Classification, Filtering, and Identification of Electrical Customer Load Patterns Through the Use of Self-Organizing Maps

Different methodologies are available for clustering purposes. The objective of this paper is to review the capacity of some of them and specifically to test the ability of self-organizing maps (SOMs) to filter, classify, and extract patterns from distributor, commercializer, or customer electrical demand databases. These market participants can achieve an interesting benefit through the knowledge of these patterns, for example, to evaluate the potential for distributed generation, energy efficiency, and demand-side response policies (market analysis). For simplicity, customer classification techniques usually used the historic load curves of each user. The first step in the methodology presented in this paper is anomalous data filtering: holidays, maintenance, and wrong measurements must be removed from the database. Subsequently, two different treatments (frequency and time domain) of demand data were tested to feed SOM maps and evaluate the advantages of each approach. Finally, the ability of SOM to classify new customers in different clusters is also examined. Both steps have been performed through a well-known technique: SOM maps. The results clearly show the suitability of this approach to improve data management and to easily find coherent clusters between electrical users, accounting for relevant information about weekend demand patterns     

SOM神经网络和C-均值法在负荷分类中的应用

负荷时变性和分散性已经成为制约负荷模型推广应用的主要因素,而负荷特性分类则是解决这个问题的有效途径.文中提出基于SOM神经网络的C-均值聚类算法的新的负荷分类方法:以负荷模型参数作为负荷动态特性分类特征向量,应用SOM神经网络对初始训练样本进行分类,将获得的聚类数目和各类中心点作为C-均值算法的初始输入进一步聚类.最后...     

Time to line crossing for lane departure avoidance: a theoretical study and an experimental setting

The main goal of this paper is to develop a distance to line crossing (DLC) based computation of time to line crossing (TLC). Different computation methods with increasing complexity are provided. A discussion develops the influence of assumptions generally assumed for approximation. A sensitivity analysis with respect to vehicle parameters and positioning is performed. For TLC computation, both straight and curved vehicle paths are considered. The road curvature being another important variable considered in the proposed computations, an observer for its estimation is then proposed. An evaluation over a digitalized test track is first performed. Real data are then collected through an experiment carried out in test tracks with the equipped prototype vehicle. Based on these real data, TLC is then computed with the theoretically proposed methods. The obtained results outlined the necessity to take into consideration vehicle dynamics to use the TLC as a lane departure indicator.     

Data mining on a transformer partial discharge data using the self-organizing map

Although experts all over the world have investigated methods for partial discharge (PD) detection and classification for over 50 years, until now there is still no universal method available for this purpose. Even in the future, it would not be possible to define a universal method for unambiguous classification and localization of PD sources in complex insulating systems (e.g. transformers or generators) due to the unlimited variations of PD source type and its location. This paper deals with PD signals obtained by remote radiometric measurements performed on a power transformer. Extensive PD measurements were performed in the substation. Since fingerprints of the remote radiometric measurements are not available, the formation of clusters with similar features obtained from captured PD data is crucial. A data mining technique known as self-organizing map (SOM) for the analysis and interpretation of captured PD data is used. Since each signal contains a large number of samples, before applying the SOM, the dimensionality reduction based on principal component analysis is performed. As a result of a data mining process a clear separation of PDs emanating from a transformer and discharges emanating from its surrounding is achieved     

基于综合能源计量数据的区域用能特性分析

用户耗能的时空分布特性对于电网规划具有重要的参考价值,是电网建设的重要依据。电力运营商通过新型计量设备分析居民的用电行为,从而促进电网高效运营。针对区域用户画像问题,提出基于综合能源计量数据的区域用能特性分析方法。利用“多表合一”用能采集系统,引入用户的燃气消耗数据,基于层次聚类与自组织映射（self organized maps,SOM）聚类方法刻画用能特征分布,通过仿真实验说明所提方法在用能特性分析问题上具有实用价值,有利于挖掘高耗能区域,能帮助电力运营商制定规划方案。     

基于综合能源计量数据的区域用能特性分析

用户耗能的时空分布特性对于电网规划具有重要的参考价值,是电网建设的重要依据。电力运营商通过新型计量设备分析居民的用电行为,从而促进电网高效运营。针对区域用户画像问题,提出基于综合能源计量数据的区域用能特性分析方法。利用“多表合一”用能采集系统,引入用户的燃气消耗数据,基于层次聚类与自组织映射（self organized maps,SOM）聚类方法刻画用能特征分布,通过仿真实验说明所提方法在用能特性分析问题上具有实用价值,有利于挖掘高耗能区域,能帮助电力运营商制定规划方案。     

A pattern recognition methodology for evaluation of load profiles and typical days of large electricity customers

This paper describes a pattern recognition methodology for the classification of the daily chronological load curves of each large electricity customer, in order to estimate his typical days and his respective representative daily load profiles. It is based on pattern recognition methods, such as k-means, self-organized maps (SOM), fuzzy k-means and hierarchical clustering, which are theoretically described and properly adapted. The parameters of each clustering method are properly selected by an optimization process, which is separately applied for each one of six adequacy measures. The results can be used for the short-term and mid-term load forecasting of each consumer, for the choice of the proper tariffs and the feasibility studies of demand side management programs. This methodology is analytically applied for one medium voltage industrial customer and synoptically for a set of medium voltage customers of the Greek power system. The results of the clustering methods are presented and discussed.     

