Power Distribution Outage Cause Identification With Imbalanced Data Using Artificial Immune Recognition System (AIRS) Algorithm

Power distribution systems have been significantly affected by many fault causing events. Effective outage cause identification can help expedite the restoration procedure and improve the system reliability. However, the data imbalance issue in many real-world data often degrades the outage cause identification performance. In this paper, artificial immune recognition system (AIRS), an immune-inspired algorithm for supervised classification task is applied to the Duke Energy outage data for outage cause identification using three major causes (tree, animal, and lightning) as prototypes. The performance of AIRS on these real-world imbalanced data is compared with an artificial neural network (ANN). The results show that AIRS can greatly improve the performance by as much as 163% when the data are imbalanced and achieve comparable performance with ANN for relatively balanced data     

Power Distribution Fault Cause Identification With Imbalanced Data Using the Data Mining-Based Fuzzy Classification E-Algorithm

Power distribution systems have been significantly affected by many outage-causing events. Good fault cause identification can help expedite the restoration procedure and improve the system reliability. However, the data imbalance issue in many real-world data sets often degrades the fault cause identification performance. In this paper, the E-algorithm, which is extended from the fuzzy classification algorithm by Ishibuchi to alleviate the effect of imbalanced data constitution, is applied to Duke Energy outage data for distribution fault cause identification. Three major outage causes (tree, animal, and lightning) are used as prototypes. The performance of E-algorithm on real-world imbalanced data is compared with artificial neural network. The results show that the E-algorithm can greatly improve the performance when the data are imbalanced     

An alternative approach to fault location on power distribution feeders with embedded remote-end power generation using artificial neural networks

In this paper, the design and implementation of a feed-forward artificial neural network (ANN)-based fault locator to classify and locate shunt faults on primary overhead power distribution lines with load taps and embedded remote-end power generation is presented. In the ANN algorithm, the standard back-propagation technique with a sigmoid activation function is used. The fault locator utilizes fault voltage and current samples obtained at a single location of a typical radial distribution system. The ANNs are trained with data under a wide variety of fault conditions and used for the fault type classification and fault location on the distribution line. A 34.5?kV distribution system is simulated using electro-magnetic transients program and their results are used to train and test the ANNs. The ANN-based fault locator gives high accuracy for the vast majority of the practically encountered systems and fault conditions, including the presence of load taps and the remote-end in-feed source.     

基于节点阻抗矩阵和电压暂降的故障定位新方法

配电网线路发生故障时,将导致用户停电,直接影响供电连续性和可靠性,及时准确的故障定位对及时排除故障,缩短停电时间,提高供电质量有重要意义。当线路发生故障时,一方面将在全系统内引起电压暂降,给系统内的敏感负荷带来损失;另一方面,利用该特征可识别故障类型并判断故障位置,为此提出利用电压暂降数据识别故障类型,基于节点阻抗矩阵实现配电网故障定位的新方法,并结合网络参数和离线仿真分析,建立不同故障类型和故障情况下的节点电压数据库,当检测到故障后,将采集到的电压暂降数据在节点电压数据库中进行搜索匹配,确定故障区间和故障点。该方法直接利用搜索结果确定故障位置,不用增加其它算法或变换,原理简单,计算迅速。最后,利用电力系统计算机辅助设计（power system computer aided design,PSCAD）仿真软件和实验室搭建实际电路进行测试,验证所提方法的正确性和可靠性。     

台风灾害下配网用户停电数量预测最优数据驱动模型选择

严重的台风灾害可能导致配网用户停电,有效的配网用户停电数量预测可为电网应急抢修提供辅助指导。综合考虑气象因素、电网因素及地理因素,提出了基于机器学习回归算法的配网用户停电数量预测方法。分析比较了线性回归、支持向量回归(SupportVectorRegression,SVR)、分类回归树(ClassificationandRegressionTree,CART)、梯度提升树(Gradient Boosting Decision Tree, GBDT)及随机森林(Random Forest, RF)等5种机器学习回归算法对配网用户停电数量预测的应用效果。对比结果表明,LR在进行配网用户停电数量预测时表现较差,SVR及CART模型效果次之,RF及GBDT效果相对较好,其中GBDT算法与RF算法误差较为接近。但考虑到GBDT算法为串行计算,而RF算法为并行计算,使用时RF算法效率更高。因此最终选取了RF进行停电数量预测效果的进一步分析。结果表明其误差在±30%以内的准确率可达70%以上,可为配网用户停电抢修提供有力指导。     

