Baseline Load Estimation for Demand Response Based on Blockchain and Neural Networks

Abstract

With the large-scale integration of distributed new energy to the power grid, the power system increasingly relies on demand response to solve the needs of power grid regulation. In demand response, how to estimate the baseline load of response resources is of great significance. With the deepening of baseline load research, the traditional baseline load estimation methods are becoming more and more difficult to apply. To this end, this paper proposes a solution to the shortcomings of traditional methods using blockchain combined with private data. Firstly, traditional baseline load estimation is not effective due to the lack of a large amount of private data. The neural network combined with private data can be used to obtain a high-precision baseline load. Secondly, to address the trust issues caused by the use of private data, the blockchain is used for encrypted storage and regular spot checks are conducted on the owners to achieve mutual trust between the two parties involved. Finally, through the experimental simulation of chemical plants and electric vehicles, the effectiveness of the proposed scheme is verified.