• Proceedings of the KIEE Conference
• /
• 2005.07a
• /
• pp.181-183
• /
• 2005

The existing distribution networks are growing with an increase of power demand more and more. Therefore, for efficient operation of distribution networks, operators are much in need of distributed generation. This paper describes a development of the digital protection relay(HIMAP) for protecting distributed generation which is expected to play an increasing role in electric power systems in the near future. This paper particularly introduces frequency protective algorithm and reverse power protective algorithm among the relaying algorithms for protecting distributed generation in distribution networks and resents capability of a developed digital protection relay including these algorithms.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.51 no.3
• /
• pp.134-142
• /
• 2002

This paper presents a new method for the protective relaying scheme in power transformer using wavelet based neural networks. This approach is as fellows. After approximation and detail information is extracted by daub wavelet transform from differential current of power transformer, the former is used for obtaining the rate of differential currents and restrain currents, the latter used as the input of artificial neural networks to avoid the Hiss-operation in over-exciting state and magnetizing inrush state of power transformer. The simulation of EMTP with respect to different faults, inrush conditions and over-exciting conditions in power transformer have been conducted, and the results preyed that the proposed method is able to discriminate magnetizing inrush states, over-exciting stales and internal faults.

• Proceedings of the KIEE Conference
• /
• 1993.07a
• /
• pp.224-226
• /
• 1993

Multi-layered neural networks offer an exciting alternative for modelling complex non-liner systems. This paper investigates the identification of continuous time nonliner system using neural networks with a single hidden layer. The digital low - pass filter are introduced to avoid direct approximation of system derivatives from sampled data. Using a pre-designed digital low pass filter, an approximated discrete-time estimation model is constructed easily. A continuous approximation liner model is first estimated from sampled input-out signals. Then the modeling error due to the nonlinearity is decreased by a compensator using neural network. Simulation results are given to demonstrate the effective of the proposed method.

• Journal of Korean Association for Spatial Structures
• /
• v.11 no.1
• /
• pp.105-112
• /
• 2011

Fundamental Electric vehicle charge system is urgently needed for commercialization of electric vehicles. Car parking building is equipped with PV system for providing electricity to charge electric vehicles, because it must be charged at least for 30 minutes. In parking lots abroad, electric car charging stations are installed to charge electric cars by the electricity gained from PV systems which are also installed. Also, charge infrastructure construction plans and electric car charging facility support standards are being set and proposed, but there are no cases like abroad of electric car charging stations using PV systems and only electric car charging stations using ordinary electricity are being proposed. Therefore, this paper prepares establishment of domestic electric car charging networks. By researching inside outside solar parking lots and cases of abroad PV system electric car charging stations, and by analysis and comparative analysis of structural systems, structural material, and etc., many cantilever structure and small-size types were installed in PV system electric car charging stations.

• Journal of KIISE
• /
• v.41 no.11
• /
• pp.958-966
• /
• 2014

Wireless sensor networks offer a distributed processing environment. Many sensor nodes are deployed in fields that have limited resources such as computing power, network bandwidth, and electric power. The sensor nodes construct their own networks automatically, and the collected data are sent to the sink node. In these traditional wireless sensor networks, network congestion due to packet flooding through the networks shortens the network life time. Clustering or in-network technologies help reduce packet flooding in the networks. Many studies have been focused on saving energy in the sensor nodes because the limited available power leads to an important problem of extending the operation of sensor networks as long as possible. However, we focus on the execution time because clustering and local distributed processing already contribute to saving energy by local decision-making. In this paper, we present a cooperative processing model based on the processing timeline. Our processing model includes validation of the processing, prediction of the total execution time, and determination of the optimal number of processing nodes for distributed processing in wireless sensor networks. The experiments demonstrate the accuracy of the proposed model, and a case study shows that our model can be used for the distributed application.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.49 no.7
• /
• pp.378-388
• /
• 2000

