Network Learning And Propagation Dynamics Analysis

Network Learning and Propagation Dynamics Analysis

Many phenomena in the fields of computer science, biology, sociology, and economics can be described as transmission dynamics on complex networks, and transmission dynamics mainly includes information transmission, disease transmission, and computer virus transmission. In many real propagation phenomena, we often want to know their propagation mechanism and law on complex networks, as well as their prediction methods and control means. Clarifying the above problems allows people to have a clear and comprehensive understanding of the evolution mechanism, propagation process, and steady-state of real phenomena. At the same time, it also provides some necessary theoretical support for predicting and controlling real systems. In recent years, many concepts and methods of statistical physics have also been successfully used in the modeling and calculation of complex networks, such as statistical mechanics, self-organization theory, critical and phase transition theory, seepage theory, and so on. In complex networks, seepage can simulate and describe the growth and evolution characteristics of many natural and social systems. Based on the classical network seepage, people have carried out a lot of research on the explosive seepage in the process of network growth in recent years. Using the seepage method, researchers have drawn many conclusions and brought new ideas in the research directions of network propagation and cascade failure. Based on these theories, many researchers have quantitatively analyzed the influence of many factors on transmission path and transmission mechanism, and then discussed the effect of the control strategy.

Network mining and propagation dynamics analysis

Advances in Artificial Intelligence Application in Data Analysis and Control of Smart Grid

Smart grid (SG) is considered a form of intelligent system that allows the electric grid to perform its functions efficiently. The SG is a network that allows for the flow of electrical energy and data, where the data is used to make intelligent decisions in the operation of the electric grid. Artificial intelligence (AI) techniques, such as expert system (ES), Machine Learning (ML), and deep Learning (DL) have brought an advancing frontier in power electronics and power engineering with their powerful data processing capabilities. The SG relies on the flow of data to make its intelligent control; therefore, AI technology is a perfect fit for the SG. The application of AI technology in the SG has the potential to improve the intelligence of the SG. This research topic is focused on ways of improving the data analysis and control of SG by leveraging technologies. Manuscripts with the progress made in solving a range of miscellaneous and critical problems in SG by leveraging AI methods such as ES, ML, and DL methods are welcome. Reviews and original research that describe the latest developments in this field are considered for publication in this research topic. The scope of this Research Topic will include the following themes, but are not limited to: 1. Data-driven and artificial intelligence approaches to enhancing flexibility and resilience of SG. 2. Expert system, Machine Learning and Deep Learning, reinforcement learning and transfer learning for applications in SG. 3. AI for development in ensuring high reliability and stability of electric power system with high penetration of renewable energy. 4. AI for studies in operation protection, integrated planning, and control of SG systems. 5. AI for development in diagnostics and diagnostics for SG. 6. Health monitoring of a modern wind generation system using an adaptive neuro-fuzzy system. 7. Space vector fault pattern identification of a smart grid subsystem by neural mapping. 8. Control techniques, mathematical programming methods, optimization techniques and metaheuristics applied in SG. 9. AI and optimization techniques for green energy and carbon footprint. 10. Novel applications of AI-based smart grids in smart cities, smart transportation, smart healthcare, and smart manufacturing.