Electric Load Prediction Baselines for Airport Buildings: A Case Study

Given their large energy footprints and the availability of building energy management systems, airports are uniquely positioned to take advantage of demand response (DR) programs. Although a baseline—the estimation of what the load would have been without load reduction—is essential to assess the performance of DR strategies, there has been very little published research on developing baselines for airports. Therefore, the research described in this paper aims to develop baseline models specially intended for airport facilities. Specifically, the authors propose piece-wise linear regression models for predicting electricity demand using time-of-week, temperature, and flight schedule information. For the given period of April and May, test results reveals that a model, which has trained over specific seasonal data with only time-of-week and temperature as inputs, has the best prediction performance. The number of passengers of departure flight schedules is shown to have a positive relationship to the load, but does not improve the model accuracy significantly. However, since this study is done for the spring season, when heating, ventilating, and air conditioning (HVAC) systems run the least, the results may not represent other seasons with high cooling or heating demand. Therefore, further studies should be carried out to conclude the potential of flight schedules in improving accuracies of energy prediction baselines.


  • English

Media Info

  • Media Type: Web
  • Features: References;
  • Pagination: pp 869-878
  • Monograph Title: Construction Research Congress 2016: Old and New Construction Technologies Converge in Historic San Juan

Subject/Index Terms

Filing Info

  • Accession Number: 01606011
  • Record Type: Publication
  • ISBN: 9780784479827
  • Files: TRIS, ASCE
  • Created Date: May 24 2016 3:03PM