省级配电自动化主站的停电信息资源池功能设计

各地配电自动化建设尚处于大规模试点阶段,很多区域的故障信息感知和定位手段有限,不同性质的停电事件信息又来源于多个业务系统,在条件有限的情况下实现停电事件精准分析的需求尤为迫切。文中结合电力公司的停电管理实际业务流程,设计停电信息资源池功能,综合分析变电站、馈线、台区、用户多层主网和配电网数据,在分层分级研判基础上建立信号可信度模型。结合DS证据理论算法融合分析,多维度灵活地挖掘分析停电事件,提高故障点定位的容错性,满足在差异化场景下构建可靠的结构化停电信息资源池实现数据的共享发布。     

基于数据关联分析的低压配电网拓扑识别方法

文中介绍了一种基于数据关联分析的低压配电网拓扑识别方法。基于低压配电网停电事件、恢复上电事件及地理位置信息将待识别低压配电网划分为单一配电变压器停电台区、由于10kV配电线路停电引起的多个配变停电台区和未停过电台区,在每类台区内筛选特征电压序列,并利用Tanimoto相似度系数计算各分组内配电变压器、分支箱、表箱、用户智能电表之间相关性和非相关性,从而实现低压配电网拓扑识别;结合同一配电变压器台区内停电与带电状态、停电时长、地理位置、供电半径等台区拓扑校验规则对识别出的拓扑进行校验。通过实际案例证明文章提出的方法能够解决现有基于大数据挖掘方法计算量大、计算结果不准确、无法校验等问题,实现了配电变压器台区拓扑的高效、准确识别,提升了配电网的信息化水平和数据质量。     

Development of reliability analysis system of transmission network for primary substations

This paper describes the development of the reliability analysis system for transmission systems from primary substations on high-voltage trunk line systems to distribution substations. This system has been developed on an engineering workstation. The user can input the network data of power systems from primary substations to distribution substations and the structure of buses and connections of transformers in substations using graphics. This analysis system can evaluate reliability at each distribution substation by simulating outage and recovery process for all fault modes which can occur, defining the capacity of facilities, probability of fault at each facility, the value of load at each bank, and the points where switching elements are turned off in the network as input data. In the calculation of the recovery process of each fault mode, the constraints of operation of radial power systems are considered.     

Development of an expert system for analyzing faults in power systems based on waveform recognition by artificial neural networks

In restoration of a power system, appropriate steps need to be taken in early stages to avoid damage to the public caused by insufficient power supply. The first step in the restoration is the analysis of the fault that has produced the power failure. Today, a large amount of data will be available at the occurrence of a fault due to the use of advanced communication systems using digital relays and optical fibers. Such systems are intended to obtain data from the relays and circuit breakers (CBs) under operation and the voltage and current during operation and the prefault and postfault periods. This paper presents a hybrid fault analyzing expert system using data based on protective devices and phasor measurement. This system is a combination of an artificial neural network (ANN) and an expert system (ES). The ANN is used to simplify the analysis of current and voltage waveforms, which is considered difficult due to the presence of a fault resistance and the line impedance. Since a fault waveforms contains various ambiguous factors depending on the nature of the fault resistance, load current and other system parameters, the use of ANN is effective making such determinations.     

