摘要
信息物理社会系统(CPSS)旨在描述复杂网络系统中信息网络、物理系统和社会因素的特征及其交互影响,以实现对该类系统的建模、推理和决策。CPSS研究中,如何反映社会行为是最大难点之一。依据历史和仿真数据,采用生成对抗网络(GAN)模型对不确定的社会行为建模,并通过混合仿真方法推演了当前广东现货电力市场设计中的实际问题,即燃气机组补贴对市场的潜在影响。
Cyber physical social system(CPSS) is applied to describe the characteristics and interactions of cyber space, physical systems and social agents in complex network systems, and it is designed to provide systematic modeling, inference and decision making. Human behavior modeling is a complex problem in CPSS. Based on the historical and simulated data, this paper employs the generated adversarial network(GAN) for uncertain social behavior modeling. Additionally, the hybrid simulation method is applied to derive the practical problem in the Guangdong electricity spot market of China, namely the potential impact of gas unit subsidies on the market.
作者
柳文轩
赵俊华
黄杰
文福拴
吕哲
薛禹胜
LIU Wenxuan;ZHAO Junhua;HUANG Jie;WEN Fushuan;LYU Zhe;XUE Yusheng(The Chinese University of Hong Kong,Shenzhen 518100,China;NARI Group Corporation(State Grid Electric Power Research Institute),Nanjing 211106,China;College of Electrical Engineering,Zhejiang University,Hangzhou 310027,China)
出处
《电力系统自动化》
EI
CSCD
北大核心
2020年第4期8-15,共8页
Automation of Electric Power Systems
基金
国家自然科学基金资助项目（91746118）
深圳市科技创新委员会基础研究项目（JCYJ20170410172224515）~~
关键词
混合仿真
信息物理社会系统
生成对抗网络
电力市场
燃气机组成本补贴
hybrid simulation
cyber physical social system(CPSS)
generated adversarial network(GAN)
electricity market
cost subsidy of gas unit
