References in periodicals archive ?
For each of the 48,268 premise IDs, CVRMSE (equation 5) and NMBE (equation 6) were calculated between it and its matched prototype building.
NMBE = [[summation].sup.N.sub.i=1]([E.sub.i] - [P.sub.i])/[[summation].sup.N.sub.i=1][E.sub.i], (14)
NMBE = 100 x[([summation](yi-[??]i))/(n-1)]/[bar.y] (2)
Equal weighting factors for kWh/kW/gas utility bills are assumed, while a ratio of 3:1 has been selected for NMBE:CV values.
The calibration results were found to be well within the acceptable limits of the NMBE and CvRMSE criteria and thus are satisfactory.
Calculating the indices, the modified model has a CVRMSE of 12.24% and an NMBE of 11%, while the default model has a CVRMSE of 14.4% and 8.16%.
Statistical indicators for Monthly Calibration of the Sample Buildings Sample Building NMBE, % CVRMSE, % 1 -2.6 8.7 2 5.0 3.4 3 1.2 6.3 Table 3.
The coefficient of variation of the root-mean-square error (CV[RMSE]) and normalized mean bias error (NMBE) were also calculated for each fitted model, shown in the following equations:
Eight specimens (Natural History Museum of Los Angeles County, LACM 146192-146197, Los Angeles, California, USA; Smithsonian Tropical Research Institute, STRI 0113, Panama; Naturhistoriches Museum Bern, NMBE 1049173-1049174, Switzerland) of A.
ASHRAE Guideline 14 suggests two main indicators: normalized mean bias error (NMBE) and coefficient of variation of the root mean square error (CVRMSE).
For the section least fitting with the experimental data, a temperature fit having a normalized mean bias error (NMBE) of 4.74 and coefficient of variance of the root mean square error (CV[RMSE]) of 5.79 is calculated for the charging case and a NMBE of 4.18 and CV(RMSE) of 4.27 for the discharging case.
The statistical indices of the coefficient of variation of the root-mean-square error (CV-RSME) and normalized mean bias error (NMBE) were used for the model validation process.
Acronyms browser ?
Full browser ?