By Topic

Intelligent Systems Applications to Power Systems, 1996. Proceedings, ISAP '96., International Conference on

Date Jan. 28 1996-Feb. 2 1996

Filter Results

Displaying Results 1 - 25 of 79
  • Proceedings of International Conference on Intelligent System Application to Power Systems

    Save to Project icon | Request Permissions | PDF file iconPDF (2644 KB)  
    Freely Available from IEEE
  • Authors/Speakers's index

    Save to Project icon | Request Permissions | PDF file iconPDF (150 KB)  
    Freely Available from IEEE
  • Subject index

    Save to Project icon | Request Permissions | PDF file iconPDF (261 KB)  
    Freely Available from IEEE
  • Fuzzy logic based security assessment of power networks

    Page(s): 405 - 409
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (432 KB)  

    A new method based on fuzzy logic is proposed for steady-state security analysis. The method has been developed for the Dutch 380 kV transmission system. The security status of the power system's operating condition is recognized from data from a SCADA system, from global knowledge and some operation characteristics of the power system. The method can classify the power system's operating condition into normal/alert state. For the alert state, it provides information about the severity and pertinent contingencies that may cause insecurity. The security assessment can follow different strategies such as risk awareness. A risk index shows the risk View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A daily peak load forecasting system using a chaotic time series

    Page(s): 283 - 287
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (336 KB)  

    In this paper, a method for the daily peak load forecasting which uses a chaotic time series and an artificial neural network in a power system is presented. We find the chaotic characteristics of the power load curve and then determine an optimal embedding dimension and delay time. For the load forecast of one day ahead daily peak load, we use the time series load data obtained in the previous year. By using the embedding dimension and delay time, we construct a strange attractor in the pseudo phase plane and the artificial neural network model trained with the attractor mentioned above. The one day ahead forecast errors are about 1.4% for absolute percentage average error View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic load modeling based on a nonparametric ANN

    Page(s): 55 - 59
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (332 KB)  

    Accurate dynamic load models allow more precise calculations of power system controls and stability limits. System identification methods can be applied to estimate load models based on measurements. Parametric and nonparametric (functional) are the two main classes in system identification methods. The parametric approach has been the only one used for load modeling so far. In this paper, the performance of a functional load model based on a polynomial artificial neural network is compared with a linear model and with the popular “ZIP” model. The impact of clustering different load compositions is also investigated. Substation buses (138 kV) from the Brazilian system feeding important industrial consumers have been modelled View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Development of an intelligent long-term electric load forecasting system

    Page(s): 288 - 292
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (492 KB)  

    An essential element of electric utility resource planning is forecasting of the future load demand in the service area. Based on the outcome of such forecasts, utilities coordinate their resources to meet the forecasted demand using a least-cost plan. In general, resource planning is performed subject to numerous uncertainties. Expert opinion indicates that a major source of uncertainty in planning for future capacity resource needs and operation of existing generation resources is the forecasted load demand. In this paper, the development and testing of a hybrid intelligent long-term load forecasting system is presented consisting of several neural networks forecasting blocks, genetic algorithms for network architecture selection and optimization, and fuzzy rules for forecast combination. This is an application of increasingly significant importance to a deregulating electric utility industry. An overview of the current practice in long term load forecasting is presented, followed by an overview of the forecasting system design process utilized in generating the long-term load forecasts and a brief description of the key building blocks of the forecasting system. This is followed by some sample long-term forecasts performed for demonstrating the feasibility of the proposed approach View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • High speed offset free distance relaying algorithm using multilayer feedforward neural networks

    Page(s): 210 - 214
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (340 KB)  

    A new high-speed digital distance relaying algorithm using artificial neural networks is presented. The proposed artificial neural network models are trained with the input patterns of distorted voltage and current signals passed a lowpass filter and with the target patterns of real and imaginary components of DC-offset free current and voltage signals conditioned by a DC-offset removing algorithm. The artificial neural networks play the roles of a DC-offset removing filter and a Fourier filter. In accordance with a series of tests, the relay operating time is less than 9 ms after faults in a 80 km, 154 kV, 60 Hz overhead transmission line system View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Temporal reasoning methodologies used in AI applications for power system control centers

    Page(s): 357 - 361
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (396 KB)  

    The results already obtained with intelligent real time applications in power systems show that artificial intelligence techniques are adequate and useful for solving some problems for which traditional programming techniques are not able to provide good solutions. On the other hand, the duration of this kind of project is still rather long and the total number of deployed systems all over the world is still very low. This is due to the complex issues that real time applications for power systems must deal with, among which temporal reasoning plays a key role. This paper presents the most important temporal reasoning requirements for real-time applications in power systems. It also presents the methods used in some systems that have been developed to deal with temporal reasoning, with particular emphasis on SPARSE, an expert system for fault analysis and service restoration, developed for Portuguese Control Centers View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evaluation of object-oriented database for distribution network monitoring system

