ABSTRACT
With the development of intelligent power technology, the prediction of users' electricity utilizes by relevant power enterprises tends to be meticulous gradually, and the accumulated data of users are various and large. On this basis of the users' data, Subspace clustering is carried out according to the evaluation index of user's electricity consumption characteristics, and various kinds of user's electricity consumption patterns are obtained. According to the different electricity consumption patterns, the users are divided into groups, and the related factors are judged by mutual information matrix for different groups of users, and then the electricity consumption is predicted by multiple linear regression algorithm. This method proposed in this paper can cluster automatically according to the electricity characteristic index, and can effectively identify the power related factors of different user groups. The simulation results show that the proposed method has better prediction effect than the comparative algorithm.
- Zhao Y., Li L., and Liu J. Y., et al. 2010. Combinational recognition model for demand side load profile in shanghai power grid. Power System Technology. 34, 1(Jan. 2010), 145--151.Google Scholar
- Zhao T., Wang L. T. and Zhang Y., et al. 2016. Relation factor identification of electricity consumption behavior of users and electricity demand forecasting based on mutual information and random forests. Proceedings of the CSEE. 36,3(Feb. 2016), 604--614Google Scholar
- Zhao T., Zhang Y., and Zhang D. X. 2014. Application technology of big data in smart distribution grid and its prospect analysis. Power System Technology. 38, 12 (Dec. 2014), 3305--3312Google Scholar
- Rallapalli S. R. and Ghosh S.. 2012. Forecasting monthly peak demand of electricity in India-A critique. Energy Policy. 45,2 (Jun. 2012), 516--520.Google ScholarCross Ref
- Ali O. P. and H. K. C.. 2013. ANN hybrid model versus ARIMA and ARIMAX models of runoff coefficient. Journal of Hydrology. 500, 11(Jun. 2013), 21--36Google Scholar
- Xu B. X. and Li X. F.. 2017. Research on the medium and long-term urban electricity consumption prediction methods. Journal of Hunan University of Technology. 31, 2(Feb. 2017)78--83.Google Scholar
- Mashud R. and Irena K. 2016. Forecasting electricity load with advanced wavelet neural networks. Neurocomputing. 182 (Jun. 2016), 118--132.Google Scholar
- Fan G. F., Peng L. and Hong W. C., et al. 2016. Electric load forecasting by the SVR model with differential empirical mode decomposition and auto regression. Neurocomputing. 173 (Jun. 2016), 958--970.Google Scholar
- Yang H., Zhang L. and He Q., et al. 2010. Study of power load classification based on adaptive fuzzy C means. Power System Protection and Control. 38, 16 (Aug. 2010), 111--115.Google Scholar
- Xue C. R., Gu J. and Zhao J. P., et al. 2014. Electricity retail tariff mechanism based on customers' electrical characteristics and cost apportionment. East China Electric Power. 42, 1 (Jan. 2014), 168--173Google Scholar
- Niu K., Zhang S. B. and Chen J. L. 2008. Subspace clustering through attribute clustering. Journal of Beijing University of Posts and Telecommunications. 30, 3(Jan. 2008), 1--5.Google Scholar
Index Terms
- Linear Regression Electricity Prediction Method Based on Clustering of Electric Characteristics
Recommendations
Clustering Residential Electricity Consumption: A Case Study
EEET '18: Proceedings of the 2018 International Conference on Electronics and Electrical Engineering TechnologyElectricity is a crucial need of any modern society for improved lifestyle. Rwanda is a fast growing economy country, with some electricity access rolling out programmes and the country is trying its best to improve the national power grid ...
Modelling the weekly electricity demand caused by electric cars
The travel demand model mobiTopp is used to analyse the effects of an increasing fleet of electric vehicles on the electricity demand. For this purpose mobiTopp has been extended to support EVs. These extensions comprise an EV ownership model, different ...
Modelling the Weekly Electricity Demand Caused by Electric Cars
AbstractAs transport is one of the big sources of carbon dioxide emissions, it is natural to seek for solutions reducing the carbon dioxide emissions in transport as well. Replacing cars powered by a combustion engine by battery electric vehicles may be ...
Comments