N-1状态下潮流不收敛问题对N-1校验和电网的安全运行造成极大困扰,但当前的潮流收敛研究主要集中于静态潮流,且调整方法不仅动作有效性低,也难以兼顾快速性和成功率。因此提出一种基于BNN-DS的DDPG改进算法,通过深度强化学习对N-1潮流不收敛网络进行智能调整。首先,根据N-1方案校验元件类型及潮流重载量等指标确定了方案的调整措施,通过广度优先算法确定调整元件组以保证动作的有效性,根据CRITIC权重法计算了多重奖励之和,据此,设计了N-1潮流收敛调整MDP模型。其次对MDP模型中所用DDPG算法进行改进,搭建了轻量BNN网络以降低计算复杂度、提高计算速度,设计了高奖励经验池以及存量判定机制以优化模型的收敛性。最后,在某分部2 179节点网络和某分部12 732节点网络上对改进算法进行测试验证,结果表明基于BNN-DS的DDPG改进算法比传统方法的成功率提高36.535%
平均用时减少95.01%。
The problem of non-convergence in N-1 power flow poses great challenges to N-1 verification and the safe operation of power grid. However
current research on power flow convergence mainly focuses on static power flow
and existing adjustment methods suffer from low effectiveness
making it difficult to balance speed and success rate. Therefore
we propose an improved DDPG algorithm based on BNN-DS
which intelligently adjusts the N-1 power flow non-convergence scenarios through deep reinforcement learning. Firstly
we determine the adjustment measures for the N-1 scenario based on indicators such as the type of verified components and the overload of the power flow. Then
we determine the adjustment component group to ensure the effectiveness of the action by the breadth first algorithm
and calculate the sum of multiple rewards based on the CRITIC weight method. Based on this
we design the N-1 power flow convergence adjustment MDP model. Secondly
we improve the DDPG algorithm used in the MDP model
build a lightweight BNN network to reduce computational complexity and improve computational speed
and design a high reward experience pool and stock determination mechanism to optimize the convergence of the model. Finally
we test and validate the improved algorithm on a 2 179 node network and a 12 732 node network of a certain branch. The results show that the improved DDPG algorithm based on BNN-DS achieves a 36.535% increase in success rate and a 95.01% reduction in average time compared to traditional methods.
黄河凯.基于知识图谱的大电网潮流计算收敛自动调整方法研究[D].哈尔滨工业大学,2021(03).
Xu Jian,Zhang Haifei,Qiu Jianlin.A deep deterministic policy gradient algorithm based on averaged state-action estimation[J].Computers and Electrical Engineering,2022.
Yifan Li,Yuchun Fang,Zahid Akhtar.Accelerating deep reinforcement learning model for game strategy[J].Neurocomputing,2020.
Ruelens Frederik,Claessens Bert J.,Vandael Stijn,De Schutter Bart,Babuska Robert,Belmans Ronnie.Residential Demand Response of Thermostatically Controlled Loads Using Batch Reinforcement Learning[J].IEEE Transactions on Smart Grid,2017.
张波,高远,李铁成,胡雪凯,贾焦心.考虑光伏电源可靠性的新能源配电网数据驱动无功电压优化控制[J].中国电机工程学报,2024(15).
李建标,陈建福,高滢,裴星宇,吴宏远,陆子凯,周少雄,曾杰.基于RG-DDPG的直流微网能量管理策略[J].中国电力,2023(07).
王一迪,李立新,於益军,杨楠,刘蒙,李桐.基于深度强化学习的电力系统安全校正控制[J].电力系统自动化,2023(12).
刘怀远,文晶,陈兴雷,黄河凯,王甜婧,王宏志,黄彦浩,汤涌,杨东华.知识驱动的大电网仿真分析知识建模方法及其在潮流智能调整问题中的应用[J].中国电机工程学报,2023(05).
宣鹏华,李岩松,龚承霄,陈兴雷,刘君.基于降维粒子群的大电网断面功率极限计算方法[J].华北电力大学学报(自然科学版),2024(04).
曾泓泰,郭庆来,周艳真,孙宏斌,刘明松,杨滢.面向电网运行方式计算的不收敛潮流无功调整方法[J].电力系统保护与控制,2022(19).
张沛,朱驻军,谢桦.基于深度强化学习近端策略优化的电网无功优化方法[J].电网技术,2023(02).
龚承霄,李岩松,刘君,黄彦浩,陈兴雷,文晶.基于深度学习的大电网断面功率快速自动调整方法[J].电力系统自动化,2023(02).
陈一丰,唐坤杰,董树锋,宋永华.输配一体化潮流计算收敛性分析及提升方法[J].中国电机工程学报,2022(20).
王甜婧,汤涌,郭强,黄彦浩,陈兴雷,黄河凯.基于知识经验和深度强化学习的大电网潮流计算收敛自动调整方法[J].中国电机工程学报,2020(08).
张松涛,张东霞,黄彦浩,李文臣,陈兴雷,汤涌.基于改进直流潮流算法的潮流计算收敛自动调整方法研究[J].电网技术,2021(01).
杨燕,杨知方,余娟,向明旭,余红欣,王洪彬.基于深度学习的含不确定性N-1安全校核方法[J].中国电机工程学报,2021(08).
安军,宋俊达,葛维春.大规模电力系统潮流计算收敛性诊断与调整方法[J].电力自动化设备,2020(02).
张自东,邱才明,张东霞,徐舒玮,贺兴.基于深度强化学习的微电网复合储能协调控制方法[J].电网技术,2019(06).
唐坤杰,董树锋,宋永华,朱炳铨.基于GPU加速的大规模系统N-1安全校验中电网连通性的检验方法[J].中国电机工程学报,2018(18).
彭慧敏,李峰,袁虎玲,鲍颜红.大规模电网运行方式调整潮流计算及病态诊断[J].电力系统自动化,2018(03).
李敏,陈金富,陈海焱,段献忠.一类潮流计算无解的实用性调整研究[J].电力系统自动化,2006(08).
0
浏览量
122
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621