期刊名称：TELKOMNIKA (Telecommunication Computing Electronics and Control)
印刷版ISSN：2302-9293
出版年度：2016
卷号：14
期号：3
页码：791-799
DOI：10.12928/telkomnika.v14i3.3413
语种：English
出版社：Universitas Ahmad Dahlan
摘要：Forecasting accuracy depends on data identification and model parameters. Volume of data and good analysis are the key factors that influence the accuracy of forecasting algorithm. This paper focused on data analysis with aim of determining the actual variables that affect the load consumption. Correlation analysis was used to determine how the load consumption is related to the forecasting variables (model inputs), and hypothesis test to justify the correlation coefficient of each variable. This produced tree different scenarios which ware used to forecast the load within short-term time frame. On the other hand, subtractive clustering and Fuzzy c-means (FCM) algorithms ware compared in fuzzy rules generation using Adaptive Neuro-Fuzzy Inference System (ANFIS) model, for short term electric load forecasting. Forecasting using Hypothesis test data with Subtractive clustering algorithm gave better accuracy compared to the other two approaches. But FCM algorithm is faster in all the three approaches. In conclusion, hypothesis test on the correlation coefficient of the data is a commendable practice for data selection and analysis in short-term load forecasting. Also, subtractive clustering algorithm is good in generating appropriate number of fuzzy rules, and the number depends on the number of input variables. Fuzzy c-means algorithm reduces the number of the rules irrespective of the number of input variables.
其他摘要：Forecasting accuracy depends on data identification and model parameters. Volume of data and good analysis are the key factors that influence the accuracy of forecasting algorithm. This paper focused on data analysis with aim of determining the actual variables that affect the load consumption. Correlation analysis was used to determine how the load consumption is related to the forecasting variables (model inputs), and hypothesis test to justify the correlation coefficient of each variable. This produced tree different scenarios which ware used to forecast the load within short-term time frame. On the other hand, subtractive clustering and Fuzzy c-means (FCM) algorithms ware compared in fuzzy rules generation using Adaptive Neuro-Fuzzy Inference System (ANFIS) model, for short term electric load forecasting. Forecasting using Hypothesis test data with Subtractive clustering algorithm gave better accuracy compared to the other two approaches. But FCM algorithm is faster in all the three approaches. In conclusion, hypothesis test on the correlation coefficient of the data is a commendable practice for data selection and analysis in short-term load forecasting. Also, subtractive clustering algorithm is good in generating appropriate number of fuzzy rules, and the number depends on the number of input variables. Fuzzy c-means algorithm reduces the number of the rules irrespective of the number of input variables.
关键词：short-term load forecasting;anfis;clustering algorithm;correlation analysis;hypothesis test
