Neural optimal self-constrained computing in smart grid considering fine-tuning island constraints with visual information

Abstract

With the expansion of the power grid and the acceleration of power information construction, the information communication network covers all aspects and collects accurate information in time to provide continuous and reliable operation for users. The modern power system will gradually enter the era of interconnected power grids. It is more environmentally friendly and efficient than traditional power systems, management is more information and lean, and its operation is safer and more stable. As the infrastructure for carrying smart grid and future energy information interaction, the power communication network has higher and higher requirements for reliability. The coupling between the communication network and the power grid is more and more closely related. The real-time acquisition and the reliable transmission of control information such as the power system require the support of the power communication network. This paper uses machine learning algorithms to learn effective features or patterns from these data and apply them to new data. In this paper, we present a neural optimal self-constrained computing model based on fine-tuning island constraints with visual information. The experimental results show that the proposed algorithm has higher processing efficiency and accuracy.