Classification of direct load control curves for performance evaluation

In evaluating the performance of direct load control (DLC) programs, an essential task is to classify the DLC curves into either the one complying with the program or not. This paper presents an efficient approach to clustering the DLC curves through a structure of self-organizing maps (SOM). Aiming at selecting significant features of DLC curves, methods of nonlinear principal component analysis (NLPCA) and periodic analysis are proposed for feature extraction. The dual multilayer neural networks (DMNN) model is employed in the proposed NLPCA method. In the periodic analysis method, the periodic characteristics of the DLC curves are investigated. In the SOM, Davies-Bouldin (DB) indexes and a k-means algorithm decide the best number of clusters to be classified. Through the proposed methods, the DLC curves are thus divided into the two categories by the SOM: DLC complying and DLC noncomplying loads. Results obtained from the comparison of six different approaches show that the clusters obtained from the proposed approach exhibit lowest degrees of misclassification for the practical data on Taiwan Power Company (TPC) DLC programs.     

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.     

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。     

Neural-network-based demand forecasting in a deregulatedenvironment

The traditional approach to load forecasting is based on processing time series of load and weather factors recorded in the past. In the dynamic environment of the deregulated power industry, historical load data may not always be available. This paper explores the possibility of an alternative approach toward load forecasting based on indirect demand estimation from available customer data. This approach requires utilization of demand models for different customer categories. This paper presents a neural network-based method of demand modeling. Neural networks are designed and trained based on the aggregate demands of the groups of surveyed customers of different categories. The performance of such models depends on the neural network design and representativeness of the training data. The forecast accuracy is also affected by the forecasted group size, customer characteristics, customer classification system, and the extent of demand survey. This paper discusses the issues of neural network design and illustrates the proposed method by its application to forecasting demand of residential customers     

A new electric power network for effective transportation of small power of dispersed generation plants

This paper proposes a new electric power network that makes it possible for many types of dispersed generation plants owned by nonutility organizations to participate in an electric power market without the disadvantages of existing power utility and customers. This power network is called an open electric energy network (OEEN) because the network is open to the many types of plants for the participation. For achieving such openness, electric power storage devices, load controller at each customer and data communication network are installed in OEEN; the flow of excess electric power generated by each plant is controlled autonomously and in a distributed way. That is, the control is done by transmitting the data on excess electric power such as generation and demand point, power quality, price, etc., from each dispersed generation plant to the power storage devices and the load controllers through the communication network. Since this data-driven power flow control is similar to the mail system for a packet with the addresses of sender and receiver, it is called packet electric power transportation. In OEEN the storage device plays a different role from load leveling. Therefore, the way to determine the storage capacity differs from the conventional approach. In this paper, the applicability of queuing theory for determining the capacity is also discussed.     

Economic evaluation of demand‐side energy storage systems by using a multi‐agent‐based electricity market

With the wholesale electric power market opened in April 2005, deregulation of the electric power industry in Japan has faced a new competitive environment. In the new environment, Independent Power Producer (IPP), Power Producer and Supplier (PPS), Load Service Entity (LSE), and electric utility can trade electric energy through both bilateral contracts and single‐price auction at the electricity market. In general, the market clearing price (MCP) is largely changed by the amount of total load demand in the market. The influence may cause a price spike, and consequently the volatility of MCP will make LSEs and their customers face a risk of higher revenue and cost. DSM is attractive as a means of load leveling, and has an effect on decreasing MCP at peak load period. Introducing Energy Storage systems (ES) is one DSM in order to change demand profile at the customer side. In the case that customers decrease their own demand due to increased MCP, a bidding strategy of generating companies may be changed. As a result, MCP is changed through such complex mechanism. In this paper the authors evaluate MCP by multi‐agent. It is considered that customer‐side ES has an effect on MCP fluctuation. Through numerical examples, this paper evaluates the influence on MCP by controlling customer‐side ES corresponding to variation of MCP. © 2009 Wiley Periodicals, Inc. Electr Eng Jpn, 167(3): 36–45, 2009; Published online in Wiley InterScience ( www.interscience.wiley.com ). DOI 10.1002/eej.20658     

电力营销管理信息系统的开发和应用

详细介绍了电力营销管理信息系统的总体结构及特点,在开发和使用电力营销管理系统时,引入了电力客户信用等级评估办法,通过办法的实施,减少了市场风险,提高了企业竞争能力,加强了需求测用户管理。     