    Page(s): 156 - 161
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (408 KB)  

    This paper outlines an original object-oriented database management system which is designed for industrial applications and describes results of an experiment to apply it to a graphical user interface in a power distribution monitoring system. Database management systems are widely used and achieve high productivity and high reliability of data management in the business field and in some engineering areas. However conventional database systems, especially relational database systems, are rarely used in industrial real-time fields. This paper presents advantages of object-oriented concepts for modeling complex data of a monitoring system. The object-oriented database successfully supports data-modeling requirements of GUI applications, and the performance is well acceptable for GUI applications View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent approach to coordination identification in distance relaying

    Page(s): 62 - 67
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (448 KB)  

    Proper coordination of the protective relays is one of the important conditions for power system security. Settings of distance relays usually determined by heuristic rules may not satisfy the coordination requirements. In this paper, the coordination behaviour of the setting rules of the distance relays is investigated. Coordination conditions and properties are derived and the coordination region is introduced. Efficient algorithms to identify the coordination status are presented together with its test results View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The application of an intelligent system to power network operation and control

    Page(s): 170 - 174
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (468 KB)  

    Recent major increases in the extent and power of the monitoring and control systems applied to power systems have led to a significant interest in the provision of online support to power network control engineers. Expectations of improved network performance which have resulted from these developments can only be met if the increased volume of data acquired is matched by increased capacity to interpret it. This paper describes the progressive development and implementation of a modular decision support system (DSS) for South Western Electricity (SWEB), UK. The authors describe the modules of the DSS, with particular emphasis on the restoration advisory function and its model of the power network, and a case study is discussed. The benefits of the step-by-step implementation process adopted are outlined View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Knowledge and model based decision support for power system protection engineers

    Page(s): 215 - 219
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (292 KB)  

    This paper discusses a decision support system for utility protection engineers, offering them the advantages of intelligent alarm processing, fault diagnosis and validation of protection operation. Knowledge based systems perform the alarm processing and fault diagnosis functions, whereas model based diagnosis is employed for the validation of protection operation. The integration of both paradigms is demonstrated through a case study View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On-line fault diagnosis using sequence-of-events recorder information

    Page(s): 339 - 344
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (460 KB)  

    This paper presents a new logic-based method for online power system fault diagnosis in a control center environment. The unique feature of the approach is the use of sequence of events recorder information from substations, together with data acquired by the energy management system (EMS). A proposed line fault proof algorithm is applied to a line if any protective device in the line's protection net is triggered. The method has been validated through testing with fault scenarios from the Italian power system View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An artificial neural network application to distance protection [of power systems]

    Page(s): 226 - 230
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (412 KB)  

    An application of artificial neural networks (ANNs) to power system distance protection is presented in this paper. A neural network was trained by data from simulation of a simple power system under load and fault conditions, tested by data with different system conditions, and finally run for faults along the whole power line. The research was concentrated on creating more selective arcing fault detection, especially for radial distribution lines where arc resistance can be a significant part of the zero sequence impedance. A nonlinear arcing resistance model was used to provide data and a new operating characteristic was devised. The prospective ANN distance relay showed very good performance in detecting a single-line-to-ground fault with nonlinear arcing resistance along the whole transmission line View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A special period peak load forecasting method based on order relations

    Page(s): 120 - 125
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (408 KB)  

    In order to forecast demand precisely through a year, we should consider various types of days. This paper presents a peak load forecasting method for special periods. In Japan, there are three special periods whose peak loads are usually less than normal days' loads. These peak loads are influenced by annual variation, date and day of the week. These facts request a new method that is different from the forecasting methods for normal days. A proposed method detects order relations of labelled days in the special period based on the days' peak loads. A labelled day is a date labelled day of the week, such as January 1st (Sun) or a date labelled abstracted day of the week, such as January 1st (weekday). The proposed method refines order relations by changing labels from detailed levels to abstracted levels. Final order relations show a structure among labelled days in the special period on peak loads. By using results of final order relations, a peak load of each day in the special period is predicted. Performance of the method which is verified with simulations on actual load data of Tokyo Electric Power Company (TEPCO) is also described View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unit commitment using stochastic optimization

    Page(s): 428 - 433
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (432 KB)  

    This paper demonstrates how the simulated annealing algorithm and genetic algorithms can be used as means to solve the power system unit commitment problem. In addition, this paper presents parallel approaches to speed up the computational requirement of the simulated annealing algorithm. The algorithms were tested with two different problems. The results have demonstrated the success of the algorithms in consistently reaching good solutions View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of wavelet theory to power distribution systems for fault detection

    Page(s): 345 - 350
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (320 KB)  

