Equilibrium-inspired multiagent optimizer with extreme transfer learning for decentralized optimal carbon-energy combined-flow of large-scale power systems

详细信息    查看全文

• 作者：Xiaoshun Zhang^a ; Yixuan Chen^a ; Tao Yu^a ; ^{taoyu1@scut.edu.cn} ; Bo Yang^b ; Kaiping Qu^a ; Senmao Mao^c
• 关键词：Equilibrium-inspired multiagent optimizer ; Extreme transfer learning ; Nash equilibrium ; State-action chain ; Decentralized optimal carbon-energy combined-flow
• 刊名：Applied Energy
• 出版年：2017
• 出版时间：1 March 2017
• 年：2017
• 卷：189
• 期：Complete
• 页码：157-176
• 全文大小：4443 K
• 卷排序：189

文摘

A shared responsibility of carbon emission is introduced in decentralized OCECF. An equilibrium-inspired multiagent optimizer is proposed for decentralized OCECF. The Nash game can ensure a self-organizing optimal operation of each agent. The convergence rate can be dramatically accelerated by extreme transfer learning. The carbon emission and power loss of power network can be significantly reduced.