• Korean Journal of Artificial Intelligence
• /
• v.12 no.1
• /
• pp.17-24
• /
• 2024

This paper introduces a novel approach to time-series estimation for energy load forecasting within Virtual Power Plant (VPP) systems, leveraging advanced artificial intelligence (AI) algorithms, namely Long Short-Term Memory (LSTM) and Seasonal Autoregressive Integrated Moving Average (SARIMA). Virtual power plants, which integrate diverse microgrids managed by Energy Management Systems (EMS), require precise forecasting techniques to balance energy supply and demand efficiently. The paper introduces a hybrid-method forecasting model combining a parametric-based statistical technique and an AI algorithm. The LSTM algorithm is particularly employed to discern pattern correlations over fixed intervals, crucial for predicting accurate future energy loads. SARIMA is applied to generate time-series forecasts, accounting for non-stationary and seasonal variations. The forecasting model incorporates a broad spectrum of distributed energy resources, including renewable energy sources and conventional power plants. Data spanning a decade, sourced from the Korea Power Exchange (KPX) Electrical Power Statistical Information System (EPSIS), were utilized to validate the model. The proposed hybrid LSTM-SARIMA model with parameter sets (1, 1, 1, 12) and (2, 1, 1, 12) demonstrated a high fidelity to the actual observed data. Thus, it is concluded that the optimized system notably surpasses traditional forecasting methods, indicating that this model offers a viable solution for EMS to enhance short-term load forecasting.

• Ocean and Polar Research
• /
• v.31 no.1
• /
• pp.71-76
• /
• 2009

Drastic changes in the water quality and phytoplankton community of the new Saemankeum Lakeduring the first decade following the construction of the Saemankeum Sea Wall has been considered to be unavoidable. Input of eutrophicated water through the Mankyeong River and Dongjin River might produce more direct effects on the water quality and phytoplankton community, which lead us to launch a long-term semi-weekly investigation at the "Mankyeong Bridge" monitoring point to resolve its short-term effect as well as long-term stabilization of the ecosystem in the new Saemankeum Lake. During 15 months starting from June 2006, the water temperature varied in accordance with the typical seasonal variations in temperate on the coasts, and no significant daily variations evoked by tidal cycle could be detected. However, there was an inverse relationship between seasonal precipitation and salinity even though the range in annual variation was drastically reduced right after the construction of the Saemankeum Sea Wall. Species richness in the phytoplankton community was also reduced due to the narrowed annual range of salinity, which would eliminate the mid-high salinity species from the Mankyeong Bridge monitoring point. Similarly, species diversity was decreased with increased dominance of the phytoplankton community after the construction. Between the two summer seasons during the present study, species diversity was higher in 2007 than in 2006, which might indicate the early stage of a gradual stabilization in the ecosystem including the phytoplankton community at the monitoring station. The phytoplankton community thus needs to be monitored on a long-term basis to identify indirect signals that can be used to assess the stability of the ecosystem in the young Saemankeum Lake.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.211-214
• /
• 1997

This paper applies fuzzy self-tuning PID controller in DS/CDMA cellular system. Power control is essential in DS/CDMA to compensate for the differing received powers due to both the slowly varying long-term and fast varying short-term fading processes and co-channel interference. The controller proposed is adaptable for the variations of the system dynamics and especially for the variable time delay which exists in mobile radio systems. Accordingly the results is the smaller power control error, that is, the smaller average transmitting power of mobile compared with the conventional control schemes. Because interferences to the other mobiles are reduced, the capacity of CDMA can be increased.

• Journal of electromagnetic engineering and science
• /
• v.4 no.1
• /
• pp.23-29
• /
• 2004

In this paper we analyze convergence constraints and time constant of IT-LMS algorithm and derive a method of making it's time constant independent of signal power by using input variance estimation. The method for estimating the input variance is to use a single-pole low-pass filter(LPF) with common smoothing parameter value, θ. The estimator is with narrow bandwidth for large θ but with wide bandwidth for small θ. This small θ gives long term average estimation(low frequency) of the fluctuating input variance well as short term variations (high frequency) of the input power. In our simulations of multipath communication channel equalization environments, the method with large θ has shown not as much improved convergence speed as the speed of the original IT-LMS algorithm. The proposed method with small θ=0.01 reach its minimum MSE in 100 samples whereas the IT-LMS converges in 200 samples. This shows the proposed, tap-power normalized IT-LMS algorithm can be applied more effectively to digital wireless communication systems.

• Journal of Astronomy and Space Sciences
• /
• v.9 no.1
• /
• pp.89-96
• /
• 1992

UBV observations of VV Cep were made in 1988-1992 as a part of the Ten-year Observing Program for Long Period Eclipsing Binary Stars(1982-1992) at Yonsei University Observatory. In addition to these the observations in the longer passbands in R and I are also made in the 1991-1992 season at the same observatory. Atmospheric extinction coefficinets determined by a comparison star 20 Cap for B and V each night have been deduced a linear relation, $K_B$=0.159+1.066kV. In this paper, light curves of this star in BVRI passbands for the 1991-1992 season only are presented. Two periodic light variations of both long-term and short-term are found as for 90 days and 20 days, respectively.

