NOTE: Restrictions are in place to limit access to one or more of the files associated with this item. Authorized users must log in to gain access. Non-authorized users do not have access to these files.
Visit the Energy Systems Laboratory Homepage.
Formulation of Prediction Algorithms for Management of Commercial and Industrial Energy Loads
MetadataShow full item record
Adaptive control promise's to significantly improve the energy efficiency of commercial and industrial HVAC systems. By predicting energy consumption and peak usage up to several hours in advance, the adaptive control scheme enables managers to adjust control strategies to minimize overall energy costs. This paper describes the formulation of statistically-based energy load prediction algorithms. For many such applications multiple linear regression analysis is appropriate. Examination of graphical and tabular data generally reveals a large set of candidate regressors. No one statistic can determine the best subset of regressors'. Rather, a set of statistics including the R-squared statistic, residual analysis, T-statistics, standard error of estimate, and correlation matrix statistics must be examined to select the best load prediction algorithm. Implementation and integration of adaptive control using such load prediction algorithms, with standard state-of-the-art control techniques is discussed.
SubjectCommercial and Industrial HVAC
Load Prediction Algorithms
Forrester, R. J.; Wepfer, W. J. (1984). Formulation of Prediction Algorithms for Management of Commercial and Industrial Energy Loads. Energy Systems Laboratory (http://esl.tamu.edu); Texas A&M University (http://www.tamu.edu). Available electronically from