A Customer Baseline Measurement Method for Residential User of Demand Response
ID：292
Submission ID：26 View Protection：ATTENDEE
Updated Time：2021-12-03 10:57:52 Hits：499
Poster Presentation
Start Time：2021-12-17 14:30 （Asia/Shanghai）
Duration：5min
Session：[Z] Poster Session » [Z6] Poster Session 6: AI-driven technology
Video
No Permission
Presentation File
Tips: The file permissions under this presentation are only for participants. You have not logged in yet and cannot view it temporarily.
Abstract
One of the most important challenges for DR revenue is the calculation of customer baseline load. In this paper a novel CBL (Customer Baseline Load ) calculation method and it’s correction based on error evaluation is proposed theoretically and empirically. A dataset consisting of 2135 residential customers from China is utilized for the case study to test the performance of the algorithm in actual conditions using accuracy and bias metrics. The case study results show that load data is non-stationary, and the baseline method of grey theory can well adapt to this feature. The model proposed in this paper can effectively improve the accuracy of demand response load baseline measurement. The average error is decreased from 6.09% to 3.56%. At the same time, it can also provide data support for adjustable load to participate in market-oriented transactions.
Keywords
Speaker
Comment submit