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PCA与SOM神经网络算法的客户价值细分模型研究

针对房地产客户价值管理问题,以某大型房地产企业的普通住宅业务为研究对象,构建了基于PCA与SOM神经网络算法的房地产客户价值细分模型。首先采用PCA主成份分析法将输入变量重组为线性不相关的综合指标,然后采用SOM神经网络算法对客户价值进行聚类分析,最后针对聚类结果,分析不同目标客户群的购买模式和价值特征,旨在为房地产企业的营销过程提供决策支持。     

Home energy management incorporating operational priority of appliances

Home energy management (HEM) schemes persuade residential customers to actively participate in price-based demand response (DR) programs. In these price-based HEM methods, a controller schedules the energy consumption of household’s controllable appliances in response to electricity price signals, considering various customer preferences. Although numerous methods have been recently proposed for HEM application, prioritizing the operation of controllable appliances from the customer’s viewpoint in price-based HEM has not been addressed, which is the focus of the present paper. To do this, the value of lost load (VOLL) of each appliance is defined to indicate the operational priority of that appliance from the customer perspective. Considering appliances’ VOLL, electricity tariffs, and operational constraints of appliances, an optimization problem is proposed to minimize customer energy and reliability costs. The output of the proposed HEM would be the optimum scheduling of household electrical demand. Numerical studies illustrate the effectiveness of the proposed HEM method in a smart home, considering different time-varying electricity pricings.     

自组织映射神经网络用于暂态稳定性分析的研究

对几种形式的自组织映射神经网络进行了集中介绍,并对自组织特征映射（SOFM）神经网络和学习矢量量化（LVQ）神经网络在电力系统暂态稳定模式识别中的应用性能进行比较。利用SOFM网络输出层聚类信息对不同ANN输入特征量的选取效果进行了直观的比较。在这些比较的基础上,利用Kohonen网络“无监督聚类、有监督学习”的工作方式,给出一种基于Kohonen网络的复杂系统在线事故筛选和发电机功角预测方法。利用华中电网的数据对这种网络进行了大量的计算,计算证实了该方法的有效性。     

Derivation of class load pattern by field test for temperature sensitivity analysis

This paper proposes systematic procedures to derive the load pattern of various customer classes in a utility company. The questionnaires are adopted to find the power consumption of key electrical appliances. The customer load information is obtained through intelligent equipment which records customers' electricity demand on a 15-minute interval basis throughout the year. Five hundred meters are installed on statistically selected samples from the various customer classes. By the proposed sampling theory, the customer load characteristics will be derived with a sufficient confidence level. Statistical analysis is then performed to find the typical load pattern of each customer class based on the power measurements of field tests. The temperature effect on the power consumption of each customer class is then solved by investigating the relationship between customer power consumption and the ambient temperature. The proposed procedure has been adopted by Taipower Company to determine the customer load pattern to provide valuable information for better distribution planning and to design better load management programs to enhance system operating efficiency.     

基于异构信息源的地区级模拟电力市场的架构研究

地区级模拟电力市场的数据分别来自于不同结构的信息源，如能量管理系统（EMS）、信息管理系统（MIS）、调度自动化系统（SCADA）、配电管理系统（DMS）和地理信息系统（GIS）等，而这些异构系统彼此相互独立，信息交换比较困难，针对这一问题，提出了基于异构信息源的地区级电力模拟市场的架构，通过对异构系统相关数据进行整合和融合，使电力模拟市场可以从集成数据中及时存取的数据，以某地区供电局电力模拟市场考核系统为例介绍了本架构的实际应用。     

多种期权合同条件下的供电公司最优购电策略

研究在电力市场背景下,当实时电力市场价格、最终顾客需求是随机变量时,作为期权合同购买方的供电公司面对多种期权合同和实时购电市场,采用最优期权合同组合的购电策略,根据每种期权合同能为供电公司带来收益的大小,推导出最优期权合同组合应满足的条件.介绍了求解每种期权合同最优购买数量的方法,并证明当可供选择的期权合同种类增加时,供电公司利润会增加.最后通过数例计算及计算机仿真说明了结论的应用.     

