Title :
Unit Commitment Scheduling Using a Hybrid ANN and Lagrangian Relaxation Method
Author :
Liu, Zhen ; Li, Na ; Zhang, Chaohai
Author_Institution :
Grad. Sch. of Eng., Nagasaki Inst. of Appl. Sci., Nagasaki
Abstract :
A hybrid artificial neural network (ANN) Lagrangian relaxation approach to combinatorial optimization problems in power systems, in particular to unit commitment is presented in this paper. Until now, the Lagrangian relaxation method has been studied as it appeared to be the most practical method for obtaining an approximate solution to unit commitment. Based on the use of supervised learning neural-net technology and the adaptive pattern recognition concept, which presume the relationship between power demand pattern and Lagrange multipliers (LMPs). The numerical results obtained are very encouraging.
Keywords :
learning (artificial intelligence); neural nets; power engineering computing; power generation scheduling; Lagrange multiplier; Lagrangian relaxation; adaptive pattern recognition; combinatorial optimization; hybrid artificial neural network; power demand pattern; power system; supervised learning neural-net technology; unit commitment scheduling; Artificial neural networks; Cost function; Demand forecasting; Hybrid power systems; Lagrangian functions; Power demand; Power generation; Power system planning; Processor scheduling; Relaxation methods; Lagrangian relaxation method; artificial neural networks; unit commitment;
Conference_Titel :
Multimedia and Ubiquitous Engineering, 2008. MUE 2008. International Conference on
Conference_Location :
Busan
Print_ISBN :
978-0-7695-3134-2
DOI :
10.1109/MUE.2008.116
