accessed: 2024-05-16].

Developers, D. (2022b). Time axes encoders [Accessed: 2024-05-16].

Dickey, D. A., & Fuller, W. A. (1979). Distribution of the estimators for autoregressive time series with a unit root. Journal of the American Statistical Association, 74(366), 427-431. https://doi.org/10.1080/01621459.1979.10482531

Garcia, C., Yang, L., Zhang, M., Chen, Y., Patel, S., & Nguyen, T. (2024). Lag-Llama: Time-series foundation models [Accessed: 2024-05-16].

Garza, A., & Mergenthaler-Canseco, M. (2023). Timegpt-1.

Goswami, M., Szafer, K., Choudhry, A., Cai, Y., Li, S., & Dubrawski, A. (2024). Moment: A family of open time-series foundation models.

Granger, C. (1969). Investigating causal relations by econometric models and cross-spectral methods [Accessed: 2024-03-12]. Econometrica, 37(3), 424-438. https: //doi.org/10.2307/1912791

Herzen, J., Lässig, F., Piazzetta, S. G., Neuer, T., Tafti, L., Raille, G., Pottelbergh, T. V., Pasieka, M., Skrodzki, A., Huguenin, N., Dumonal, M., Kościsz, J., Bader, D., Gusset, F., Benheddi, M., Williamson, C., Kosinski, M., Petrik, M., & Grosch, G. (2022). Darts: User-friendly modern machine learning for time series [Accessed: 2024-05-16]. Journal of Machine Learning Research, 23(124), 1-6. https: //unit8co.github.io/darts/index.html; http: //jmlr.org/papers/v23/21-1177.html

Howard, J., & Ruder, S. (2018). Universal language model fine-tuning for text classification.

Kingma, D. P., & Ba, J. (2017). Adam: A method for stochastic optimization.

Liu, L., Jiang, H., He, P., Chen, W., Liu, X., Gao, J., & Han, J. (2021). On the variance of the adaptive learning rate and beyond.

Oreshkin, B. N., Carpov, D., Chapados, N., & Bengio, Y. (2020). N-beats: Neural basis expansion analysis for interpretable time series forecasting.

Patterson, D., Gonzalez, J., Le, Q., Liang, C., Munguia, L. M., Rothchild, D., So, D., Texier, M., & Dean, J. (2021). Carbon emissions and large neural network training.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., et al. (2011). Scikit-learn: Machine learning in python [Accessed: 2024-05-16]. Journal of machine learning research, 12(Oct), 2825-2830. https://scikit- learn.org/stable/modules/ generated/sklearn.linear model.LinearRegression.html.

Su, J., Lu, Y., Pan, S., Murtadha, A., Wen, B., & Liu, Y. (2023). Roformer: Enhanced transformer with rotary position embedding.

Winters, P. R. (1960). Forecasting sales by exponentially weighted moving averages. Management Science, 6(3), 324-342. https://doi.org/10.1287/mnsc.6.3.324

Woo, G., Liu, C., Kumar, A., Xiong, C., Savarese, S., & Sahoo, D. (2024). Unified training of universal time series forecasting transformers.

Ye, J., Zhang, W., Yi, K., Yu, Y., Li, Z., Li, J., & Tsung, F. (2024). A survey of time series foundation models: Generalizing time series representation with large language model.