• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.5
• /
• pp.718-723
• /
• 2016

The temperature changes are very important in improving the accuracy of the load forecasting during the summer. It is because the cooling load in summer contribute to the increasing of the load. This paper proposes a weekend load forecasting algorithm using the temperature change characteristic in a summer of Jeju. The days before and after weekends in Jeju, when the load curves are quite different from those of normal weekdays. The temperature change characteristic are obtained by using weekends peak load and high temperature data. And load forecasted based on the sensitivity between unit temperature changes and load variations. Load forecast data with better accuracy are obtained by using the proposed temperature changes than by using the ordinary daily peak load forecasting. The method can be used to reduce the error rate of load forecast.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.940-947
• /
• 2011

Load capacity varies according to a day of the week in traction power supply system, because time schedule in railway is changed as demand for passengers and freights. Therefore, Voltage drop also varies as load capacity. In Korea railway, Voltage collected from catenary in train is decreased, as load supplied traction power supply system is increased. Therefore, investigation about voltage drop should be performed, before development of countermeasure against voltage drop. The investigation can be performed by simulation or field test. Naturally, field test is more precise than simulation. In addition, field test should be carried out at peak load. This paper presents test and analysis about voltage drop in railway. The test is performed in both a day of the week and weekend. The analysis is figured out comparison load capacity between two days and voltage drop across terminal.

• Proceedings of the KIEE Conference
• /
• 1991.11a
• /
• pp.39-42
• /
• 1991

The Application of Artificial Neural Network(ANN) to forecast a load in a power system is investigated. The load forecasting is important in the electric utility industry. This technique, methodology based on the fact that parallel structure can process very fast much information is a promising approach to a load forecasting. ANN that is highly interconnected processing element in a hierachy activated by the each input. The load pattern can be divided distinctively into two patterns, that is, weekday and weekend. ANN is composed of a input layer, several hidden layers, and a output layer and the past data is used to activate input layer. The output of ANN is the load forecast for a given day. The result of this simulation can be used as a reference to a electric utility operation.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.2210-2211
• /
• 2011

Load capacity varies according to a day of the week in traction power supply system, because time schedule in railway is changed as demand for passengers and freights. Therefore, Voltage drop also varies as load capacity. In Korea railway, Voltage collected from catenary in train is decreased, as load supplied traction power supply system is increased. Therefore, investigation about voltage drop should be performed, before development of countermeasure against voltage drop. The investigation can be performed by simulation or field test. Naturally, field test is more precise than simulation. In addition, field test should be carried out at peak load. This paper presents test and analysis about voltage drop in railway. The test is performed in both a day of the week and weekend. The analysis is figured out comparison load capacity between two days and voltage drop across terminal.

• Proceedings of the KIEE Conference
• /
• 2001.05a
• /
• pp.230-232
• /
• 2001

This paper presents a model for short-term load forecasting using multiple time-series. We made one-hour ahead load forecasting without classifying load data according to daily load patterns(e.g. weekday. weekend and holiday) To verify its effectiveness. the results are compared with those of neuro-fuzzy forecasting model(5). The results show that the proposed model has more accurate estimate in forecasting.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.1
• /
• pp.8-14
• /
• 1999

This paper presents the methods of short-term load forecasting Kohonen neural networks and back-propagation neural networks. First, historical load data is divided into 5 patterns for the each seasonal data using Kohonen neural networks and using these results, load forecasting neural network is used for next day hourly load forecasting. Next day hourly load of weekdays and weekend except holidays are forecasted. For load forecasting in summer, max-temperature and min-temperature data as well as historical hourly load date are used as inputs of load forecasting neural networks for a better forecasting accuracy. To show the possibility of the proposed method, it was tested with hourly load data of Korea Electric Power Corporation(1994-95).

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.71-72
• /
• 2011

단기 전력수요예측의 오차를 줄여 불필요한 전력생산을 이전에 방지하는 것은 매우 중요하다. 본 논문에서는 오차율이 높은 연휴 전 평일의 단기 전력수요예측 정확도를 높이기 위해 이전 평일과 주말의 데이터를 이용한 새로운 예측 방법을 제안하고, 추석연휴 전 평일에 제안한 방법을 적용하여 수요예측에 대한 오차가 개선됨을 확인하였다.

• The Proceedings of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.11 no.5
• /
• pp.62-66
• /
• 1997

This paper is presented to short-term load forecast algorithm using weekday change ratio. The week periodicity was excluded from weekday change ratio. That was composed with the power demand forecast term of five and multiple regression model of the three form. The precision was good with 2.8[%]. Also the power demand of special day(weekend) of completely difficult forecast case of using the multiple regression model was able to forecast at this paper. Therefore, the forecast precision was enhanced and the reliable forecast model was constructed.

• 한국태양에너지학회:학술대회논문집
• /
• 2011.04a
• /
• pp.127-132
• /
• 2011

Worldwide, the building energy simulation becomes inevitable step for predicting the energy consumption in building. In simulation process, the expertise is required for the accurate analysis results. In Korea, however, most of user use the inconsistent data with Korea circumstance. In this step, we need to construct the standard input data matched building in Korea. In this study, electricity consumption of apartments in Daejeon is analyzed. The yearly data of a apartment complexes of 2009 are analyzed as monthly, daily(week and weekend), timely, and completion year. With this result, we are able to predict the demand pattern of electricity in a house and make the schedule by demand pattern. The results of this study are followed. The averaged amount of electricity consumption in winter is higher than summer because of the high capacity of heating equipment. All of the house has electric base load from 0.26kWh to 0.5kWh. The average of the electricity consumption of month is shown as 326.7kWh. A week is seperated as 4 part such as week, weekend, Saturday and Sunday. During week, the average of timely electricity consumption is shown as 0.442kWh. The Saturday consumption is 0.453kWh. The Sunday is 0.461kWh.

• Journal of Korean Society for Atmospheric Environment
• /
• v.4 no.1
• /
• pp.79-83
• /
• 1988

To improve working environment for the toll workers who were working at Kyungbu expressway in outskirts of Seoul and Suwon, the status of air pollution surrounding toll booth were measured from March 28 through June 14, 1986. The results were as follows: 1. The amount of TSP (total suspended particle) surrounding toll booth was directly proportional to the traffic load. The ratio of traffic load at Seoul and Suwon toll was 3.2:1 and of TSP was 2.6:1. 2. The proportion of particle larger than 5$\mum$ was 24.8 $\sim$ 34.9% of TSP at Seoul toll and 19.2 $\sim$ 32.7% at Suwon. The proportion of particle less than 2$\mum$ was 38.7 $\sim$ 51.8% of TSP at Seoul toll and 34.8 $\sim$ 54.8% at Suwon. 3. The concentration of respirable particle les than 7$\mum$ measured by personal air sampler was higher in Seoul toll booth than that of Suwon and it seems to be influenced by the exhausion of diesel engine. Especially the concentration of respirable particle of reformed toll booth with air curtain was 20% lower than unreformed one. 4. Concentration of Pb among suspended particles around Seoul toll was 5 times higher than Pb of Suwon toll. So it is considered that there were other possible pollution source of Pb beyond heavy traffic in Seoul toll area. The amount of Pb inside toll booth was extremely small but the concentration of benzo(a)pyrene showed a trend of increase according to traffic stagnation. 5. The concentration of $SO_2$ arround toll showed no difference between weekday and weekend and also showed no relation with traffic load. But the concentration of $NO_2$ was affected by traffic load.