AUTHOR=Wei-Jie Tang , Hai-Tao Wang , Ping-Ji Liu , Feng-Lei Qian TITLE=Combustion Optimization Under Deep Peak Shaving Based on DYNA-A3C With Dynamic Weight JOURNAL=Frontiers in Energy Research VOLUME=Volume 10 - 2022 YEAR=2023 URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2022.953387 DOI=10.3389/fenrg.2022.953387 ISSN=2296-598X ABSTRACT=The combustion process of boilers under deep peak shaving conditions is a multivariate process with big data, and has complex characteristics such as super multivariable, nonlinear and large lag. It is difficult to handle complex data and calculate appropriate distributed results. To this end, this paper applies using the A3C method based on the dynamic weight DYNA-structure to the boiler combustion system. This method trains and optimizes the boiler combustion system by establishing a data center, designing appropriate states and reward values, and the simulation results show that this method is used to optimize the boiler combustion system. It can effectively reduce NOX emissions and improve boiler combustion efficiency.