配电网停电管理系统的研究分析

随着配电系统设备的日益增多,设备种类也日趋繁杂,因此配电网的操作人员要在最短的时间内找出故障设备,以恢复供电是相当困难而且很费时的。为了能够准确而又快速地找出故障点,以便系统维修人员抢修,及早恢复供电,许多电力公司正在考虑为其配电网安装停电管理系统。因此研制和开发一个功能强大且可以升级的停电管理系统提到了电力行业的日程中来。针对配网停电管理系统的应用进行了深入的研究和分析。     

考虑负荷重分配攻击的电力系统运行可靠性评估

负荷重分配(load redistribution, LR)攻击对线路的实时停运模型和最优负荷削减模型均会产生影响。现有研究忽略LR攻击对线路实时停运模型的影响,因此无法准确反映LR攻击下的电力系统运行风险。为此,分析了LR攻击原理,建立了考虑LR攻击对线路实时停运和系统最优负荷削减双重影响的运行可靠性模型。并提出了考虑LR攻击双重影响的电力系统运行可靠性评估方法。以IEEE14节点修改系统为例进行算例分析。算例结果表明：LR攻击对系统运行人员的调度行为会产生较大影响,LR攻击下运行人员非最优调度引起的负荷削减量与攻击资源数目有关;LR攻击可能导致部分线路的实时停运概率增加,从而使得系统实时运行可靠性降低。该研究能为信息物理融合电力系统的规划设计和调度运行提供参考。     

SVM在中压配网停电事件补全中的应用研究

应用大数据平台深入挖掘计量数据对配电网的运行支撑是当前电网重要研究方向,文中应用支持向量机(SVM)算法研究中压配网停电事件补全方法,解决停电事件准确统计难题。首先总结中压配电网的5类停电事件,接着重点研究了SVM补全方法,给出停电事件补全思路,5类停电事件的SVM补全模型构建方法,并提出了涵盖配电网模型构建、SVM模型构建、SVM求解及故障类型判断的补全流程,然后从工程应用角度,设计了补全模块与用电信息采集等各相关系统间的业务关系框架并进行数据分析架构设计。最后以安徽黄山等4家地市公司为例进行了实践应用分析,验证了文中研究方法可极大提升停电事件统计的及时性和准确性。     

Asset maintenance planning in electric power distribution network using statistical analysis of outage data

The problems faced by electric power utilities in developing countries today is that the power demand is increasing rapidly whereas the supply growth is constrained by aging generating and distributing assets, scarce resources for constructing new ones and other societal issues. This has resulted in the need for constructing new additional generating plants and a more economic ways of planning and maintaining existing Generating and Electric power distribution assets. System planning and maintenance that is based on reliability – centred asset management approach had been adopted in this paper.Maintenance of critical asset is an essential part of asset management in distribution network. In most Electric utilities, planning for maintenance constitutes an essential parts of asset management. In this paper, an enhanced RCM methodology that is based on a quantitative statistical analysis of outage data Performed at system/component level for overall system reliability was applied for the identification of distribution components critical to system reliability. The conclusion from this study shows that it is beneficial to base asset maintenance management decisions on processed, analyzed and tested outage data.     

小电流接地系统接地型早期故障扰动特征分析

早期故障用于描述系统中不会导致继电保护动作的瞬时性自恢复故障扰动。基于对早期故障扰动的检测识别可实现对配网的故障预测和预警,对于提升供电可靠性有重要意义。受中性点接地方式影响,小电流接地系统中早期故障将有不同表现形式。针对小电流接地系统特点及其运行要求,分别从等效电路及仿真建模两方面,对该类系统中接地型早期故障的表现形式及其电气量变化特征进行了分析和总结。结果表明,小电流接地系统中接地型早期故障分为"单相接地型"和"异名相两点接地型",同时总结了各种情况下早期故障扰动波形的变化特征。仿真和部分现场故障录波数据证明了分析结论的正确性,研究结论将为小电流接地系统早期故障检测识别及故障预测预警提供重要理论支撑。     

