| Título: | Research in Residential Electricity Characteristics and Short-Term Load Forecasting |
| Autores: |
Feng, Haixia; University of Chinese Academy of Science Wang, Zhongfeng; University of Chinese Academy of Science Ge, Weichun; University of Chinese Academy of Science Wang, Yingnan; University of Chinese Academy of Science |
| Fecha: | 2013-07-03 |
| Publicador: | TELKOMNIKA: Indonesian journal of electrical engineering |
| Fuente: |
 |
| Tipo: |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
| Tema: | residential electricity; short-term load forecasting; linear regression; artificial neural network |
| Descripción: | In this paper we make research in Residential short-term load forecasting. Different application scenes have different affecting factors of short-term load, so we should specifically analysis of factors that affect the load of the residential electricity. We use SPSS (Statistic Package for Social Science) to figure out the relationship between the daily load and temperature, weather conditions and other factors, finding the main factors among the impacting factors, and analyzing residential electricity consumption habits and load characteristics. Then, the paper introduces the common prediction methods. Combining with the above analysis to choose short-term load forecasting methods for residential users, we create automatic linear regression model and artificial neural network model to predict the future electricity load, calculating the residual between the predicted values and the actual values and mean square deviation of the values, and evaluating the accuracy of the load forecasting. The results prove that automatic linear regression model is effective in residential short-term electricity load forecasting. |
| Idioma: | Inglés |