Journal Home > Volume 1 , Issue 3

Building-level load forecasting has become essential with the support of fine-grained data collected by widely deployed smart meters. It acts as a basis for arranging distributed energy resources, implementing demand response, etc. Compared to aggregated-level load, the electric load of an individual building is more stochastic and thus spawns many probabilistic forecasting methods. Many of them resort to artificial neural networks (ANN) to build forecasting models. However, a well-designed forecasting model for one building may not be suitable for others, and manually designing and tuning optimal forecasting models for various buildings are tedious and time-consuming. This paper proposes an adaptive probabilistic load forecasting model to automatically generate high-performance NN structures for different buildings and produce quantile forecasts for future loads. Specifically, we cascade the long short term memory (LSTM) layer with the adjusted Differential ArchiTecture Search (DARTS) cell and use the pinball loss function to guide the model during the improved model fitting process. A case study on an open dataset shows that our proposed model has superior performance and adaptivity over the state-of-the-art static neural network model. Besides, the improved fitting process of DARTS is proved to be more time-efficient than the original one.


menu
Abstract
Full text
Outline
About this article

Adaptive probabilistic load forecasting for individual buildings

Show Author's information Chenxi Wang1Dalin Qin1Qingsong Wen2Tian Zhou3Liang Sun2Yi Wang1 ( )
Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong SAR, China
DAMO Academy, Alibaba Group (U.S.) Inc., Bellevue, WA 98004, USA
DAMO Academy, Alibaba Group, Hangzhou 310023, China

Abstract

Building-level load forecasting has become essential with the support of fine-grained data collected by widely deployed smart meters. It acts as a basis for arranging distributed energy resources, implementing demand response, etc. Compared to aggregated-level load, the electric load of an individual building is more stochastic and thus spawns many probabilistic forecasting methods. Many of them resort to artificial neural networks (ANN) to build forecasting models. However, a well-designed forecasting model for one building may not be suitable for others, and manually designing and tuning optimal forecasting models for various buildings are tedious and time-consuming. This paper proposes an adaptive probabilistic load forecasting model to automatically generate high-performance NN structures for different buildings and produce quantile forecasts for future loads. Specifically, we cascade the long short term memory (LSTM) layer with the adjusted Differential ArchiTecture Search (DARTS) cell and use the pinball loss function to guide the model during the improved model fitting process. A case study on an open dataset shows that our proposed model has superior performance and adaptivity over the state-of-the-art static neural network model. Besides, the improved fitting process of DARTS is proved to be more time-efficient than the original one.

Keywords: long short-term memory (LSTM), Probabilistic load forecasting, Differentiable neural ARchiTecture Search (DARTS), building load forecasting

References(32)

[1]

Hong, T. (2014). Energy forecasting: Past, present, and future. Foresight: The International Journal of Applied Forecasting, 32: 43–48.

[2]

Mocanu, E., Nguyen, P. H., Gibescu, M., Kling, W. L. (2016). Deep learning for estimating building energy consumption. Sustainable Energy, Grids and Networks, 6: 91–99.

[3]

Chen, Y. B., Xu, P., Chu, Y. Y., Li, W. L., Wu, Y. T., Ni, L. Z., Bao, Y., Wang, K. (2017). Short-term electrical load forecasting using the support vector regression (SVR) model to calculate the demand response baseline for office buildings. Applied Energy, 195: 659–670.

[4]

Yu, C. N., Mirowski, P., Ho, T. K. (2017). A sparse coding approach to household electricity demand forecasting in smart grids. IEEE Transactions on Smart Grid, 8: 738–748.

[5]
Liu, H., Simonyan, K., Yang, Y. (2018). Darts: Differentiable architecturesearch. arXiv preprint, 1806.09055.
[6]

Nepal, B., Yamaha, M., Yokoe, A., Yamaji, T. (2020). Electricity load forecasting using clustering and ARIMA model for energy management in buildings. Japan Architectural Review, 3: 62–76.

[7]

Dagdougui, H., Bagheri, F., Le, H., Dessaint, L. (2019). Neural network model for short-term and very-short-term load forecasting in district buildings. Energy and Buildings, 203: 109408.

[8]

Kim, Y., Son, H. G., Kim, S. (2019). Short term electricity load forecasting for institutional buildings. Energy Reports, 5: 1270–1280.

[9]

Wang, J. S., Chen, X. H., Zhang, F., Chen, F. X., Xin, Y. (2021). Building load forecasting using deep neural network with efficient feature fusion. Journal of Modern Power Systems and Clean Energy, 9: 160–169.

[10]

Shi, H., Xu, M. H., Li, R. (2018). Deep learning for household load forecasting—A novel pooling deep RNN. IEEE Transactions on Smart Grid, 9: 5271–5280.

