Intelligent power grid monitoring and management strategy using 3D model visual computation with deep learning. (November 2022)

• Record Type: Journal Article
• Authors: Wang, Hongxing; Huang, Zheng; Zhang, Xin; Huang, Xiang; Zhang, Xing wei; Liu, Bin
• Is Part Of: Energy reports. Volume 8(2022)
• Page Start: 3636
• Page End: 3648
• Publication Date: 2022-11
• Subjects: Power grid -- A.I. -- Deep learning -- Industry -- 3D -- Visualization; Power resources -- Periodicals; Energy industries -- Periodicals; Power resources; Periodicals; Electronic journals; 621.04205
• DOI: 10.1016/j.egyr.2022.02.123
• Languages: English
• ISSNs: 2352-4847

Abstract

Abstract: The legacy grid is developing into an intelligently rooted grid system that can enhance and adapt its performance to learning experiences in its architectural components. Due to the evolution of artificial intelligence and in-depth learning techniques, decision-making and execution can become autonomous activities in intelligent power grids throughout the years. 3D visualization plays a vital role in simplifying monitoring, analysis, and reaction to events in the smart grid. The visualization of the 3D models for various energy system applications is first summarized, including the smart grid, power vehicles, and energy consumption of buildings. Accordingly, design principles are provided for wide-screen, personal computer, or mobile interfaces. Visualization technology for geographical information systems is described. 3D technology, animations, and AR&VR to visualize the energy system is discussed. In this article, a coherent 3D visualization approach for the control and monitoring of intelligent power grids (P.G.) via the deep learning (DL) method is examined in industry literature (3D-PGDL). Data visualization is gaining significance with improved measurement systems and Big Data Analytics in intelligent grids and low carbon energy systems. No data design study, accompanying technology, or visualization tools have been conducted. The analysis and practice of data viewing on energy and power systems are thoroughly addressed here. Because of the intrinsic properties of intelligent grids, all collected and processed data are heterogeneous to provide a more comprehensive, multifaceted control viewpoint for the energy sector by creating new ICT instruments and platforms. This section's experiment resulted in a 95.3 % prediction rate and improved data management ratio of 95.7 %, a lower energy consumption ratio of 18.2%, a lower probability of 18.4 %, a lower CO2 emission level of 15.6 % and a humidity rate of 93.1 %.