Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Fault diagnosis, service restoration, and data loss mitigation through multi-agent system in a smart power distribution grid
Energy Sources, Part A: Recovery, Utilization, and Environmental Effects ( IF 2.9 ) Pub Date : 2020-09-16 , DOI: 10.1080/15567036.2020.1817190
Ishan Srivastava 1 , Sunil Bhat 1 , Arvind R. Singh 2
Affiliation  

Smart power distribution grid is equipped with different sensors and smart meters for getting measurements at different nodes. Additionally, for monitoring and control purpose Intelligent Electronic Devices (IEDs) are also installed. On the occurrence of fault in the grid, power utility implement a Fault Detection, Isolation and Restoration (FDIR) scheme to restore the power in healthy section of the network, this process is known as Service Restoration (SR). In the existing scenario, a centralized control scheme is used for monitoring and control of distribution grid. This control scheme is slow in terms of deployment of FDIR plan. So, the authors propose a multi-agent-based de-centralized control scheme for FDIR. For this multi-agent system, different agents are defined to perform tasks of fault detection, fault isolation, and restoration. Also, the aspect of communication among agents is presented and to tackle data loss problem, a Compressive Sensing (CS) based technique is applied. A novel Support Vector Machine (SVM) approach is proposed for fault classification. For SR, a Non-Dominated Sorting Genetic Algorithm-II (NSGA-II) based method is used and is validated through its application for different fault scenarios in an IEEE 69 bus test system. Also, for testing of data loss mitigation agent, a real-time Phasor Measurement Unit (PMU) data is taken. The whole framework is designed in a python-based Smart Python Agent Development Environment (SPADE) and the related computation is done using MATLAB.



中文翻译:

通过智能配电网中的多代理系统进行故障诊断,服务恢复和数据丢失缓解

智能配电网配备了不同的传感器和智能电表,用于在不同节点进行测量。此外,出于监视和控制目的,还安装了智能电子设备(IED)。在电网中发生故障时,电力公司会实施故障检测,隔离和恢复(FDIR)方案,以恢复网络的健康部分的电力,此过程称为服务恢复(SR)。在现有方案中,集中控制方案用于监视和控制配电网。就FDIR计划的部署而言,此控制方案很慢。因此,作者提出了一种基于多主体的FDIR分散控制方案。对于此多主体系统,定义了不同的主体来执行故障检测,故障隔离和恢复的任务。也,提出了代理之间的通信方式,并针对数据丢失问题,应用了基于压缩感知(CS)的技术。提出了一种新颖的支持向量机(SVM)方法进行故障分类。对于SR,使用了一种基于非支配排序遗传算法II(NSGA-II)的方法,并已通过其在IEEE 69总线测试系统中针对不同故障场景的应用进行了验证。另外,为测试数据丢失缓解代理,需要获取实时相量测量单元(PMU)数据。整个框架是在基于python的Smart Python Agent开发环境(SPADE)中设计的,相关的计算是使用MATLAB进行的。提出了一种新颖的支持向量机(SVM)方法进行故障分类。对于SR,使用了一种基于非支配排序遗传算法II(NSGA-II)的方法,该方法已通过在IEEE 69总线测试系统中针对不同故障场景的应用进行了验证。另外,为了测试缓解数据丢失的代理,需要获取实时相量测量单元(PMU)数据。整个框架是在基于python的Smart Python Agent开发环境(SPADE)中设计的,相关的计算是使用MATLAB进行的。提出了一种新颖的支持向量机(SVM)方法进行故障分类。对于SR,使用了一种基于非支配排序遗传算法II(NSGA-II)的方法,该方法已通过在IEEE 69总线测试系统中针对不同故障场景的应用进行了验证。另外,为了测试缓解数据丢失的代理,需要获取实时相量测量单元(PMU)数据。整个框架是在基于python的Smart Python Agent开发环境(SPADE)中设计的,相关的计算是使用MATLAB进行的。

更新日期:2020-09-16
down
wechat
bug