Optimization of time-of-use electricity tariffs for multi-type consumers using price-based demand response and consumer classification model

Existing researches predominantly focus on optimizing time-of-use tariffs for single-type consumers, overlooking the fact that an actual distribution system comprises multi-type consumers with distinct power consumption behaviors and preferences. To better cater to the diverse needs of different consumer types, this study proposes an optimization method for multi-type consumers of time-of-use tariffs using price-based demand response and a consumer classification model. Firstly, a joint classification model for multi-type consumers is constructed based on convolutional neural network autoencoder and hierarchical clustering algorithm. Then, by applying the constructed model to historical power consumption data, consumers are classified into several groups. Secondly, a fuzzy heuristic algorithm is introduced to optimize time-of-use tariffs for these consumer groups. Through fuzzy reasoning, the optimal tariffs during different time periods are determined for each group using the fuzzy heuristic algorithm. The effectiveness and adaptability of the proposed method is verified through an application example involving time-of-use tariff optimization for an actual distribution network. Simulation results demonstrated that the maximum power demands for consumers powered by the power company reduced by 6%~9%. The load rate for the studied power company increased from 0.77 to 0.81 ~ 0.84. In addition, compared with two latest methods, when the proposed method was used for ToU tariff optimization, reduction rate of the maximum power demand was improved by 0.75%~2.05% and 0.98%~2.52%, respectively. Load rate for the power company was improved by 0.01 ~ 0.03 and 0.02 ~ 0.03.