    In this paper, an investigation of the wavelet transform as a means of creating a feature extractor for artificial neural network (ANN) training is presented for application to distribution network fault location. The study includes a terrestrial-based three-phase delta-delta power distribution system. Faults were injected into the system and data was obtained from experimentation. Graphical representations of the feature extractors obtained in the time domain, the frequency domain and the wavelet domain are presented to ascertain the superiority of the wavelet transform feature extractor View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An expert system based aid for clearing overloads on power system plant

    Page(s): 242 - 246
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (388 KB)  

    This paper describes an expert system application for clearing emergency overloads on power systems. A method employing the network sensitivity factors is used to determine appropriate control actions and amount of corrections required to clear overloads. The expert system was developed on the basis of the commercial package VP EXPERT. VP EXPERT provides interactions with a power flow analysis package, PSSE, to calculate network sensitivity factors and line flows, and other external programs and a database. The governing rules for clearing overloads are introduced and the proposed approach is implemented on the IEEE 30-bus system View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A survey of applications of evolutionary computing to power systems

    Page(s): 35 - 41
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (832 KB)  

    Evolutionary computing techniques are fast emerging as efficient approaches for various search, optimization and classification problems. Many works have reported application of evolutionary techniques to solve or aid the solution of various power system problems The interest in this field has increased exponentially in the past few years. This paper surveys the published literature in the field of power systems. The paper gives a brief description of what problems evolutionary computing techniques have been used for, highlighting some common features and drawing out some key aspects of the methodology used View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An expert system based framework for an incipient failure detection and predictive maintenance system

    Page(s): 321 - 326
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (412 KB)  

    Traditional preventive maintenance operations are being abandoned and electric utilities are becoming more failure driven due to the financial constraints being placed on them. When some distribution equipment begins to deteriorate, intermittent incipient faults persist in the system from as little as several days to several months. The failure of equipment in power distribution systems can have a direct or indirect impact on the reliable delivery of quality power. Also, certain failures can result in loss of service. There is great interest in the utility industry for low-cost, automated, real-time approaches which can detect distribution incipient faults and locate their source. This paper discusses an expert system based incipient failure detection and predictive maintenance (FDPM) system being developed for application in distribution systems. The FDPM system includes an expert system engine, a knowledge base, mathematical and neural network models of aging of distribution equipment, historical measurements databases, a distribution state estimator, a fault and disturbance event locator and a distribution system interconnection map. The FDPM system detects incipient disturbances, classifies the type of disturbance, and locates the source of the incipient behavior. If the source is one of the components under observation by the FDPM system, it assesses the integrity of the distribution system component and predicts maintenance needs View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Development of genetic algorithm embedded Kohonen neural network for dynamic security assessment

    Page(s): 44 - 49
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (456 KB)  

    A Kohonen self-organizing neural network embedded with a genetic algorithm is proposed in this paper. The genetic algorithm is embedded to initiate the Kohonen classifiers. By the proposed approach, the neural network learning performance and accuracy are greatly enhanced. In addition, the genetic algorithm can successfully avoid the neural network from being trapped in a local minimum. The proposed method is developed and tested on an electric utility system to access its dynamic security View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An intelligent support system for local control center using meta-inference and reconstruction of knowledge-base

    Page(s): 247 - 251
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (324 KB)  

    This paper presents an intelligent support system for local power system control centers that has been tested in a practical local control centers. A special modular structure is applied to enhance the processing time and to spare memory. This reconstructed modular knowledge base would be eventually indispensable to enhance the performance of an intelligent system; furthermore, based on this structure, a distributive structured large intelligent system that consists of many enhanced substation automation systems would be easily realized with some supervisory meta-inference system View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Future flexible power delivery system and its intelligent functions

    Page(s): 261 - 265
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (376 KB)  

    In this paper, the authors propose a “flexible, reliable and intelligent electrical energy delivery system (FRIENDS)” and discuss its intelligent functions. In the near future, electrical power systems will be facilitated by dispersed energy resources and dispersed energy stores on the demand side. The electrical power delivery system itself will have to be changed to co-operate with these facilities. The authors have proposed a flexible system named FRIENDS for such a situation. Noticeable intelligent functions for FRIENDS are flexible network reconfiguration for uninterrupted power supply, protective control, on-line information service to customers (including automated metering), DSM and home automation as well as multi-quality power supply. In this paper, the new concept of the power delivery system of FRIENDS is explained, and how the intelligent functions can be realized in it is discussed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An on-line knowledge-based system for fault section diagnosis in control centers

    Page(s): 232 - 236
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (456 KB)  

    This paper presents a knowledge-based system for online diagnosis of power system fault allocation (SIDUF-TR), a decision making support for the energy control center operators in Mexico. A new inference method for possible faulted elements is proposed, which uses the real-time information about tripped relays and circuit breakers to generate a decision tree describing the operation of the protection schemes in the power system. The inference method conforms the branches of decision trees performing a classification process which identifies the type of relay and circuit breaker operation for different possible faulted elements. Architecture for real-time operation of SIDUF-TR and the result of its application to a real disturbance are also presented in this paper View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.