Combined Real and Reactive Power Economic Dispatch using Multi-Objective Reinforced Learning with Optimized Losses
Date
2015Author
Musau, Moses Peter
Abungu, Nicodemus Odero
Wekesa, Cyrus Wabuge
Type
ArticleLanguage
enMetadata
Show full item recordAbstract
Most of the economic dispatch (ED) works so far deal with real power dispatch only. With the integration of renewable
energy into the grid, reactive power dispatch cannot be ignored any longer due to its importance in providing security and reliability in
power system planning, operation and control. This paper deals with the formulation of combined real and reactive economic dispatch
(CRRED) subject to equality, inequality and stochastic constraints. An effective algorithm that uses a hybrid of distributed slack bus
(DSB) formulated using combined participation factors (PF) and multi objective reinforcement learning (MORL) is proposed in this
paper. The IEEE 14 Bus was used to validate the effectiveness of the proposed CRRED formulation and Hybrid method .The
numerical results obtained show that combining real and reactive power results in a 0.95% decrease in the overall generation cost as
compared to a case in which only real power is considered. Further, when the losses are distributed in the entire network using the
DSB, then the overall generation cost is reduced by 29.6% due to the reduced losses in DSB model.
Citation
IJSRP, Volume 5, Issue 10, October 2015Subject
Combined Real and Reactive Economic Dispatch (CRRED)Distributed Slack Bus (DSB), Participation Factors (PF)
Reinforcement Learning (RL)
Rights
Attribution-NonCommercial-NoDerivs 3.0 United StatesUsage Rights
http://creativecommons.org/licenses/by-nc-nd/3.0/us/Collections
The following license files are associated with this item: