Open AccessAn Adaptive Multi-Scene Single-User Flexible Negative Control Effect Evaluation Algorithm
Author(s) -
Gaoyang Zhang,
Huimin Ke,
Gang Wang,
Dong Wang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1650/3/032054
Subject(s) - computer science , algorithm , artificial neural network , set (abstract data type) , basis (linear algebra) , scheme (mathematics) , control (management) , data mining , mathematical optimization , artificial intelligence , mathematics , mathematical analysis , geometry , programming language
Designing an evaluation algorithm that can adapt to the demand response of multiple scenarios can effectively reduce the cost of secondary development of the system and improve the willingness of users to participate in the regulation. In this paper, a self-oriented single user flexible negative control evaluation algorithm is proposed. In this algorithm, the determination method of target load curve is proposed first. On this basis, the generalized distance between curves is defined according to the characteristics of common evaluation indexes. Several parameters are reserved in the generalized distance. By adjusting the parameters, the evaluation scheme can be adapted to different scenarios. Then, this paper puts forward a method to set the initial value of parameters. By using this method and neural network, and combining with the existing evaluation samples, the parameters in the generalized distance can be determined automatically. Furthermore, an annual updating method of each parameter in the generalized distance is proposed by using the algorithm of neural network. Finally, the effectiveness of the algorithm is verified by the historical response data of Changzhou Lvjian district.