摘要
可再生能源出力的波动性、间歇性、用户电力负荷的随机不确定性,使微电网的能量调度极具挑战性.为此,该文提出激励竞争双深度Q网络(motivation dueling double deep Q-network,简称MD3QN)算法,对微电网能量进行协调优化.仿真分析结果表明:采用MD3QN算法对微电网进行能量调度,能实现削峰填谷,使微电网的经济效益最大化;相对于其他4种算法,MD3QN算法具有更高的综合性能.因此,MD3QN算法具有有效性.
The volatility and intermittency of renewable energy output,and the stochastic uncertainty of customer power loads make energyscheduling for microgrids very challenging.Thus,to coordinate and optimize microgrid energy scheduling,a motivation dueling double deep Q-network(MD3QN)algorithm was proposed in this paper.Simulation analysis results demonstrated that the MD3QN algorithm for microgrids energy scheduling could obtain maximum economic benefit,and the peak shaving and valley filling of microgrids was achieved.Compared with the other four algorithms,the MD3QN algorithm had a higher composite performance.Therefore,the MD3QN algorithm was effective.
作者
李小豹
赵婵娟
程志友
徐恒
LI Xiaobao;ZHAO Chanjuan;CHENG Zhiyou;XU Heng(School of Internet,Anhui University,Hefei 230039,China;School of Electronic and Information Engineering,Anhui Jianzhu University,Hefei 230601,China)
出处
《安徽大学学报（自然科学版）》
CAS
北大核心
2024年第2期46-52,共7页
Journal of Anhui University(Natural Science Edition)
基金
安徽省自然科学基金资助项目(2108085QE237,2208085UD01)
安徽省教育厅自然科学重点项目(2023AH050104)
安徽建筑大学安徽省古建筑智能感知与高维建模国际联合研究中心开放课题基金资助项目(GJZZX2021KF03)。
关键词
并网型微电网
能量管理
MD3QN
实时电价激励机制
grid-connected microgrid
energymanagement
MD3QN
real-time electricity price incentive mechanism
