摘要
在分析太阳能、风能、海洋能、地热能等能源特点的基础上,提出了多能源混合供电的系统结构,建立了基于神经网络的控制模型,提出了多能源混合供电控制策略。在对神经网络训练时采用Levenberg-Marquaret算法,并引入动量因子α,加快了收敛速度和防止了振荡。仿真结果表明该策略是有效的,在最大限度地使用可再生能源的前提下,交流微网输出电压持续、稳定、不间断,能够满足交流微网内用户用电需要。
A system structure of multi-energy hybrid power supply is proposed by analyzing the characteristics of solar energy,wind energy,o cean energy and geothermal energy.The control model based on neural netowork is established,and the control strategy for multi-energy hybrid power syupply is proposed.In order to accelerate the convergence and to prevent oscillation.Levenberg-Marquaret algorithm is used and the momentum factor α is introduced in the training.Simulation shows that this strategy can make the voltage sustained,stable and continuous in the maximum use of renewable energy,which can satisfy customers＇ electricity need.
出处
《电力系统保护与控制》
EI
CSCD
北大核心
2010年第20期141-144,147,共5页
Power System Protection and Control
基金
国家自然科学基金项目(60804026)
上海海事大学博士生创新基金项目(yc2009104)~~
关键词
神经网络
多能源
混合供电
共直流母线
neural network
multi-energy
hybrid power supply
common DC bus
