1. This article proposes a data and model hybrid driven two-layer optimization scheduling decision method for regional comprehensive energy systems.
2. The upper layer uses a mix integer linear programming (MILP) to solve the daily scheduling plan, while the lower layer combines convolutional neural network (CNN) and gated recurrent unit (GRU) for daily rolling optimization decisions.
3. The effectiveness of this proposed method is verified through case studies.
The article is generally reliable and trustworthy as it provides detailed information about the proposed method, including its components, how it works, and how its effectiveness is verified through case studies. However, there are some potential biases that should be noted. For example, the article does not provide any counterarguments or explore alternative solutions to the proposed method. Additionally, there is no discussion of possible risks associated with using this method or any potential drawbacks that could arise from its implementation. Furthermore, the article does not present both sides of the argument equally; instead, it focuses solely on promoting the benefits of this proposed method without providing an equal amount of attention to potential drawbacks or risks associated with it.