基于用户响应的分时电价时段划分

如何在已实施分时电价地区兼顾已有的用户响应,合理调整时段划分是分时电价设计面临的新问题。鉴于传统模糊隶属度函数时段划分方法缺乏对用户需求响应的考虑,已不适用于时段划分调整,故文中建立了基于用户响应的分时电价时段划分模型。通过比对电力用户负荷曲线比重结构变化强度,评估电力用户在各时刻点的响应程度,提出了时刻点的响应度属性指标。模型融合时刻点的响应度属性指标,对依据各时刻点峰、谷隶属度模糊聚类形成的时段划分进行修正。结合某地区实例分析表明,在时段划分模型中引入响应度属性,考虑用户需求响应修正时段划分的方案,兼顾了系统负荷曲线本身的峰谷形态特征,以及曲线中包含的各类用户的需求响应特征,使得时段划分有利于激励更多的需求响应资源。     

基于聚类事务的档案聚合技术在电子商务推荐系统中的应用

通常电子商务网站使用推荐系统为客户建议一些产品和为客户提供信息来帮助他们决定哪些产品是他们潜在要买的.研究人员已经应用包括web使用挖掘在内的许多方法来解决正在发展中的准确和有效的推荐系统的基本问题.本文提出在设计B2C推荐系统中应用一种在web使用挖掘中广泛使用的基于聚类事务的档案聚合(PACT)技术.应用这种技术本文实现了一个网上在线商店客户所属目标组的识别,并设计了一个推荐系统.通过使用这个推荐系统,客户的偏好和相关的产品信息是自动地从单击流(web使用数据)中获得的,不像其他的推荐方法仅仅是从购买记录中获得的.这样能为不同客户实时地推荐满足其偏好的个性化商品,保证了推荐质量,建立了良好的客户群体,提高了服务质量,加强了站点市场竞争力.     

An operational algorithm for residential cogeneration systems based on the monitored daily‐basis energy demand

Residential cogeneration systems with PEFC are promising as distributed power system resources with the ability to improve energy system efficiency. However, it is important to develop an efficient algorithm for operation because the energy demand at each house differs greatly from day to day. In this paper, we propose an operational algorithm and evaluate it from the viewpoint of energy conservation and economic effectiveness based on the energy demand characteristics. In the algorithm, the hot water and electricity demand on the next day are estimated based on the average of past data. The results of simulations using actually monitored energy demand data indicate that (1) the greater the electrical demand of a household, the more effective this algorithm becomes with respect to energy conservation; (2) the greater the hot water demand of a household, the more effective this algorithm becomes with respect to economic effectiveness. © 2009 Wiley Periodicals, Inc. Electr Eng Jpn, 170(2): 37–45, 2010; Published online in Wiley InterScience ( www.interscience.wiley. com ). DOI 10.1002/eej.20892     

可靠性需求市场中用户的风险决策

市场环境下,用户的身份按其参与市场的方式可分为用电容量的需求方和备用容量的供应方2类。为提高用户收益,该文在对这2种容量不同收益特性及其互补性进行分析的基础上,基于风险管理观点与协调优化理念,提出基于风险的用户可靠性需求决策模型,使用户参与用电市场的确定性收益与参与备用市场的风险性收益之和最大。为加快寻优速度,提出基于灵敏度技术的优化算法。仿真结果表明用户可靠性需求过高或过低都不合适,而应存在最优值。     

用户用电设备评估的区间熵权法

随着智能电网的建设,新能源的接入和电动汽车的普及,致使用户用电设备种类多样,用户用电服务质量诉求逐年增加,用户用电设备的状况不仅影响电网双向互动的功能实施,也关系着电网的运行和维护,文章阐述了用户用电设备的评价指标体系,以及区间熵权法。首先,介绍了用户用电设备的定义、范畴和分类;其次从能效评估、安全监测和需求响应三方面阐述用户设备评价指标体系,并对指标体系中一些重要指标进行了详细说明;最后,为了在考虑数据不确定性前提下计算指标权重值,详细陈述区间熵权法的计算过程,并进行了居民用户设备的案例分析,期望能够为科学、完整和系统的对用户电力设备进行评估提供借鉴。     

Analysis of long‐term profitability and DSM needs of utilities in a partially liberalized retail market by a generation system expansion model

Retail competition in the electric power market was introduced in Japan in March 2000. Although the liberalization is limited to a part of the retail power market having about 30% of the total electricity demand, the liberalized customer segment is now subject to competition among the utilities and new entrants. This paper examines the profitability of competitive pricing for eligible segmented customers through a scenario‐based model analysis focusing on the demand characteristics of segmented customers. The model includes the utility's investment in power generation for segmented customers, considering long‐term rather than short‐term profitability. Load leveling is not always achieved under profit‐maximizing behavior of the utility because the profitability of competitive pricing depends on load patterns of bypassed customers and price differentials among power suppliers. © 2003 Wiley Periodicals, Inc. Electr Eng Jpn, 144(4): 43–52, 2003; Published online in Wiley InterScience ( www.interscience.wiley.com ). DOI 10.1002/eej.10111