In this paper, we propose Fuzzy Polynomial Neural Networks(FPNN) based on Polynomial Neural Networks(PNN) and Fuzzy Neural Networks(FNN) for model identification of complex and nonlinear systems. The proposed FPNN is generated from the mutually combined structure of both FNN and PNN. The one and the other are considered as the premise part and consequence part of FPNN structure respectively. As the consequence part of FPNN, PNN is based on Group Method of Data Handling(GMDH) method and its structure is similar to Neural Networks. But the structure of PNN is not fixed like in conventional Neural Networks and self-organizing networks that can be generated. FPNN is available effectively for multi-input variables and high-order polynomial according to the combination of FNN with PNN. Accordingly it is possible to consider the nonlinearity characteristics of process and to get better output performance with superb predictive ability. As the premise part of FPNN, FNN uses both the simplified fuzzy inference as fuzzy inference method and error back-propagation algorithm as learning rule. The parameters such as parameters of membership functions, learning rates and momentum coefficients are adjusted using genetic algorithms. And we use two kinds of FNN structure according to the division method of fuzzy space of input variables. One is basic FNN structure and uses fuzzy input space divided by each separated input variable, the other is modified FNN structure and uses fuzzy input space divided by mutually combined input variables. In order to evaluate the performance of proposed models, we use the nonlinear function and traffic route choice process. The results show that the proposed FPNN can produce the model with higher accuracy and more robustness than any other method presented previously. And also performance index related to the approximation and prediction capabilities of model is evaluated and discussed.

• Proceedings of the KIEE Conference
• /
• 2000.11d
• /
• pp.663-665
• /
• 2000

For the control system of thermal turbine in fuel and nuclear power plant, as high reliability and availability are required, redundant control system is generally applied. This paper presents the configuration and design of such a redundant control system that can be suitable for control and monitoring of the turbine. System components such as I/O system, communication networks, voting system are designed, and especially the new intelligent voter using serial communication are proposed. The characteristics of the implemented control system is independence of the control, protection and monitoring functions, and discrimination of the redundancies, and high availability. The control functions such as speed control, load control, valve control and protective functions such as overspeed and PLU are designed in detail.

• KEPCO Journal on Electric Power and Energy
• /
• v.2 no.2
• /
• pp.245-251
• /
• 2016

Despite the exponential throughput improvement in mobile communications systems, their ability to satisfy requirements of state-of-the-art and future applications of advanced metering infrastructure (AMI) is still under investigation. Challenges are mainly due to the inadequacy of third generation partnership project (3GPP) networks to support large amounts of devices simultaneously, while the number of AMI end-devices and the frequency of their data transmission increase with new AMI-based applications. In this introductory survey, innovative and future AMI applications and their communication requirements are first reviewed. Then, we identify challenges of 3GPP long term evolution (LTE) in enabling future AMI applications. More importantly, the latest improvements to LTE-A standard release 12 and 13 are reviewed and analyzed with regards to their potential to improve the quality of LTE-enabled AMI. It is found that 3GPP enhancements on machine type communications (MTC) standards will significantly enhance AMI communications. Beyond MTC specifications, non-MTC-specific enhancements such as carrier aggregation and multi-connectivity for user equipment will also contribute greatly to improving reliability and availability of AMI devices. The paper's focus is towards improved backhaul support for innovative and future AMI applications, beyond traditional automatic meter reading.

• KEPCO Journal on Electric Power and Energy
• /
• v.7 no.1
• /
• pp.93-99
• /
• 2021

The government has proposed a mission to enhance intelligent power networks, decrease coal-fired generation, expand distributed energy resources, and promote energy prosumer into the distribution network in Korea. Installation cost of facility expansion to guaranteed interconnection with small distributed energy resources increases dramatically on KEPCO's distribution sector. And it is hard to withdraw in time. In addition, there are explicit research is required to meet the reliability on grid corresponding to the increase of distributed power. Infrastructure support for accommodating energy prosumer is also needed. Therefore, KEPCO is pushing transition to DSO by expanding distribution management scope and changing its roles. In addition, KEPCO is proactively preparing for integrated operation between distribution network and existing distributed power which is accommodated passively. KEPCO is also trying to accept multiple network users, e.g. building platforms, to manage a data and promote new markets. In the long term, transition to DSO will achieve saving investment costs for accommodating distributed sources and maintaining stable electrical quality. And it will be possible to create new business model using the platform to secure revenue.

• KEPCO Journal on Electric Power and Energy
• /
• v.7 no.2
• /
• pp.323-328
• /
• 2021

Diagnostic models are required. Data augmentation is one of the best ways to improve deep learning performance. Traditional augmentation techniques that modify image brightness or spatial information are difficult to achieve great results. To overcome this, a generative adversarial network (GAN) technology that generates virtual data to increase deep learning performance has emerged. GAN can create realistic-looking fake images by competitive learning two networks, a generator that creates fakes and a discriminator that determines whether images are real or fake made by the generator. GAN is being used in computer vision, IT solutions, and medical imaging fields. It is essential to secure additional learning data to advance deep learning-based fault diagnosis solutions in the power industry where facilities are strictly maintained more than other industries. In this paper, we propose a method for generating power facility images using GAN and a strategy for improving performance when only used a small amount of data. Finally, we analyze the performance of the augmented image to see if it could be utilized for the deep learning-based diagnosis system or not.