Abstract
Due to the popularity of smart electric meter, electricity data is fast generated and abundantly transmitted through hierarchical servers in smart power grid domain. The missing record during transmission will influence subsequent analyses. However, it is not trivial to improve the quality of such continuous sensory data, because both interpolate accuracy and processing latency are hard to guarantee in practice through traditional means. We propose a data interpolation method for electricity data of smart meters in hierarchical edge environment. The missing records would be interpolated by predictive values through support vector regression in edge environment. In extensive experiments on real data, accuracy of data interpolation is guaranteed above 90% with executive time less than 20 milliseconds.
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
Similar content being viewed by others
References
S. Jianxin, Y. Shaniin, Electricity consumption prediction based on SVR with particle swarm optimization in smart grid [J]. Sci. Technol. Manage. Res (2013)
J. Lin, W. Yu, X. Yang, Towards multistep electricity prices in smart grid electricity markets [J]. IEEE Trans. Parallel Distrib. Syst. 27(1), 286–302 (2015)
J. Lin, W. Yu, X. Yang, Towards multistep electricity prices in smart grid electricity markets [J]. IEEE Trans. Parallel Distrib. Syst. 27(1), 286–302 (2015)
M.S.H. Nazmudeen, A.T. Wan, S.M. Buhari, Improved Throughput for Power Line Communication (PLC) for Smart Meters Using Fog Computing Based Data Aggregation Approach [C]. Smart Cities Conference (IEEE, 2016)
Y. Xia, X. Wang, W. Ding, A data cleaning service on massive spatio-temporal data in highway domain, in Service-Oriented Computing – ICSOC 2018 Workshops, ICSOC 2018. Lecture Notes in Computer Science, ed. by X. Liu et al., vol. 11434, (Springer, Cham, 2019)
W. Ding, S. Zhang, Z. Zhao, A collaborative calculation on real-time stream in smart cities [J]. Simul. Modell. Pract. Theory 73, 72–82 (2017)
A. Bose, Smart transmission grid applications and their supporting infrastructure [J]. IEEE Trans. Smart Grid 1(1), 11–19 (2010)
W. Shi, I.E.E.E. Fellow, et al., Edge computing: Vision and challenges [J]. IEEE Internet of Things J. 3(5), 637–646 (2016)
W. Dewen, Y.A.N.G. Liping, Stream processing method and condition monitoring anomaly detection for big data in smart grid [J]. Autom. Electr. Power Syst. 40(14), 122 (2016)
S. Weisong, S. Hui, C. Jie, et al., Edge computing—An emerging computing model for the internet of everything era [J]. J. Comput. Res. Dev 54, 907–924 (2017)
W. Ding, Z. Zhao, DS-harmonizer: A harmonization service on spatiotemporal data stream in edge computing environment [J]. Wirel. Commun. Mobile Comput. 2018, 1–12 (2018)
L. Qiu-Hua, C. Jie, G. Hai-Qing, Forecasting on the amount of sales of electric power based on improved grey model [J]. Stat. Inform. Forum (2009)
Y. Wei, C. Chao, X. Bin, et al., Forecasting for monthly electricity consumption using X12 multiplication method and ARIMA model [J]. Proc CSU-EPSA (2016)
A. Sozen, E. Arcaklioglu, M. Ozkaymak, Modelling of the Turkey’s net energy consumption using artificial neural network. Int. J. Comput. Appl. Technol. 22(2/3) (2005)
Z. Hui, W. Wei, L.I. Xiao-Mei, Study of the model for forecasting vendition kW·h Using ANN [J]. Hunan Electr. Power (2004)
H. Dawen, F. Penglan, Power consumption forecasting application based on XGBoost algorithm [J]. Modern Inform. Technol. (2017)
K. Kavaklioglu, Modeling and prediction of Turkey’s electricity consumption using support vector regression [J]. Appl. Energy 88(1), 368–375 (2011)
G. Yan-Dong, L.I. Rong, Annual electric demand forecasting based on support vector regression [J]. Techniq. Autom. Appl (2008)
L.L. Li, Q.Z. Jing, C.H. Xin, et al., Forecast of electric power demand in Hubei province based on SVR model during the period of 2016—2010 [J]. Power Demand Side Management (2017)
F. Kaytez, M.C. Taplamacioglu, E. Cam, et al., Forecasting electricity consumption: A comparison of regression analysis, neural networks and least squares support vector machines [J]. Int. J. Electr. Power Energy Syst 67(67), 431–438 (2015)
M.S. Al-Musaylh, R.C. Deo, J.F. Adamowski, Y. Li, Short-term electricity demand forecasting with MARS, SVR and ARIMA models using aggregated demand data in Queensland, Australia [J]. Adv. Eng. Inform. 35, 1):1–1)16 (2018)
A.J. Smola, B. Schölkopf, A tutorial on support vector regression. Stat. Comput. 14, 199–222 (2004)
W. Ding, Y. Han, J. Wang, Z. Zhao, Feature-based high availability mechanism for quantile tasks in real-time data stream processing. Softw. Pract. Exp 44(7), 855–871 (2014). 26
W. Ding, Z. Zhao, and Y. Han, A Framework to Improve the availability of Stream Computing. in Proceedings of the 2016 23rd IEEE International Conference on Web Services (ICWS 2016), pp. 594–601, IEEE, SanFrancisco, June 2016
Acknowledgments
This work was supported by National Natural Science Foundation of China (No. 61702014), Beijing Municipal Natural Science Foundation (No. 4192020), and the Top Young Innovative Talents of North China University of Technology (No. XN018022).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Ding, W., Wang, Z., Xia, Y., Ma, K. (2021). An Efficient Interpolation Method Through Trends Prediction in Smart Power Grid. In: Gao, H., Yin, Y. (eds) Intelligent Mobile Service Computing. EAI/Springer Innovations in Communication and Computing. Springer, Cham. https://doi.org/10.1007/978-3-030-50184-6_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-50184-6_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-50183-9
Online ISBN: 978-3-030-50184-6
eBook Packages: EngineeringEngineering (R0)