• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.7
• /
• pp.824-832
• /
• 2018

According to the government's policy to demonstrate and expand the renewable energy sources, distributed generators such as PV and WP are installed and operated in distribution systems. However, there are many issues related to power quality problems including over voltage and under voltage of customers. In order to overcome these problems, the electric power company have installed a step voltage regulator (SVR) in primary feeders interconnected with distributed generators, and also have established the technical guidelines for the distributed generators to stabilize the customer voltages in distribution systems. However, it is difficult to maintain the customer voltages within allowable limit. Therefore, this paper reviews the problems of voltage control by SVR in a distribution systems interconnected with a large amount of PV systems, and proposes characteristics of operating range and voltage control limit of the small hydropower generators. Also, with the estimation of the influence to the power system voltages from the voltage control mode of generators, this paper proposes the optimal voltage control algorithm of the small hydropower generators. By programming the proposed algorithm into control simulator of exciter, it is confirmed that the proposed algorithm can contribute the voltage stabilization in distribution systems interconnected with large scaled PV systems.

• Journal of Biomedical Engineering Research
• /
• v.6 no.1
• /
• pp.1-4
• /
• 1985

Background EEG signals can be represented as the sum of a conventional AR process and an innovation process. It is know that conventional estimation techniques, such as least square estimates (LSE) or Gauasian maximum likelihood estimates (MLE-G) are optimal when the innovation process satisfies the Gaussian or presumed distribution. When the data are contaminated by outliers, however, these assumptions are not met and the power spectrum estimated by conventional estimation techniques may be fatally biased. EEG signal may be affected by artifacts, which are outliers in the statistical term. So the robust filtering estimation technique is used against those artifacts and it performs well for the contaminated EEG signal.

• Communications for Statistical Applications and Methods
• /
• v.31 no.1
• /
• pp.65-85
• /
• 2024

The tail probability of a function of a multivariate random variable is not easy to estimate by the crude Monte Carlo simulation. When the occurrence of the function value over a threshold is rare, the accurate estimation of the corresponding probability requires a huge number of samples. When the explicit form of the cumulative distribution function of each component of the variable is known, the inverse transform likelihood ratio method is directly applicable scheme to estimate the tail probability efficiently. The method is a type of the importance sampling and its efficiency depends on the selection of the importance sampling distribution. When the cumulative distribution of the multivariate random variable is represented by a copula and its marginal distributions, we develop an iterative algorithm to find the optimal importance sampling distribution, and show the convergence of the algorithm. The performance of the proposed scheme is compared with the crude Monte Carlo simulation numerically.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.4
• /
• pp.270-275
• /
• 2016

We present an approach for acceleration actor-critic algorithm for reinforcement learning with continuous action space. Actor-critic algorithm has already proved its robustness to the infinitely large action spaces in various high dimensional environments. Despite that success, the main problem of the actor-critic algorithm remains the same-speed of convergence to the optimal policy. In high dimensional state and action space, a searching for the correct action in each state takes enormously long time. Therefore, in this paper we suggest a search accelerating function that allows to leverage speed of algorithm convergence and reach optimal policy faster. In our method, we assume that actions may have their own distribution of preference, that independent on the state. Since in the beginning of learning agent act randomly in the environment, it would be more efficient if actions were taken according to the some heuristic function. We demonstrate that heuristically-accelerated actor-critic algorithm learns optimal policy faster, using Educational Process Mining dataset with records of students' course learning process and their grades.

• Journal of Korean Society for Quality Management
• /
• v.40 no.2
• /
• pp.117-125
• /
• 2012

For the highly reliable products, an accelerated degradation test (ADT) is a useful tool which has been employed in industry to obtain reliability-related information within an affordable amount of time and cost. In an ADT, as all other reliability tests, it is important to carefully design the ADT beforehand to obtain estimates of the quantities of interest as precisely as possible. In this paper, optimal ADTs are developed assuming that the constant-stress loading method is employed and the degradation characteristic follows a Wiener process. Under the constraint that the total cost does not exceed a pre-specified budget, the stress levels, the number of test units allocated to each stress level and the number of measurement (termination time) are determined such that the asymptotic variance of the maximum likelihood estimator of the q-th quantile of the lifetime distribution at the use condition is minimized.

• IE interfaces
• /
• v.19 no.3
• /
• pp.245-254
• /
• 2006

Equipments in container terminal have a lot of parts, and an equipment breakdown affects the productivity of terminal. In this paper, we develop a maintenance management system for improving reliability, availability and maintainability of equipments in container terminals. The developed system consists of five modules : equipment structure module, equipment operation management module, maintenance control module, spare part control module and data analysis module. The system supports reliability engineers to manage and improve RAM of equipments in container terminals. For example, FMEA, failure state analysis and life distribution parameters estimation are easily or automatically done by the system. This system also provides optimal preventive maintenance intervals by simulation and optimal yearly PM schedules for equipments in container terminal are recommended.

• Proceedings of the KIEE Conference
• /
• 2003.11a
• /
• pp.151-153
• /
• 2003

This paper proposes determining a optimal number, size and allocation of DGs(Distributed Generations) needed to minimize operation cost of distribution system, obtains economic benefit in operation planning of DG and improves system reliability. System reliability is assessed whether DG install and reliability cost consider. DG optimal allocations are determined to minimize total cost with power buying cost, operation cost of DG, loss cost and outage cost using GA(Genetic Algorithm). And it was determined installed load-point and order.

• Journal of Korean Institute of Industrial Engineers
• /
• v.25 no.4
• /
• pp.466-475
• /
• 1999

A backward Dynamic Programming(DP) model for the optimal facility replacement decision problem during a finite planning horizon is presented. Multiple alternative challengers to a current defender are considered. All facilities are assumed to have finite service lives. The objective of the DP model is to maximize the profit over a finite planning horizon. As for the cost elements, purchasing cost, maintenance costs and repair costs as well as salvage value are considered. The time to failure is assumed to follow a weibull distribution and the maximum likelihood estimation of Weibull parameters is used to evaluate the expected cost of repair. To evaluate the revenue, the rate of operation during a specified period is employed. The cash flow component of each challenger can vary independently according to the time of occurrence and the item can be extended easily. The effects of inflation and the time value of money are considered. The algorithm is illustrated with a numerical example. A MATLAB implementation of the model is used to identify the optimal sequence and timing of the replacement.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.18-20
• /
• 2006

The statistics for the neighbor differences between the particular pixels and their neighbors are introduced. They are incorporated into the filter to remove additive Gaussian noise contaminating images. The derived denoising method corresponds to the maximum likelihood estimator for the heavy-tailed Gaussian distribution. The error norm corresponding to our estimator from the robust statistics is equivalent to Huber's minimax norm. Our estimator is also optimal in the respect of maximizing the efficacy under the above noise environment.

• Proceedings of the KSR Conference
• /
• 2002.05a
• /
• pp.330-335
• /
• 2002

To estimate the reliability of the standard electric multiple unit developed by Korea Railroad Research Institute, the vehicle system composed of 4 cars is divided into 14 subsystems. The 14 subsystems are connected in series. For each subsystem except for car body and bogie, failure rate is evaluated by an optimal failure model used in reliability engineering. For car body and bogie probabilistic structural integrity analysis is carried out. The distribution of failure rate of each part and system is assumed to be exponential. The estimated MTBF of the vehicle satisfies the planned MTBF.