Using connectionist systems for electric energy consumption forecasting in shopping centers

• Published in: Automation and remote control Vol. 73; no. 6; pp. 1075 - 1084
• Main Authors: Kamaev, V. A., Shcherbakov, M. V., Panchenko, D. P., Shcherbakova, N. L., Brebels, A.
• Format: Journal Article
• Language: English
• Published: Dordrecht SP MAIK Nauka/Interperiodica 01-06-2012
• Subjects: CAE) and Design; Calculus of Variations and Optimal Control; Optimization; Computer-Aided Engineering (CAD; Control; Large Scale Systems Control; Mathematics; Mathematics and Statistics; Mechanical Engineering; Mechatronics; Robotics; Systems Theory; Energy Consumption; Linear Regression Model; Forecast Error; Remote Control; Mean Absolute Percentage Error
• ISSN: 0005-1179; 1608-3032
• DOI: 10.1134/S0005117912060124

A solution is presented for the short-term electrical energy forecasting in shopping centers located in the Netherlands and Belgium. A forecasting method is proposed on the basis of connectionist systems. General description of the forecasting method is provided, as well as its specific features with respect to the forecasting problem are studied. Several connectionist models are generalized, stated and applied, notably, moving average model, linear regression model, and neural network model. In addition, changes in forecasting quality are demonstrated depending on different input variables. The results of using these connectionist models are discussed, and conclusions regarding specific features of every model are outlined.