粗糙集理论在电力系统中的应用

粗糙集理论是一种较新的软计算方法,可以有效地分析和处理不完备信息。近几年来,该理论日益受到国际学术界的重视,已在模式识别、预测建模、医疗诊断、决策分析等许多领域得到成功的应用。粗糙集理论在电力系统中的研究起步较晚,目前尚鲜见实际应用的报道。为了进一步推动粗糙集理论在电力系统广泛和深入地应用,文中综述了近年来粗糙集理论在电力系统设备故障诊断、配电网故障诊断、暂态稳定评估、电压无功控制、数据挖掘等方面应用研究的主要成果与方法。探讨了粗糙集理论在电力市场数据挖掘中的巨大潜力,以及与专家系统、人工神经网络、模糊理论和多代理系统等其他人工智能技术的相互结合问题,并提出了若干需要进一步研究的问题。     

基于分块技术的用户停电损失估算方法研究

介绍了停电损失的概念及影响因素．引入分块技术将配电网分块．并确定故障停电事件发生后各分块负荷点的类型;提出根据负荷点停电类型分别确认各分块区域的停电持续时间．结合综合用停电损失函数计算各分区的用户停电损失．最后汇总估算系统的用户停电损失．与传统的用户停电损失估算结果比较．证明了该方法的有效性。     

Artificial neural network based fault diagnostic system for electric power distribution feeders

This paper describes the development of a fast, efficient, artificial neural network (ANN) based fault diagnostic system (FDS) for distribution feeders. The principal functions of this diagnostic system are: (i) detection of fault occurrence, (ii) identification of faulted sections, and (iii) classification of faults into types, e.g. HIFs (high impedance faults) or LIFs (low impedance faults). This has been achieved through a cascaded, multilayer ANN structure using the back-propagation (BP) learning algorithm. This paper shows that the FDS accurately identifies HIFs, which are relatively difficult to identify with other methods. Test results are generated using the Manitoba Hydro 24 kV distribution feeder. These results amply demonstrate the capacibility of the FDS in terms of accuracy and speed with respect to detection, localization, and classification of distribution feeder faults.     

基于格拉姆角场与ResNet的输电线路故障辨识方法

针对如何利用实际故障录波数据,提取和放大故障特征差异,开展故障类型与故障原因辨识的问题,提出了基于格拉姆角场与迁移学习-ResNet的输电线路故障辨识方法。首先,统计分析了输电线路故障类型和故障原因的分布特征,用于指导构建适用于类不平衡问题的故障分类器。然后,利用格拉姆角场变换将采集得到的故障电压、电流时序信号转化为格拉姆角场图像,放大故障特征差异,作为故障分类器的输入。进一步,将生成的图像集输入搭建好的故障分类器进行网络训练和测试,输出输电线路故障类型和故障原因。最后,完全采用真实故障录波数据开展了算例分析。结果表明：所提方法对故障类型的辨识准确率达到了97.51%,对故障原因的辨识准确率达到了94.23%。并且将训练的故障辨识网络迁移至其他地区时,仍然具有较好的故障辨识效果和泛化性能。所提方法为基于暂态波形数据驱动的故障辨识提供了新方法,可以用于实际电网的输电线路故障辨识。     

自适应控流型故障选线方案

针对国内配电网单相接地故障选线问题,提出了一种全新而有效的选线方法:当配电网发生单相接地故障时,通过对母线PT二次侧开口三角有控制地实行短路,以产生强度足够大同时又不至于大到影响系统正常运行的瞬时短路脉冲进入系统,置于各出线端的短路脉冲检测器通过对该短路脉冲电流的检测与区分以实现故障线路的判定。理论、仿真分析以及模拟实验都验证了该方法的有效性。     

电流互感器饱和影响测距精度的一种解决方法

电流互感器(TA)饱和会给基于工频电气量的输电线路故障测距精度带来很大的误差。文中利用MATLAB程序，设计了一个前向BP网络，利用BP网络来对TA饱和电流进行矫正补偿，然后再进行故障测距。EMTP仿真的结果表明，对TA饱和电流进行补偿矫正后，明显地改进了故障测距的精度。