Abstract
Providing accurate load forecast to electric utility corporations is essential in order to reduce their operational costs and increase profits. Hence, training set selection is an important preprocessing step which has to be considered in practice in order to increase the accuracy of load forecasts. The usage of mutual information (MI) has been recently proposed in regression tasks, mostly for feature selection and for identifying the real instances from training sets that contains noise and outliers. This paper proposes a methodology for the training set selection in a least squares support vector machines (LS-SVMs) load forecasting model. A new application of the concept of MI is presented for the selection of a training set based on MI computation between initial training set instances and testing set instances. Accordingly, several LS-SVMs models have been trained, based on the proposed methodology, for hourly prediction of electric load for one day ahead. The results obtained from a real-world data set indicate that the proposed method increases the accuracy of load forecasting as well as reduces the size of the initial training set needed for model training.
Highlights
With the promotion of the smart grid concept and the introduction of restructuring into the electric power industry, load forecasting has an even greater importance due to its applications in the planning of demand side management, distributed energy resources, electric vehicles, etc
Three groups of models are generated with different training sets which are formed from the initial training set, each using different measurement criterion for input selection with an “mutual information (MI) threshold” or “number of inputs” option
Two models are generated with an initial training set, one based on simple average fitting and the other based on a recursive forecasting model with direct implementation
Summary
With the promotion of the smart grid concept and the introduction of restructuring into the electric power industry, load forecasting has an even greater importance due to its applications in the planning of demand side management, distributed energy resources, electric vehicles, etc. Many operating decisions rely on accurate short-term load forecasting (STLF), such as generation capacity scheduling, scheduling of fuel and coal purchases, system security analyses, energy transaction planning, etc It plays a significant role in the coordination of hydro-thermal systems, generator maintenance scheduling, load flow analysis, etc. Complex nonlinear relationships between load and its various influential factors cannot be properly represented by conventional linear models and for that purpose artificial intelligence-based techniques are employed These methods include: Kalman filters [1], fuzzy inference [2], knowledge-based expert systems [3], artificial neural networks (ANNs) [4] and support vector machines (SVMs) [5].
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.
