April 2025
·
4 Reads
To achieve the low carbon optimization in hydrogen-based integrated energy system(HIES), this paper proposes a dynamic carbon emissions optimization method for HIES based on cloud-edge collaborative CBAM-BiLSTM-PSO network. Firstly, based on the theory of carbon emission flow, the carbon emissions in HIES are converted from the source to multiple energy load nodes, and a dynamic carbon reduction model for HIES is established. The HIES source load coordinated carbon reduction is achieved by setting the edge objective function at the load and the cloud objective function. And by setting noise sources to correlate the relationship between input variables and decision variables, uncertainty embedding of the objective function is achieved. Then, a cloud-edge collaborative computing network is established to achieve the prediction of new energy power output and multi-energy load consuming as well as scheduling plan solving. Convolutional block attention module (CBAM) is used to strengthen key feature data and fuse heterogeneous data. The particle swarm algorithm (PSO) is combined with the bidirectional long short-term memory network (BiLSTM) to form the CBAM-BiLSTM-PSO solving algorithm, which realizes the solution of HIES source load coordinated carbon emission reduction plan. Finally, the method proposed in this paper was validated using actual running HIES as an example. The results showed that the proposed method can effectively extract the operating characteristics of equipment within HIES, achieve coordinated optimization of carbon reduction, and reduce the carbon emissions of HIES. Compared with other models, the training time of this model is shortened and the accuracy is improved, providing a feasible solution for the data-based low-carbon operation of HIES.