月前日负荷曲线的概率预测和随机场景模拟

针对现有中长期日负荷曲线预测方法大多为点预测,难以满足电力系统不确定性分析的不足,提出了一种基于因子分析和神经网络分位数回归的月前日负荷曲线概率预测和随机场景模拟方法。采用因子分析技术,在保留日内负荷时序相关性的前提下,对日负荷序列向量降维;提取出少数相互独立的负荷公共因子作为预测变量,以日气象因素、星期类型和前一日公共因子值为输入特征,建立计及相邻日负荷相关性的神经网络分位数回归概率预测模型;以此为基础,利用中期气象预报信息,逐日预测和模拟未来30日的负荷曲线,并生成未来月负荷曲线的随机模拟场景。实际算例结果验证了所提概率预测方法的准确性和高效性,其生成的日负荷曲线模拟场景更好地体现了负荷的时序相关性,能为调度人员提供更准确、全面的月前负荷预测信息。     

干扰条件下基于改进SOM故障诊断研究

针对机载电子设备在噪声干扰条件下故障诊断效果不佳的问题，基于自组织特征映射网络（SOM），提出了改进的SOM的网络算法，该算法在标准SOM网络的基础上引入了滤波算法进行初级降噪处理，然后进行阈值学习，重新定义了邻域函数和学习率，最后以故障评价指标为基准进行故障的隔离定位。在高斯白噪声条件下以某型飞机前端接收机的故障数据为例建立诊断模型。通过聚类和网络训练等仿真测试实验得到了故障模式的分类和隔离。同时通过与其他方法的性能比较验证了SOM神经网络在高斯白噪声干扰条件下故障诊断中的有效性、准确性和鲁棒性。     

Periodic steady state analysis using shooting and wave-form-newton

This paper describes a method of determining the forced periodic steady state response of non-linear circuits. the method is closely related to the work of Aprille and Trick Proc. IEEE, 60 , 108-114 (1972) and also to the finite difference method for solving a boundary value problem. The new approach is a shooting method in the sense that in every iteration an initial value problem is solved. It is, however, also a relaxation method, because in every iteration a periodic wave-form is obtained. This is achieved by solving in each step a linear time-dependent differential equation whose solution can be easily transformed into a periodic solution satisfying this linear equation. Because the iteration takes place on wave-forms rather than initial values and every solution satisfies the boundary conditions, the method is robust. It will be shown that for a causal approximation of the time derivatives the iterated wave-forms are equal to those found using the finite difference methods.     

改进的暂态稳定双向模块简化仿真算法

基于发电机双向模块简化技术,提出了一种改进的电力系统轨迹仿真新算法。新算法根据网络和发电机模块各自的特点,采用不同的LU分解方法,在保持牛顿法良好收敛性的基础上,提高了计算效率。同时．新算法具有模块清晰、易于扩展应用于新器件的优点。并对新算法进行了复杂度分析。在实际电力网络上的仿真结果表明,改进的仿真新算法可以极大地提高计算速度。通过与BPA商业软件的仿真结果比较．验证了改进算法的有效性和合理性。     

基于两步分群法的双馈机组风电场等值建模

为了在保证风机等值精度的基础上降低风电场仿真模型的复杂度,考虑到实际风电场内尾流效应及风机控制方式不同的情况,借鉴层次分析法的思想提出了两步分群法。该方法综合考虑了风机初始运行点以及动态特性。首先考虑风电机组间尾流效应计算输入风速,根据机组桨距角动作情况进行初次分群,通过转子电流受扰曲线识别动态特性相近的风机实现再次分群。然后在保证风电机组功率输出特性和电压差恒定的基础上,进行风机和集电线路参数等值,得到风电场多机等值模型。最后通过仿真验证了所述方法的合理性。     

基于机会约束规划的直接负荷控制及可中断负荷联合优化调度研究

为充分利用需求响应资源,可对不同需求响应资源进行整合。本文以调度成本最低为目标函数,构建了含直接负荷控制和可中断负荷的优化模型。对比了直接负荷控制及可中断负荷在受控量、受控时间、补偿价格等方面的异同,重点分析了两者在负荷反弹方面的差异。采用机会约束考虑了负荷预测的不确定性,并将机会约束转化为其确定性等价形式。采用拉格朗日松弛法对确定性模型求解,并采用蒙特卡罗模拟对机会约束置信水平进行验证。算例表明模型综合了直接负荷控制移峰和可中断负荷削峰特点,可有效降低系统高峰时段负荷,避免二次负荷高峰的产生。     

