An Integrated Energy Situational Awareness Approach Based on Markov Transition Field

Situational awareness is a technology for acquiring, understanding and predicting changes that can lead to changes in the state of a system, and its core goal is to help people better understand the current situation, which requires collecting and integrating from various sensors, data sources and information flows to generate useful data, and then using this data as a basis for predicting and analyzing the next operating state of the model. In order to improve the performance of the model's situational awareness and prediction, this paper proposes a hybrid neural network integrated energy situational awareness method based on Markov Transition Fields (MTF), which analyzes the offset values of the electrical and thermal states of the integrated energy system, and identifies the operating state of the integrated energy system to complete situational awareness. The experimental results show that the system in this paper can reduce the relative error of situational awareness and improve the accuracy of situational awareness.