In this paper, we propose a new ensemble residual network model for short-term load forecasting (STLF). This model improves the accuracy of short-term load forecasting (24 hours in advance). The model has a two-stage network structure. First, the different fully-connected layers are combined, and the combined structure is similar to a recurrent neural network (RNN). Features obtained from historical load data are input to the first stage of the model to get preliminary prediction results. The second stage of the model is a modified residual network, and the final predictions are output from here. We use the ensemble snapshot model with learning rate decay to improve the generalization capability of the model. The model proposed in this paper was trained and tested on two public datasets. Numerical testing shows that the proposed model can get better forecasting results in comparison with other methods, and the ensemble method adopted effectively improves the generalization ability of the model.
Software project cost estimation is a key point for enterprises to make reasonable project quotations. However, most software cost estimation methods have limited features, such as requiring higher data volume or only having lower estimation accuracy. Aiming to resolve these problems, a novel algorithm for software development cost estimation based on fuzzy rough set was presented. First, the influencing factors of software development cost were analyzed. The objective weight of each influencing factor was obtained from the data analysis of completed projects by using rough set theory. Second, the comprehensive weight of each influencing factor was recalculated by combining the results of the first step with the subjective weight of the factors given by the experts. Combining the comprehensive weight with fuzzy theory, fuzzy similarities were calculated. Third, according to fuzzy similarity, several items that were most similar to the current project were selected as the samples from the completed projects. Then, the software development cost was estimated based on the cost data of samples from the completed project. Finally, this new algorithm was verified to be effective. The result showed that the maximum and average deviations of the fuzzy rough set algorithm were less than 10%, and the estimated maximum and average deviations of the fuzzy rough set algorithm were less than that of the fuzzy analogy algorithm. Thus, the algorithm could estimate the software cost accurately.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.