For access to this article, please select a purchase option:
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Your recommendation has been sent to your librarian.
Transmission line project is an important link of power grid construction stage. The refined prediction of line project cost can help and promote project evaluation, budget formulation, capital audit and other aspects. Intelligent model has been widely used in the modelling process of line engineering cost prediction. This paper describes the establishment process of two classical intelligent algorithm prediction model in detail, compares the advantages and disadvantages of neural network and support vector machine prediction model, and analyses the applicable fields of the two methods. The application of K-means clustering, hierarchical clustering and fuzzy clustering in the field of prediction have been described. Three clustering methods are used to improve the prediction accuracy of neural network and support vector machine intelligent algorithm. In this article a method of comprehensive intelligent prediction of transmission line project cost based on clustering is proposed. Taking the cost of 90 groups of 110kV transmission line projects newly built in 2017–2018 of a block power grid as the data source for example verification. The experiment shows the comprehensive clustering of data sources can significantly improve the accuracy of the application of neural network and support vector machine algorithm in the price prediction of transmission line projects. All of the prediction errors are less than 20%. Hierarchical clustering has the most significant effect on reducing the error of neural network algorithm, while fuzzy clustering has more obvious effect on improving the accuracy of SVM algorithm.
Inspec keywords: pattern clustering; support vector machines; neural nets; power engineering computing; power transmission lines; power grids; fuzzy set theory
Subjects: Data handling techniques; Combinatorial mathematics; Power engineering computing; Combinatorial mathematics; Neural nets; Power systems; Support vector machines; Power transmission lines and cables