基于最小最大核K均值聚类算法的水电机组 振动故障诊断

基于聚类分析的故障诊断方法能够按照故障样本之间的相似性无监督地将同类故障聚为一簇,当前已成为一类有效的故障诊断策略。为解决传统聚类算法受初始聚类中心的影响,易陷入局部最优解的问题,提出一种最小最大核K均值聚类方法。该方法在聚类过程中为簇内方差赋以与其大小成正比的自动修正的权重,并引入核函数技术以处理低维输入空间的线性不可分问题,大大提高了聚类的精确性。在标准数据上将所提方法与标准K-means及K-means++比较,显示了所提算法的有效性和优越性。基于这一聚类方法提出了一种具有自学习能力的故障诊断模型。     

基于Duffing振子的弱信号频率检测研究

现有Duffing振子弱信号检测方法检测频率信号时存在检测频率范围窄的缺点,在检测宽频带信号时需要用到多振子阵列,增加了实现的复杂度。文章充分利用周期信号频率特性和Duffing振子的弱信号检测技术,提出了一种新的Duffing振子检测频率信号的方法,该方法摒弃了传统外加周期策动力的方式,将待测信号直接送入Duffing振子,然后对振子输出量作频谱分析,降低了调谐的难度并增加了振子运行的稳定性。仿真结果表明,该方法可实现对信号频率的精确检测,具有精确度高（10-4数量级）、复杂度低的优点。     

微电网经济运行中的典型时序场景分析方法

微电网经济运行涉及对大量场景和方案的分析评价,区域内风电/光伏出力和负荷变化的时序性、周期性和不确定性给微电网运行带来影响。提出一种典型场景分析方法,对计算周期内的大量风电/光伏出力和负荷原始数据进行同步聚类划分,形成能够反映计算周期内历史数据特征的典型场景集;建立包含多种分布式电源和储能单元的微电网系统经济运行优化模型;针对某微电网区域,比较典型时序场景、全周期时序场景、周期内缩减场景3类场景数据的经济运行优化结果,验证所提方法的有效性。     

应用曲线分群预测的电动汽车充电设施规划方法

针对电动汽车公共充电设施的建设规划问题,以充电设施的建设数量满足电动汽车的充电需求为目标,建立电动汽车充电需求预测模型。采用基于充电电量曲线聚类的分群预测方法,应用霍普金斯统计量评估曲线聚类趋势,结合肘方法(elbow method)来选择合理的聚类数;考察各类典型充电电量曲线趋势和扰动方面的特征并选取适用的预测算法(Holt-Winters指数平滑、ARIMA模型),有效提高了电动汽车充电需求预测的准确性。采用某市15个行政区县的电动汽车充电数据进行实例分析,分析结果表明,利用此模型对电动汽车公用充电设施的充电需求进行预测,准确量化公共充电设施的建设规模,提高了公共充电设施投放的针对性。     

Electricity peak load forecasting with self‐organizing map and support vector regression

This paper aims to study the short‐term peak load forecasting (PLF) by using Kohonen self‐organizing maps (SOM) and support vector regression (SVR). We first adopt a SOM network to cluster the input data set into several subsets in an unsupervised learning strategy. Then, several SVRs for the next day's peak load are used to fit the training data of each subset in the second stage. In the numerical experiments, data of electricity demand from the New York Independent System Operator (ISO) are used to verify the effectiveness of the prediction for the proposed method. The simulation results show that the proposed model can predict the next day's peak load with a considerably high accuracy compared with the ISO forecasts. © 2006 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

基于自组织映射神经网络的电力用户负荷曲线聚类

电力用户负荷曲线的聚类是形成合理电价体系和实施负荷管理措施的基础。文中基于自组织映射（SOM）神经网络进行低压终端用户的负荷曲线聚类研究。首先定义并提取功率曲线、分时功率、功率频谱3类向量,分别作为SOM神经网络的输入进行可视化聚类。采用相对量化误差和拓扑误差2个指标表征聚类质量,选取聚类结果最好的SOM输出层结合 k均值法进行用户负荷曲线划分。根据Davies指标将所研究的131条曲线划分为8类,对每类曲线进行描述。最后进行新用户的识别,结果表明聚类方法有效、可靠。     

Evolutionary programming based economic dispatch of generators with prohibited operating zones

This paper presents a new approach using evolutionary programming for solving the economic dispatch (ED) problem of generators when some/all of the units have prohibited operating zones. In this method, additional constraints such as spinning reserve requirements and ramp-rate limits are also considered besides taking into account network losses. The proposed method is implemented for solving a few example dispatch problems. The results obtained by this new approach are compared with those obtained using traditional methods. The study results have shown that the approach developed is feasible and efficient.