摘要
对含有光伏、风机、柴油发电机以及微燃气轮机组成的微电网系统进行研究,建立了基于经济和环境双重目标的微电网优化模型,并使用遗传优化神经网络的方法来预测不可控电源的出力以及负荷的需求,将预测的数据代入模型,并使用交替方向乘子法(ADMM)进行求解。将此优化结果与多目标粒子群算法(MOPSO)以及多目标遗传算法(NSGA-Ⅱ)优化结果进行对比,结果表明,ADMM算法具有更高的收敛精度与收敛速度,所得的解决方案更好,验证了所提模型与算法的合理性。
The micro-grid system consisting of photovoltaic,fan,diesel generator and micro gas turbine is studied.A micro-grid optimization model based on economic and environmental objectives is established.The genetic optimization neural network is used to predict the output of uncontrollable power supply and the load demand.The predicted data are substituted into the model,and the alternating direction multiplier method(ADMM)is used to solve the problems.The optimization results are compared with those obtained by the multi-objective particle swarm optimization(MOPSO)and multi-objective genetic algorithm(NSGA-II)optimization.The results show that the ADMM algorithm has higher convergence precision and convergence speed,and the obtained solution is better.The rationality of the proposed model and algorithm is verified.
作者
邝凯旋
张赟宁
KUANG Kaixuan;ZHANG Yunning(College of Electrical Engineering and New Energy,China Three Gorges University,Yichang 443002,China)
出处
《电力科学与工程》
2019年第8期54-59,共6页
Electric Power Science and Engineering
关键词
微电网
多目标优化
神经网络
ADMM算法
micro-grid
multi-objective optimization
neural network
ADMM algorithm