[11]
Marino, D. L., Amarasinghe, K., Manic, M. (2016). Building energy load forecasting using deep neural networks. In: Proceedings of the IECON 2016—42nd Annual Conference of the IEEE Industrial Electronics Society, Florence, Italy.
DOI
[12]
Melis, G., Kočiskỳ, T., Blunsom, P. (2019). Mogrifier LSTM. arXiv preprint, 1909.01792.
[13]

Shen, X. D., Zhao, H. X., Xiang, Y., Lan, P., Liu, J. Y. (2022). Short-term electric vehicles charging load forecasting based on deep learning in low-quality data environments. Electric Power Systems Research, 212: 108247.

[14]
Tan, B., Ma, X., Shi, Q. H., Guo, M., Zhao, H. X., Shen, X. D. (2021). Ultra-short-term wind power forecasting based on improved LSTM. In: Proceedings of the 2021 6th International Conference on Power and Renewable Energy (ICPRE), Shanghai, China.
DOI
[15]

Alhussein, M., Aurangzeb, K., Haider, S. I. (2020). Hybrid CNN–LSTM model for short-term individual household load forecasting. IEEE Access, 8: 180544–180557.

[16]

Hong, T., Fan, S. (2016). Probabilistic electric load forecasting: A tutorial review. International Journal of Forecasting, 32: 914–938.

[17]

Hong, T., Wilson, J., Xie, J. R. (2014). Long term probabilistic load forecasting and normalization with hourly information. IEEE Transactions on Smart Grid, 5: 456–462.

[18]

Taylor, J. W., Buizza, R. (2002). Neural network load forecasting with weather ensemble predictions. IEEE Transactions on Power Systems, 17: 626–632.

[19]

Zhang, W. J., Quan, H., Srinivasan, D. (2019). An improved quantile regression neural network for probabilistic load forecasting. IEEE Transactions on Smart Grid, 10: 4425–4434.

[20]

Liu, B. D., Nowotarski, J., Hong, T., Weron, R. (2017). Probabilistic load forecasting via quantile regression averaging on sister forecasts. IEEE Transactions on Smart Grid, 8: 730–737.

[21]

Shepero, M., van der Meer, D., Munkhammar, J., Widén, J. (2018). Residential probabilistic load forecasting: A method using Gaussian process designed for electric load data. Applied Energy, 218: 159–172.

[22]

Wang, Y., Gan, D. H., Sun, M. Y., Zhang, N., Lu, Z. X., Kang, C. Q. (2019). Probabilistic individual load forecasting using pinball loss guided LSTM. Applied Energy, 235: 10–20.

[23]

Xu, L., Hu, M. M., Fan, C. (2022). Probabilistic electrical load forecasting for buildings using Bayesian deep neural networks. Journal of Building Engineering, 46: 103853.

[24]

Xu, L., Wang, S. W., Tang, R. (2019). Probabilistic load forecasting for buildings considering weather forecasting uncertainty and uncertain peak load. Applied Energy, 237: 180–195.

[25]

He, X., Zhao, K. Y., Chu, X. W. (2021). AutoML: A survey of the state-of-the-art. Knowledge-Based Systems, 212: 106622.

[26]
Zoph, B., Le, Q. V. (2016). Neural architecture search with reinforcementlearning. arXiv preprint, 1611.01578.
[27]
Pham, H., Guan, M., Zoph, B., Le, Q., Dean, J. (2018). Efficient neural architecture search via parameters sharing. In: Proceedings of the 35th International Conference on Machine Learning.
[28]

Real, E., Aggarwal, A., Huang, Y. P., Le, Q. V. (2019). Regularized evolution for image classifier architecture search. Proceedings of the AAAI Conference on Artificial Intelligence, 33: 4780–4789.

[29]
Shin, R., Packer, C., Song, D. X. (2018). DARTS: Differentiable neural network architecture search. Available at https://openreview.net/forum?id=S1eYHoC5FX.
[30]
Biju, G. M., Pillai, G. N., Seshadrinath, J. (2019). Electric load demand forecasting with RNN cell generated by DARTS. In: Proceedings of the TENCON 2019—2019 IEEE Region 10 Conference, Kochi, India.
DOI
[31]
Huber, P. J. (2009). Robust Statistics. Hoboken, NJ, USA: John Wiley & Sons.
DOI
[32]

Miller, C., Kathirgamanathan, A., Picchetti, B., Arjunan, P., Park, J. Y., Nagy, Z., Raftery, P., Hobson, B. W., Shi, Z. X., Meggers, F. (2020). The Building Data Genome Project 2, energy meter data from the ASHRAE Great Energy Predictor III competition. Scientific Data, 7: 368.

Publication history
Copyright
Rights and permissions

Publication history

Received: 17 August 2022
Revised: 02 October 2022
Accepted: 08 October 2022
Published: 20 September 2022
Issue date: September 2022

Copyright

© The author(s)

Rights and permissions

Copyright: by the author(s). The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).

Return