首页|基于数字孪生的配电网过载风险评估优化仿真

基于数字孪生的配电网过载风险评估优化仿真

扫码查看
随着配电网技术的快速发展,电力传输的压力逐渐增加,检修工作人员对配电网进行过载风险评估的需求也日益提升。为解决当前风险评估算法准确率低、时效性差等问题,提出基于数字孪生的配电网综合过载风险评估算法。算法首先使用数字孪生技术构建配电网过载风险评估体系,将电网实体与虚拟平台进行实时同步,提高监控与操作的时效性;然后采用马尔科夫算法计算过载风险概率,将配电网各部分风险进行加权求和,并利用蒙特卡洛算法评估综合风险指标;最后将过载风险与综合风险进行过载风险态势表征,提高配电网过载风险评估的准确能力。实验结果表明,较其它基线模型相比,在风险评估方面,新构建的模型其性能提升了4。28%,有效地提高了配电网过载风险评估的准确率,提高了配电网的安全性。电网实体与虚拟平台的结合提高了工作人员配置电网的时效性。
Optimal Simulation of Overload Risk Assessment in Distribution Network Based on Digital Twins
With the rapid development of distribution network technology,the pressure of power transmission is gradually increasing,and the demand of maintenance staff for overload risk assessment of distribution network is also increasing.In order to solve the problems of low accuracy and poor timeliness of current risk assessment algorithms,this paper proposes a distribution network comprehensive overload risk assessment algorithm based on digital twins.Firstly,the algorithm uses digital twinning technology to build the distribution network overload risk assessment sys-tem,which synchronizes the grid entity and virtual platform in real time,and improves the timeliness of monitoring and operation;Then,Markov algorithm is used to calculate the overload risk probability,and the risk of each part of the distribution network is weighted and summed,and Monte Carlo algorithm is used to evaluate the comprehensive risk index;Finally,the overload risk and comprehensive risk are represented to improve the accuracy of the overload risk assessment of the distribution network.The experimental results show that compared with other baseline models,in terms of risk assessment,the performance of the model built in this paper has improved by 4.28%,effectively impro-ving the accuracy of distribution network overload risk assessment,improving the security of distribution network,and the combination of grid entities and virtual platforms has improved the timeliness of staff configuration of the grid.

Digital twinsDistribution networkRisk assessmentMonte Carlo method

李瑞、刘珊、周自强、祗会强

展开 >

国网山西省电力公司电力科学研究院,山西 太原 030001

太原理工大学,山西 太原 030021

数字孪生 配电网 风险评估 蒙特卡洛法

国网山西省电力公司科技项目资助

52053022000C

2024

计算机仿真
中国航天科工集团公司第十七研究所

计算机仿真

CSTPCD
影响因子:0.518
ISSN:1006-9348
年,卷(期):2024.41(6)
  • 8