 Smart generation control based on multi-agent reinforcement learning with the idea of the time tunnelLei Xi, Jianfeng Chen, Yuehua Huang, Yanchun Xu, Lang Liu, Yimin Zhou and Yudan Li Energy, 2018, vol. 153, issue C, 977-987 Abstract: One of the significant solutions for hazy is to reduce carbon emission by introducing renewable energy on a large scale. However, the large-scale integration of new energy will result in stochastic disturbance to power grid. Therefore it becomes a top priority to make new energy compatible with power system. The PDWoLF-PHC(λ) based on the idea of time tunnel is to be proposed in this paper. Optimal strategy could be obtained by adopting the variable learning rate in a variety of complex operating environments, and thence it can deal with stochastic disturbance caused by massive integrations of new energy and distributed energy sources to the power grid, which is difficult for traditional centralized AGC. The proposed algorithm is simulated to be effective according to the improved IEEE standard two-area load-frequency control power system model and the Central China Power Grid model. Compared with the traditional smart ones, the proposed algorithm is characterized with faster convergence and stronger robustness, which makes it able to reduce carbon emission and enhance utilization rate of the new energy. Keywords: Automatic generation control; PDWoLF-PHC; Multi-agent; Carbon emission (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:153:y:2018:i:c:p:977-987 DOI: 10.1016/j.energy.2018.04.042 Access Statistics for this article Energy is currently edited by Henrik Lund and Mark J. Kaiser More articles in Energy from Elsevier |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.