• Journal of the korean society of oceanography
• /
• v.38 no.3
• /
• pp.135-142
• /
• 2003

Gas flux across the air-sea interface is often determined by the product of gas transfer velocity k) and the difference of concentrations in water and air. k is primarily controlled by wind stress on the air-sea interface, thus all parameterizations ofk involve wind speed, a rough indicator of wind stress, as one of the independent variables. We attempted to explore the spatial and temporal variations of k in the East (Japan) Sea using a database from Naet al. (1992). Three different parameterizations were employed: those of Liss and Merlivat (1986), Wanninkhof(1992), and Wanninkhofand McGillis (1999). The strong non-linear dependence of k on wind speed in all parameterizations leads us to examine the effect of time resolution, in which the binned wind speeds are averaged, on the estimation ofk. Two time resolutions of 12 hours (short-term) and one month (long-term) were chosen. The mean wind speeds were fed into the given parameterizations, resulting in six different transfer velocities of $CO_2$ ranging from 12 to 32 cm/h. In addition to the threefold difference depending on the choice of parameterization, the long-term average of wind speed results in a value ofk up to 20% higher than the short-term (12 hours) average of wind speed due to the non-Rayleigh wind distribution in the East (Japan) Sea. While it is not known which parameterization is more reliable, this study proposes that the time-averaged wind speed should not be used in areas where non-Ralyleigh wind distribution prevails such as the East (Japan) Sea. The net annual $CO_2$ flux was estimated using the value of k described above and the monthly ${\Delta}fCO_2$ of Oh et al. (1999); this ranges from 0.034 to 0.11 Gt-C/yr.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.12
• /
• pp.238-244
• /
• 2013

For musical genre classification, various types of feature vectors are utilized. Mel-frequency cepstral coefficient (MFCC), decorrelated filter bank (DFB), and octave-based spectral contrast (OSC) are widely used as short-term features, and their long-term variations are also utilized. In this paper, OSC features are extracted not only in the single-octave band domain, but also in the multiple-octave band one to capture the correlation between octave bands. As a baseline system, we select the genre classification system that won the fourth place in the 2012 music information retrieval evaluation exchange (MIREX) contest. By applying the OSC features based on multiple-octave bands, we obtain the better classification accuracy by 0.40% and 3.15% for the GTZAN and Ballroom databases, respectively.

• Environmental Engineering Research
• /
• v.19 no.4
• /
• pp.331-338
• /
• 2014

Descriptive statistics methods were used to study the spatiotemporal variations and sources of ambient particulate matter ($PM_{10}$) in Luzhou, China. The analyzed datasets were collected from four national air quality monitoring stations: Jiushi (S1), Xiaoshi (S2), Zhongshan (S3), Lantian (S4) over the period of 2003-2012. This city was subjected serious $PM_{10}$ pollution, and the long-term annual average $PM_{10}$ concentrations varied from 76 to $136{\mu}g/m^3$. The maximum concentration was more than 3-fold of the annual average ($40{\mu}g/m^3$) issued by EPA-China for the ambient air quality. General temporal pattern was characterized by high concentrations in winter and low concentrations in summer, and general spatial gradient was in the reduction order of S2 > S4 > S3 > S1, which were both due to different particulate contributors and special meteorological conditions. The source apportionment indicated that vehicular emissions, road dusts, coal burning and chemical dusts were the major contributors of the identified $PM_{10}$ pollution, and the vehicular emissions and the road wear re-suspended particles dominated the heavy $PM_{10}$ pollution in recent years. Two other potential sources, agricultural and celebration activities could decrease the air quality in a short term. Finally, some corresponding suggestions and measures were provided to improve the air quality.

• Journal of Korean Society for Atmospheric Environment
• /
• v.31 no.2
• /
• pp.181-194
• /
• 2015

Spatial-temporal meteorological features of the Ulsan metropolitan region (UMR) were analyzed using observations and high-resolution numerical modeling. Long-term trend analysis (1970~2013) showed a significant increase of $0.033^{\circ}Cyr^{-1}$ in the 5-year moving average temperature, although detailed short-term features varied, whereas wind speed and relative humidity over the same period displayed clear decreases of $-0.007ms^{-1}$ and $-0.29%yr^{-1}$, respectively. These trends indicate the effects of regional climate change and urbanization in the UMR. Seasonal variations averaged for the most recent three years, 2011~2013, showed that temperatures in three different regions (urban/industrial, suburban, coastal areas) of the UMR had similar seasonality, but significant differences among them were observed for a certain season. Urban and industrial complex regions were characterized by relatively higher temperatures with large differences (max.: $3.6^{\circ}C$) from that in the coastal area in summer. For wind speed, strong values in the range from 3.3 to $3.9ms^{-1}$ occurred in the coastal areas, with large differences clearly shown between the three regions in September and October. Diurnal variations of temperature were characterized by pronounced differences during the daytime (in summer) or nighttime (in winter) between the three regions. Results from the WRF modeling performed for four months of 2012 showed large variations in gridaverage temperature and winds in the UMR, which displayed significant changes by season. Especially, a clear temperature rise in the urban center was identified in July ($0.6^{\circ}C$ higher than nearby urban areas), and overall, relatively weak winds were simulated over urban and inland suburban regions in all seasons.

• Journal of the East Asian Society of Dietary Life
• /
• v.20 no.5
• /
• pp.776-784
• /
• 2010

This study investigated causal relationships between goal orientation, sales and performance towards increasing the effectiveness of up-selling in internal promotion methods in family restaurants and provided implications about the hiring and training of sales people. The subjects were 232 sales people in family restaurants. The data were collected by self-administered questionnaires and analyzed by exploratory factor analysis, reliability analysis, comparative analysis of the average, and regression analysis. Results, showed that variations in goal orientation, sales, and performance depended on the age and experience of salespeople and that goal orientation makes adaptive selling more effective. It turned out that effort selling affects up-selling result than adaptive selling. Long-term workers were better than short-term workers in goal orientation, selling, and up-selling results, so human resource management needs to implement a long-term plan to enhance these effects. And, because effort selling is more effective than adaptive selling in up-selling results in family restaurants, effort selling requires training.