Research on low carbon economic dispatch of integrated energy system based on source-grid-load-storage collaboration
•The integrated strategy of source network load and storage optimization is adopted.•A comprehensive optimization method of step demand response incentive is proposed.•An adaptive optimization step demand response mechanism is proposed.•Integrate deep learning and intelligent control to reduce predi...
Saved in:
| Published in: | Energy and buildings Vol. 349; p. 116434 |
|---|---|
| Main Authors: | , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier B.V
15.12.2025
|
| Subjects: | |
| ISSN: | 0378-7788 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | •The integrated strategy of source network load and storage optimization is adopted.•A comprehensive optimization method of step demand response incentive is proposed.•An adaptive optimization step demand response mechanism is proposed.•Integrate deep learning and intelligent control to reduce prediction error.
To reduce the impact of the weak stability of renewable energy, fully invoking the flexible load resources on the load side, and achieving low carbon economic dispatch of integrated energy systems, this paper proposes an optimization approach with source-grid-load-storage collaboration. Firstly, deep learning was used to build the next moment of wind power and photovoltaic prediction model. Based on this model, predictive control functions for wind and photovoltaic power generation are established from the objective function optimization-seeking perspective. Secondly, combining the coupling relationship and flexibility characteristics with the energy conversion of electric, heat, and cool loads, a stepped demand response incentive mechanism is introduced, and adaptive optimization is carried out for three parameters: compensation base price, interval length, and price growth rate. Finally, a multi-objective optimization model of the integrated energy system is developed by combining the different interests of the supply and load sides, solved by the multi-objective grey wolf optimization algorithm. Compared with the system optimized by a single multi-objective grey wolf optimization algorithm, the total cost and carbon emission reduction rates during the system optimization period were 8.89 % and 6.29 %, respectively. |
|---|---|
| ISSN: | 0378-7788 |
| DOI: | 10.1016/j.enbuild.2025.116434 |