Abstract
Load forecasting is to use historical load information to estimate the load demand for a period of time in the future. At present, mode decomposition algorithm is often used in the field to improve the forecasting accuracy. However, mode decomposition will cause the accumulation of errors, in order to solve this problem, this paper analyzes the relationship between the original load and the Intrinsic Mode Functions (IMFs), and constructs an ultra-short-term load forecasting algorithm based on Variational Mode decomposition (VMD) and TGCN-GRU (Temporal Graph Convolution-Gated Recurrent Unit). Firstly, the model uses VMD to decompose the original load into multiple relatively stable IMFs. Then it inputs the original load, external factors that affect the load, and all IMFs into TGCN, and uses TGCN to extract the spatial relationships of each graph node and the timing characteristics of each graph node itself. Finally, these spatiotemporal features are input into the GRU unit for prediction. The model not only rationally combines all IMFs into a whole and to solve the problem of error accumulation, but also fully analyzes the interrelationship among the IMFs, the original load and the external factors affecting the load. We conducted comparison experiments using real load data and other load forecasting models, and the experiment results indicate, that the overall accuracy of this model is superior to the model compared.
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, X., Li, C., Wang, C.: Short-term electrical load forecasting based on error correction using dynamic mode decomposition. Appl. Energy 261, 114368 (2020)
Saber, A.Y., Alam, A.K.M.R.: Short term load forecasting using multiple linear regression for big data. In: IEEE Symposium Series on Computational Intelligence, pp. 1–6. Honolulu (2016)
Alberg, D., Mark, L.: Short-term load forecasting in smart meters with sliding window-based ARIMA algorithms. Vietnam J. Comput. Sci. 261(3), 241–249 (2019)
Guefano, S., Tamba, J.G., Azong, T.E.W.: Forecast of electricity consumption in the Cameroonian residential sector by Grey and vector autoregressive models. Energy 214, 118791 (2021)
Fan, G.F., Peng, L.L., Hong, W.C.: Short term load forecasting based on phase space reconstruction algorithm and bi-square kernel regression model. Appl. Energy 224, 13–33 (2018)
Liu, S., Cui, Y., Ma, Y et al.:Short-term load forecasting based on GBDT combinatorial optimization. In: 2nd IEEE Conference on Energy Internet and Energy System Integration, pp. 1–5. Beijing (2018)
Kaytez, F.: A hybrid approach based on autoregressive integrated moving average and least-square support vector machine for long-term forecasting of net electricity consumption. Energy 197, 118791 (2021)
Zhang., J, Xu. C.C., Zhang. Z: Electric load forecasting in smart grids using long-short-term-memory based recurrent neural network. In: The 51st Annual Conference on Information Sciences and Systems, pp. 1–6. Baltimore (2017)
Kong, W., Dong, Z.Y., Jia, Y.: Short-term residential load forecasting based on LSTM recurrent neural network. IEEE Trans. Smart Grid. Energy 10(1), 841–851 (2017)
Kin, T.Y., Cho, S.B.: Predicting residential energy consumption using CNN-LSTM neural networks. Energy 182, 72–81 (2019)
Sajjad, M., Khan, Z.A., Ullah, A.: A novel CNN-GRU-based hybrid approach for short-term residential load forecasting. IEEE Access. 8, 143759–143768 (2020)
Wang, S., Wang, X., Wang, S.: Bi-directional long short-term memory method based on attention mechanism and rolling update for short-term load forecasting. Int. J. Electr. Power Energy Syst. 109, 470–479 (2019)
Liu, Y.H., Zhao, Q.: Ultra-short-term power load forecasting method based on cluster empirical mode decomposition of CNN-LSTM. Power Syst. Technol. 45(11), 4444–4451 (2021)
Tayab, U.B., Zia, A., Yang, F.: Short-term load forecasting for microgrid energy management system using hybrid HHO-FNN model with best-basis stationary wavelet packet transform. Energy 203, 117857 (2020)
Liang, Y., Niu, D., Hong, W.C.: Short term load forecasting based on feature extraction and improved general regression neural network model. Energy 166, 653–663 (2019)
Li, J., Deng, D., Zhao, J.: A novel hybrid short-term load forecasting method of smart grid using MLR and LSTM neural network. IEEE Trans. Ind. Informat. 17(4), 2443–2452 (2020)
Han, L., Zhang, R., Wang, X.: Multi-step wind power forecast based on VMD-LSTM. IET Renew. Power Gener. 13(10), 1690–1700 (2019)
Zhao, L., Zhao, Y., Zhao, C.: T-GCN: a temporal graph convolutional network for traffic prediction. IEEE Trans. Intell. Transp. Syst. 21(9), 3848–3858 (2019)
Zhu, J., Wang, Q., Tao, C.: AST-GCN: attribute-augmented spatiotemporal graph convolutional network for traffic forecasting. IEEE Access. 9, 35973–35983 (2021)
Hou, X., Wang, K., Zhong, C.: ST-Trader: a spatial-temporal deep neural network for modeling stock market movement. IEEE/CAA J. Automatica Sinica 8(5), 1015–1024 (2021)
Jung, S., Moon, J., Park, S.: An attention-based multilayer GRU model for multistep-ahead short-term load forecasting. Sensors 21(5), 1639 (2021)
Luis, C. https://archive-beta.ics.uci.edu/ml/datasets/appliances+energy+prediction. Accessed 12 Jan 2021
Zhao, B., Wang, Z.P., Ji, W.J.: A short-term power load forecasting method based on attention mechanism of CNN-GRU. Power Syst. Technol. 43(12), 4370–4376 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Ding, M., Zhang, H., Zeng, B., Cai, G., Chai, Y., Gan, W. (2022). Ultra-short-Term Load Forecasting Model Based on VMD and TGCN-GRU. In: Fujita, H., Fournier-Viger, P., Ali, M., Wang, Y. (eds) Advances and Trends in Artificial Intelligence. Theory and Practices in Artificial Intelligence. IEA/AIE 2022. Lecture Notes in Computer Science(), vol 13343. Springer, Cham. https://doi.org/10.1007/978-3-031-08530-7_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-08530-7_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08529-1
Online ISBN: 978-3-031-08530-7
eBook Packages: Computer ScienceComputer Science (R0)