EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
3683. Benchmarking Building Energy Consumption Performance by A Nonparametric Least Squares Method
Contributed abstract in session MC-22: Advancements in energy system optimization and analysis tools, stream Energy Management.
Monday, 12:30-14:00Room: 81 (building: 116)
Authors (first author is the speaker)
| 1. | William Chung
|
| Management Sciences, City University of Hong Kong |
Abstract
The Convex Nonparametric Least Squares (CNLS) method can be used to develop a benchmarking model represented by a set of hyperplanes. CNLS assumes that the regression function is either concave or convex. However, there may be instances where the regression function exhibits concave and convex patterns, rendering this assumption invalid. This paper addresses this drawback by proposing a new method called Concave-Convex Nonparametric Least Squares (C2NLS), which incorporates concavity and convexity constraints in CNLS. It is proved that C2NLS will have better goodness-of-fit performance than CNLS, but the number of hyperplanes will also increase. Since C2NLS contains both concave and convex portions, it is not sufficient to rely solely on the concavity assumption (or convexity assumption) during the benchmarking process. To tackle this issue, it is suggested that both concave and convex portions be used separately and combined with the resulting benchmarking scores. An illustrative example is provided, and the energy performance of Hong Kong secondary schools is used to demonstrate the goodness-of-fit of C2NLS.
Keywords
- Energy Policy and Planning
- OR in Energy
- Decision Support Systems
Status: accepted
Back to the list of papers