• Proceedings of the KIEE Conference
• /
• 1989.07a
• /
• pp.202-206
• /
• 1989

A new algorithm is suggested to solve the optimal reactive power control(optimal VAR control) problem. An efficient computer program based on the latest achievements in the sparse matrix/vector techniques has been developed for this purpose. The model minimizes the real power losses in the system. The constraints include the reactive power limits of the generators, limits on the bus voltages and the operating limits of control variables- the transformer tap positions, generator terminal voltages and switchable reactive power sources. The method developed herein employs linearized sensitivity relationships of power systems to establish both the objective function for minimizing the system losses and the system performance sensitivities relating dependent and control variables. The algorithm consists of two modules, i.e. the Q-V module for reactive power-voltage control, Load flow module for computational error adjustments. In particular, the acceleration factor technique is introduced to enhance the convergence property in Q-module, The combined use of the afore-mentioned two modules ensures more effective and efficient solutions for optimal reactive power dispatch problems. Results of the application of the method to the sample system and other worst-case system demonstrated that the algorithm suggested herein is compared favourably with conventional ones in terms of computation accuracy and convergence characteristics.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.39 no.3
• /
• pp.232-239
• /
• 1990

A new algorithm is suggested to solve the optimal reactive power and voltage control (optimal VAR control) problem. The model minimizes the real power losses in the system. The constraints include the reactive power limits of the generators, limits on the bus voltages and the operating limits of control variables-the transformer tap positions generator terminal voltages and switchable reactive power sources. The method presented herein, using a newly developed Jacobian decomposition method, employs linearized sensitivity relationships of power systems to establish both the objective function for minimizing the system losses and the system performance sensitivities relating dependent and control variables. The algorithm consists of two modules, i.e. the Q-V module for reactive power-voltage control, and load flow module for computational error adjustments. In particular the acceleration factor technique is introduced to enhance the convergence property in Q-V module. The combined use of the afore-mentioned two modules ensures more effective and efficient solutions for optimal reactive power dispatch problems. Results of the application of the method to a sample system and other worst-case systems demonstrated that the algorithm suggested herein is compared favourably with conventional ones in terms of computation accuracy and convergence characteristics.

• Journal of Information Technology Services
• /
• v.15 no.4
• /
• pp.85-95
• /
• 2016

Recently, deep learning and machine learning have attracted considerable attention and many supporting frameworks appeared. In artificial intelligence field, a large body of research is underway to apply the relevant knowledge for complex problem-solving, necessitating the application of various learning algorithms and training methods to artificial intelligence systems. In addition, there is a dearth of performance evaluation of decision making agents. The decision making agent that can find optimal solutions by using reinforcement learning methods designed through this research can collect raw pixel data observed from dynamic environments and make decisions by itself based on the data. The decision making agent uses convolutional neural networks to classify situations it confronts, and the data observed from the environment undergoes preprocessing before being used. This research represents how the convolutional neural networks and the decision making agent are configured, analyzes learning performance through a value-based algorithm and a policy-based algorithm : a Deep Q-Networks and a Policy Gradient, sets forth their differences and demonstrates how the convolutional neural networks affect entire learning performance when using pixel data. This research is expected to contribute to the improvement of artificial intelligence systems which can efficiently find optimal solutions by using features extracted from raw pixel data.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2006.05a
• /
• pp.321-326
• /
• 2006

This paper is proposed an efficiency optimization control algorithm for a synchronous reluctance motor which minimizes the copper and iron losses. The design of the speed controller based on adaptive fuzzy-neural networks(AFNN) controller that is implemented using fuzzy control and neural networks. There exists a variety of combinations of d and q-axis current which provide a specific motor torque. The objective of the efficiency optimization controller is to seek a combination of d and q-axis current components, which provides minimum losses at a certain operating point in steady state. It is shown that the current components which directly govern the torque production have been very well regulated by the efficiency optimization control scheme. The proposed algorithm allows the electromagnetic losses in variable speed and torque drives to be reduced while keeping good torque control dynamics. The control performance of the hybrid artificial intelligent controller is evaluated by analysis for various operating conditions. Analysis results are presented to show the validity of the proposed algorithm.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.135-135
• /
• 2022

In this study, we evaluated uncertainties in baseflow separation filter methods focusing on changes in recession constant (𝛼) values, which include Lynie & Holick (LH) algorithm, Chapman algorithm, Eckhardt filter, and EWMA filter. Here, we analyzed daily streamflow data at 14 stations in the Urmia Lake basin, Iran, from 2015 to 2019. The 𝛼 values were computed using three different approaches from calculating the slope of a recession curve by averaging the flow over all seasons, a correlation method, and a mean value of the ratio of Q_t+1 to Q_t. In addition to the 𝛼 values, the BFImax (maximum value of the baseflow index (BFI)) was determined for the Eckhardt filter through the backward filter method. As results, it indicates that the estimated baseflow is dependent upon the selection of filter methods, their parameters, and catchment characteristics at different stations. In particular, the EWMA filter showed the least changes in estimating the baseflow value by changing the 𝛼 value, and the Eckhardt filter and LH algorithm showed the highest sensitivity to this parameter at different stations.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.11a
• /
• pp.230-231
• /
• 2023

This study proposes a deep reinforcement learning-based algorithm to automatically generate a ship's passage plan. First, Busan Port and Gwangyang Port were selected as target areas, and a container ship with a draft of 16m was designated as the target vessel. The experimental results showed that the ship's passage plan generated using deep reinforcement learning was more efficient than the Q-learning-based algorithm used in previous research. This algorithm presents a method to generate a ship's passage plan automatically and can contribute to improving maritime safety and efficiency.

