Abstract
Nowadays, intelligent energy networks are rising with the development of Internet of Things. Relying on massive quantity of sensors, digital twin technology makes it possible to monitor the condition of an energy network in real time. However, for decision makers, future condition is more valuable. Common types of energy like cooling, heating and electrical power, are difficult to be stored. So, the production and consumption of energy shall be in a balance. The prediction of energy consumption helps to reduce cost and waste. Furthermore, the prediction equipment condition can support scheduling and maintenance. As a result, accurate and efficient condition prediction is strongly required in novel energy network. To solve the problem, a principle components analysis (PCA) based temporal and spatial view analysis and prediction (PTSVP) model is proposed in this paper. Because of the considerable amount of data in energy network, data analysis is difficult and inefficient. Dimension reduction can help to reduce data model complexity and lead to efficient prediction. Thanks to the linear dependency among network record, we use feature exaction technology to reduce dimension of energy network data. Besides, traditional prediction model tends to ignore the spatial relations among data. In this paper, both temporal and spatial factors are considered to make this prediction model more accurate and explainable. We apply this model to a practical energy network in Hongqiao, Shanghai, and compare it with traditional statistical learning and machine learning models. The result shows that our model is accurate, stable and efficient.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Yusheng, X.U.E.: Energy internet or comprehensive energy network? J. Mod. Power Syst. Clean Energy 3(3), 297–301 (2015)
Chakravarthy, S.K., Sudhakar, N., Reddy, E.S., Subramanian, D.V., Shankar, P.: Dimension reduction and storage optimization techniques for distributed and big data cluster environment. In: Soft Computing and Medical Bioinformatics, pp. 47–54. Springer, Singapore (2019)
Amasyali, K., El-Gohary, N.M.: A review of data-driven building energy consumption prediction studies. Renew. Sustain. Energy Rev. 81, 1192–1205 (2018)
Guo, J., He, H., Sun, C.: ARIMA-based road gradient and vehicle velocity prediction for hybrid electric vehicle energy management. IEEE Trans. Veh. Technol. (2019)
Greff, K., Srivastava, R.K., Koutník, J., Steunebrink, B.R., Schmidhuber, J.: LSTM: a search space odyssey. IEEE trans. Neural netw. Learn. Syst. 28(10), 2222–2232 (2016)
Vrablecová, P., Ezzeddine, A.B., Rozinajová, V., Šárik, S., Sangaiah, A.K.: Smart grid load forecasting using online support vector regression. Comput. Electr. Eng. 65, 102–117 (2018)
Parra, D., Swierczynski, M., Stroe, D.I., Norman, S.A., Abdon, A., Worlitschek, J., Bauer, C.: An interdisciplinary review of energy storage for communities: challenges and perspectives. Renew. Sustain. Energy Rev. 79, 730–749 (2017)
Sheng, H., Xiao, J., Cheng, Y., Ni, Q., Wang, S.: Short-term solar power forecasting based on weighted Gaussian process regression. IEEE Trans. Industr. Electron. 65(1), 300–308 (2017)
Wang, Y., Hu, Q., Meng, D., Zhu, P.: Deterministic and probabilistic wind power forecasting using a variational Bayesian-based adaptive robust multi-kernel regression model. Appl. Energy 208, 1097–1112 (2017)
Sun, Y., Xu, L., Li, L., Xu, B., Yin, C., Cai, H.: Deep learning based image cognition platform for IoT applications. In: 2018 IEEE 15th International Conference on e-Business Engineering (ICEBE), Xi’an, pp. 9–16. IEEE (2018)
Muralitharan, K., Sakthivel, R., Vishnuvarthan, R.: Neural network based optimization approach for energy demand prediction in smart grid. Neurocomputing 273, 199–208 (2018)
Meng, C., Zeleznik, O.A., Thallinger, G.G., Kuster, B., Gholami, A.M., Culhane, A.C.: Dimension reduction techniques for the integrative analysis of multi-omics data. Brief. Bioinform. 17(4), 628–641 (2016)
Zhao, W., Du, S.: Spectral–spatial feature extraction for hyperspectral image classification: a dimension reduction and deep learning approach. IEEE Trans. Geosci. Remote Sens. 54(8), 4544–4554 (2016)
Li, L., Zhang, J., Wang, Y., Ran, B.: Missing value imputation for traffic-related time series data based on a multi-view learning method. IEEE Trans. Intell. Transp. Syst. (2018)
Tan, Q., Liu, J., Shi, B., Liu, Y., Zhou, X.N.: Public health surveillance with incomplete data–spatio-temporal imputation for inferring infectious disease dynamics. In: 2018 IEEE International Conference on Healthcare Informatics (ICHI), New York, pp. 255–264. IEEE (2018)
Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2414–2423. IEEE (2016)
Acknowledgement
This research is supported by the National Nature Science Foundation of China under Grant No. 61972243.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Yin, Y., Sun, Y., Yu, H., Bi, Z., Xu, B., Cai, H. (2020). PCA Based Energy Network Temporal and Spatial Data Analysis and Prediction. In: Chao, KM., Jiang, L., Hussain, O., Ma, SP., Fei, X. (eds) Advances in E-Business Engineering for Ubiquitous Computing. ICEBE 2019. Lecture Notes on Data Engineering and Communications Technologies, vol 41. Springer, Cham. https://doi.org/10.1007/978-3-030-34986-8_41
Download citation
DOI: https://doi.org/10.1007/978-3-030-34986-8_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-34985-1
Online ISBN: 978-3-030-34986-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)