China
Africa
Explore chapters and articles related to this topic
Real-Time Residential Demand Response Management
Published in Hussein T. Mouftah, Melike Erol-Kantarci, Smart Grid, 2017
In this case, the coefficient of determination (COD) (8.70) is introduced to evaluate the effectiveness of adopting batteries for electric privacy protection, where the residual sum of squares (RSS) is RSS=∑t(Pca,t−Pa,t)2 and the explained sum of squares (ESS) is ESS=∑t(Pca,t−P¯ca)2. A smaller COD value indicates a smaller fluctuation profile and thus a better electric privacy protection performance. The results with the three individual similarity indices are presented in Table 8.3. It is shown that the energy usages and electricity bills are at the same magnitude. The energy consumption of index S3 is slightly higher than those of S1 and S2, because there is only a lower energy usage limit (8.43) and no such upper bounds. The lowest battery cost of $0.169 is obtained with index S1, as compared to $0.607 with S3 and as high as $3.69 with S2. It shows that S2 has the least COD of 0.345 as compared to 0.876 for S3 and 0.989 for S1. This indicates that S2 will bring the best electric privacy protection performance compared to S1 and S2. The results further show that the better electric privacy performance one wants to pursue, the more one has to pay. () COD=1−RSSRSS+ESS,0≤COD≤1
Incorporating temporal correlation into a multivariate random parameters Tobit model for modeling crash rate by injury severity
Published in Transportmetrica A: Transport Science, 2018
Qiang Zeng, Huiying Wen, Helai Huang, Xin Pei, S. C. Wong
The Bayesian R2, a global model-fit measurement, is used to estimate the ratio of the explained sum of squares to the total sum of squares (Zeng and Huang 2014). The Bayesian R2 values of crash rates at each injury severity and all observations, represented by and , respectively, are calculated as (Zeng et al., “A Multivariate Random-Parameters,” 2017)
Evaluation of fitting to hyperbolic functions of load transfer curves for piles in granular soil profiles
Published in International Journal of Geotechnical Engineering, 2023
D. F. Silva, Alfran Sampaio Moura
where R2 is the coefficient of determination; TSS is the total sum of squares; RSS is the residual sum of squares; and ESS is the explained sum of squares; yest, yexp are the estimated and experimental values of the independent variable (in this case, t and q of the load–transfer curves); yavg is the average of yexp per load–transfer curve; n is the number of experimental points; and k is the number of independent variables (two for a hyperbolic function).
Spatial joint analysis for zonal daytime and nighttime crash frequencies using a Bayesian bivariate conditional autoregressive model
Published in Journal of Transportation Safety & Security, 2020
Qiang Zeng, Huiying Wen, S.C. Wong, Helai Huang, Qiang Guo, Xin Pei
The Bayesian R2, which measures the global model fit, is used to estimate the ratio of the explained sum of squares to the total sum of squares (Zeng & Huang, 2014). The Bayesian R2 values of daytime and nighttime crash frequencies, represented by and , respectively, are calculated as