Abstract
Accurate residential load forecasting is crucial to the future smart grid since its fundamental role in efficient energy distribution and dispatch. Compared with aggregated electricity consumption forecasting, predicting residential load of an individual user is more challenging due to the stochastic and dynamic characteristics of electricity consumption behaviors. Existing methods did not fully explore the intrinsic correlations among different types of electricity consumption behaviors, which restricts the performance of these methods. To fill this gap, this paper proposes a residential load forecasting method employing graph neural networks (GNN) to make full use of the intrinsic dependencies among various types of electricity consumption behaviors. Specifically, two kinds of graphs are constructed to leverage the dependence information, i.e., short-term dynamic graphs are constructed for describing correlations among different appliances’ electricity consumption behaviors only a short time ago, while long-term static graphs are built to profile a more general pattern for the internal structure of individual electricity consumption. Both short-term and long-term correlations are restricted mutually through the fusion of these two graphs. GNN is then employed to learn the implied dependencies from both the fused graphs and time-series data for load forecasting. Experiment results on a real-world dataset demonstrate the advantages of the proposed model.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kong, W., Dong, Z.Y., Jia, Y., Hill, D.J., Xu, Y., Zhang, Y.: Short-term residential load forecasting based on LSTM recurrent neural network. IEEE Trans. Smart Grid 10(1), 841–851 (2017)
Uddin, M., Romlie, M.F., Abdullah, M.F., Abd Halim, S., Kwang, T.C., et al.: Areview on peak load shaving strategies. Renew. Sustain. Energy Rev. 82, 3323–3332 (2018)
Zhang, W., Quan, H., Srinivasan, D.: An improved quantile regression neural network for probabilistic load forecasting. IEEE Trans. Smart Grid 10(4), 4425–4434 (2019)
Huang, S.J., Shih, K.R.: Short-term load forecasting via ARMA model identification including non-Gaussian process considerations. IEEE Trans. Power Syst. 18(2), 673–679 (2003)
Li, W., Zhang, Z.: Based on time sequence of ARIMA model in the application of short-term electricity load forecasting. In: 2009 International Conference on Research Challenges in Computer Science, pp. 11–14. IEEE (2009). https://doi.org/10.1109/ICRCCS.2009.12
Ghelardoni, L., Ghio, A., Anguita, D.: Energy load forecasting using empirical mode decomposition and support vector regression. IEEE Trans. Smart Grid 4(1), 549–556 (2013)
Chen, K., Chen, K., Wang, Q., He, Z., Hu, J., He, J.: Short-term load forecasting with deep residual networks. IEEE Trans. Smart Grid 10(4), 3943–3952 (2018)
Shi, H., Xu, M., Li, R.: Deep learning for household load forecasting-a novel pooling deep RNN. IEEE Trans. Smart Grid 9(5), 5271–5280 (2017)
Hossen, T., Nair, A.S., Chinnathambi, R.A., Ranganathan, P.: Residential load forecasting using deep neural networks (DNN). In: 2018 North American Power Symposium (NAPS), pp. 1–5 (2018). https://doi.org/10.1109/NAPS.2018.8600549
Sze, V., Chen, Y.H., Yang, T.J., Emer, J.S.: Efficient processing of deep neural networks: a tutorial and survey. Proc. IEEE 105(12), 2295–2329 (2017)
Rahman, A., Srikumar, V., Smith, A.D.: Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks. Appl. Energy 212, 372–385 (2018)
Chaouch, M.: Clustering-based improvement of nonparametric functional time series forecasting: application to intra-day household-level load curves. IEEE Trans. Smart Grid 5(1), 411–419 (2013)
Razghandi, M., Turgut, D.: Residential appliance-level load forecasting with deep learning. In: GLOBECOM 2020–2020 IEEE Global Communications Conference, pp. 1–6 (2020). https://doi.org/10.1109/GLOBECOM42002.2020.9348197
Dinesh, C., Makonin, S., Bajić, I.V.: Residential power forecasting using load identification and graph spectral clustering. IEEE Trans. Circuits Syst. II Express Briefs 66(11), 1900–1904 (2019)
Wu, Z., Pan, S., Long, G., Jiang, J., Chang, X., Zhang, C.: Connecting the dots: multivariate time series forecasting with graph neural networks. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 753–763 (2020). https://doi.org/10.1145/3394486.3403118
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)
Acknowledgement
This work is partly supported by National Natural Science Foundation of China (NSFC) with grant number 61801315 and 62171302.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Deng, Y., Zhou, Y., Zhang, Z. (2021). Short-Long Correlation Based Graph Neural Networks for Residential Load Forecasting. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Lecture Notes in Computer Science(), vol 13109. Springer, Cham. https://doi.org/10.1007/978-3-030-92270-2_37
Download citation
DOI: https://doi.org/10.1007/978-3-030-92270-2_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92269-6
Online ISBN: 978-3-030-92270-2
eBook Packages: Computer ScienceComputer Science (R0)