An investigation of the relationship between accuracy of customer baseline calculation and efficiency of Peak Time Rebate program

In this paper, the relationship between accuracy of Customer Baseline (CBL) calculation and efficiency of Peak Time Rebate (PTR) program for residential customers is investigated. To perform the analysis, well-established CBL calculation methods, HighXofY(NYISO), LowXofY, MidXofY, exponential moving average(ISONE) and regression are first introduced and then utilized to calculate the CBL. A dataset consisting of 262 residential customers is used for this analysis. In addition, the error analysis is performed using accuracy and bias metrics. Furthermore, to reach a valid conclusion about overall performance of CBL methods, an economic analysis of a PTR program is carried out. According to the results, in the case study, utility pays at least half of its revenue as a rebate merely due to the inaccuracy of CBL methods. In addition, it is shown that PTR causes a lot of inefficiencies in the residential sector because of the failure of CBL calculation methods to predict the customers load profile on event day.