Abstract
Short-term load forecasting (STLF) plays an important role in the secure and reliable operation of the electric power system. Grouping similar load profiles by a clustering algorithm is a common method to reduce the uncertainty of electric consumption data. However, due to the uneven distribution of different date types in a historical data set, the tradition fuzzy c-means clustering (FCM) algorithm cannot identify typical load consumption patterns accurately. To solve this problem, a novel STLF model based on the improved FCM (IFCM) algorithm, random forest (RF) and deep neural networks (DNN) is proposed in this paper. First, IFCM is used to partition the load consumption profiles into several groups, and each group represents a typical load consumption pattern. The optimal number of clusters is determined by a recent clustering validity index. Then, a RF model is trained by the meteorological and calendar features of the historical data set. Finally, a DNN model is established for each group, and is trained using the features of the days that are partition into this group by IFCM. The experimental results on two daily load consumption data sets have showed that the proposed STLF model achieves better prediction performance as compared to other methods. In addition, the load consumption pattern of holidays was extracted from the historical data sets by utilizing IFCM, and the prediction performance of holidays in the testing set therefore has been significantly improved.
Highlights
FCM, short term load forecasting (STLF), RF, deep neural networks (DNN), convolutional neural networks (CNN), RNN, DBN, LSTM, general regression neural network (GRNN), ELM, MAPE, MASE, fuzzy c-means clustering short-term load forecasting random forest deep neural network convolutional neural network recurrent neural network deep brief network long short-term memory generalized regression neural network extreme learning machine mean absolute percentage error mean absolute scaled error
It can be observed that the prediction performance is significantly improved by utilizing improved FCM (IFCM) on the D_China data set as the levels of MAPE, MASE and root mean square error (RMSE) are much lower than that of FCM
For the D_China data set, the average values of MAPE, MASE and RMSE of the IFCM+support vector machine (SVM) model are 0.4%, 6% and 0.3% less than that of the FCM+SVM model respectively, these values of the IFCM+GRNN model are 0.1%, 2% and 0.1% less than that of the FCM+GRNN model respectively, these values of the IFCM+ELM model are 0.3%, 7% and 0.4% less than that of the FCM+ELM model respectively, and these values of the proposed model are 0.9%, 16% and 1.2% less than that of the FCM+DNN model respectively
Summary
FCM, STLF, RF, DNN, CNN, RNN, DBN, LSTM, GRNN, ELM, MAPE, MASE, fuzzy c-means clustering short-term load forecasting random forest deep neural network convolutional neural network recurrent neural network deep brief network long short-term memory generalized regression neural network extreme learning machine mean absolute percentage error mean absolute scaled error. A number of methods have been proposed to perform the load forecasting, and can be usually divided into two categories: traditional linear prediction methods. F. Liu et al.: Hybrid STLF Model Based on Improved FCM, RF and DNNs and artificial intelligence (AI) based methods. As the load consumption patterns become more dynamic and unpredictable, AI-based methods are applied to improve the prediction precision [7]. Several models have been used to preform the load forecasting, such as the artificial neural network [47], wavelet transform [9], random forest method [1] and so on. Compared with traditional linear prediction approaches, AI-based methods have been showed better prediction performance owing to the advanced models they use
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