• Journal of applied mathematics & informatics
• /
• v.28 no.1_2
• /
• pp.13-30
• /
• 2010

Let C be a nonempty closed convex subset of a real Hilbert space H. Consider the following iterative algorithm given by $x_0\;{\in}\;C$ arbitrarily chosen, $x_{n+1}\;=\;{\alpha}_n{\gamma}f(W_nx_n)+{\beta}_nx_n+((1-{\beta}_n)I-{\alpha}_nA)W_nP_C(I-s_nB)x_n$, ${\forall}_n\;{\geq}\;0$, where $\gamma$ > 0, B : C $\rightarrow$ H is a $\beta$-inverse-strongly monotone mapping, f is a contraction of H into itself with a coefficient $\alpha$ (0 < $\alpha$ < 1), $P_C$ is a projection of H onto C, A is a strongly positive linear bounded operator on H and $W_n$ is the W-mapping generated by a finite family of nonexpansive mappings $T_1$, $T_2$, ${\ldots}$, $T_N$ and {$\lambda_{n,1}$}, {$\lambda_{n,2}$}, ${\ldots}$, {$\lambda_{n,N}$}. Nonexpansivity of each $T_i$ ensures the nonexpansivity of $W_n$. We prove that the sequence {$x_n$} generated by the above iterative algorithm converges strongly to a common fixed point $q\;{\in}\;F$ := $\bigcap^N_{i=1}F(T_i)\;\bigcap\;VI(C,\;B)$ which solves the variational inequality $\langle({\gamma}f\;-\;A)q,\;p\;-\;q{\rangle}\;{\leq}\;0$ for all $p\;{\in}\;F$. Using this result, we consider the problem of finding a common fixed point of a finite family of nonexpansive mappings and a strictly pseudocontractive mapping and the problem of finding a common element of the set of common fixed points of a finite family of nonexpansive mappings and the set of zeros of an inverse-strongly monotone mapping. The results obtained in this paper extend and improve the several recent results in this area.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.5
• /
• pp.591-597
• /
• 2007

In swarm robot systems, each robot must behaves by itself according to the its states and environments, and if necessary, must cooperates with other robots in order to carry out a given task. Therefore it is essential that each robot has both learning and evolution ability to adapt the dynamic environments. In this paper, the new polygon based Q-learning algorithm and distributed genetic algorithms are proposed for behavior learning and evolution of collective autonomous mobile robots. And by distributed genetic algorithm exchanging the chromosome acquired under different environments by communication each robot can improve its behavior ability Specially, in order to improve the performance of evolution, selective crossover using the characteristic of reinforcement learning is adopted in this paper. we verify the effectiveness of the proposed method by applying it to cooperative search problem.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1037-1044
• /
• 2020

Since radar wind profiler (RWP) provides wind field data with high time and space resolution in all weather conditions, their verification of the accuracy and quality is essential. The simultaneous wind measurement from rawinsonde is commonly used to evaluate wind vectors from RWP. In this study, the simulation algorithm which produces the spectrum and raw time series (I/Q) data from the average values of moments is presented as a step-by-step verification method for the signal processing algorithm. The possibility of the simulation algorithm was also confirmed through comparison with the raw data of LAP-3000. The Doppler power spectrum was generated by assuming the density function of the skew-normal distribution and by using the moment values as the parameter. The simulated spectrum was generated through random numbers. In addition, the coherent averaged I/Q data was generated by random phase and inverse discrete Fourier transform, and raw I/Q data was generated through the Dirichlet distribution.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.12
• /
• pp.437-444
• /
• 2022

Recently, research on mobile edge services has been conducted to handle computationally intensive and latency-sensitive tasks occurring in wireless networks. However, MEC, which is fixed on the ground, cannot flexibly cope with situations where task processing requests increase sharply, such as commuting time. To solve this problem, a technology that provides edge services using UAVs (Unmanned Aerial Vehicles) has emerged. Unlike ground MEC servers, UAVs have limited battery capacity, so it is necessary to optimize energy efficiency through load balancing between UAV MEC servers. Therefore, in this paper, we propose a load balancing technique with consideration of the energy state of UAVs and the mobility of vehicles. The proposed technique is composed of task offloading scheme using genetic algorithm and task migration scheme using Q-learning. To evaluate the performance of the proposed technique, experiments were conducted with varying mobility speed and number of vehicles, and performance was analyzed in terms of load variance, energy consumption, communication overhead, and delay constraint satisfaction rate.