Abstract
The traditional scheduling approach, which primarily considers energy oligarchs like large-scale loads and large-scale generators, is challenged by the rapid rise of distributed energy resources (DERs) in energy internet of things (EIoT). Metaverse is emerging as one of the most promising technologies considering emergence from DERs in EIoT. Our work, from a macro perspective in the virtual space, provides a metaverse framework to harness the swarm intelligence that emerges from the aggregation behavior of massive diverse DERs in EIoT. The presented framework is built upon virtual twins, data science, systems theory, and 4th-Paradigm (data-intensive scientific discovery paradigm), enabling a novel energy scheduling mode. Our goal is to achieve data empowerment and intelligence improvement through data connectivity, virtual and real interaction, which will ultimately result in a new theory on complex system scheduling.
Funder
National Natural Science Foundation of China
Science and Technology Commission of Shanghai Municipality
Reference15 articles.
1. Key scientific issues and theoretical research framework for power systems with high proportion of renewable energy.;C Kang;Automation of Electric Power Systems.,2017
2. Practice and prospects of intelligent dispatch with Chinese characteristics.;J Yao;Automation of Electric Power Systems.,2009
3. Economic generation scheduling of a microgrid using mixed integer programming.;X Wu;Proceedings of the CSEE.,2013
4. Deep reinforcement learning for scenario-based robust economic dispatch strategy in internet of energy.;D Fang;IEEE Internet Things J.,2020
5. Deep learning based distributionally robust joint chance constrained economic dispatch under wind power uncertainty.;C Ning;IEEE Trans Power Syst.,2021