AUTHOR=Huang Yifan , Liu Yang , Xu Lixiong , Guo Haoran TITLE=A residential user classification approach based on the graded portrait with considering the IDR adaptability and potential JOURNAL=Frontiers in Energy Research VOLUME=10 YEAR=2022 URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2022.1012721 DOI=10.3389/fenrg.2022.1012721 ISSN=2296-598X ABSTRACT=

In the current modern power system, extreme load peaks and valleys frequently occur due to the complicated electricity consumption behaviors. This point severely impacts the security, stability, and economy of the power system. Demand response (DR) has been proved to be one of the most effective ways to shift load to relieve the intensity of the power system. Although DR is mainly applied on the commercial and industrial loads traditionally, in recent years, the residential load has gradually attracted attentions of DR researches, especially incentive demand response (IDR) research because of its remarkable stability and flexibility in terms of load shifting. However, the difficulty of measuring the IDR adaptability and potential of a residential user according to the load curve significantly prevents the IDR from being conveniently implemented. And further, the power company is tremendously difficult to efficiently and effectively select the users with high IDR adaptabilities and potentials to participate in IDR. Therefore, to address the aforementioned issues, this paper presents a residential user classification approach based on the graded user portrait with considering the IDR adaptability and potential. Based on the portrait approach, the residential users with high IDR adaptabilities can be preliminarily selected. And then, based on the selected users, the portrait approach to delineate the users with high IDR potentials is further presented. Afterward, the achieved residential users with high adaptabilities and potentials are labeled, which are employed to train the presented variational auto encoder based deep belief network (VAE-DBN) load classification model. The experimental results show the effectiveness of the presented user portrait approaches as well as the presented load classification model. The results suggest that the presented approaches could be potential tools for power company to identify the suitable residential users for participating in the IDR tasks.