• 전기학회논문지
• /
• 제64권12호
• /
• pp.1666-1672
• /
• 2015

Small islands are quite adequate places where microgrid system with renewable sources can replace diesel engines as operation costs of diesel engine in most small islands are very high. To get the large amount of renewable energy, the microgrid system has very large capacity of renewable sources. The system with large capacity of renewable sources can meet the case when supplied energy is greater than the load and the fluctuation of source output is very large. The battery energy storage system can be a solution to stabilize the system with large capacity of renewable sources. In this case, BESS can be utilized as a master source for the synchronous operation of all sources including diesel engine, wind turbine and PV. The diesel generators can be used as a backup in case the BESS SOC goes below a certain level. In this paper, we suggest a novel unit commitment of diesel generators and operation schedule of pump for water supply service with the information of wind forecast, PV forecast, and load forecast. The proposed methods has been implemented and tested at the test bed in Gasa-Island.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.271-274
• /
• 2005

Under competitive power markets, various long-term and short-term contracts based on spot price are used by producers and consumers. So an accurate forecasting for spot price allow market participants to develop bidding strategies in order to maximize their benefit. Artificial Neural Network is a powerful method in forecasting problem. In this paper we used Radial Basis Function(RBF) network to forecast spot price. To learn ANN, in addition to price history, we used some other effective inputs such as load level, fuel price, generation and transmission facilities situation. Results indicate that this forecasting method is accurate and useful.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1994년도 추계학술대회 논문집 학회본부
• /
• pp.21-23
• /
• 1994

The degree of forecast accuracy with BP-algorithm largely depends upon the neuron number in hidden layer. In order to construct the optimal structure, first, we prescribe the error bounds of learning procedure, and then, we provid the method of incrementing the number of hidden neurons by using the derivative of errors with respect to an output neuron weights. For the case study, we apply the proposed method to forecast the component-wise residential load, and compare this results to that of time series forecasting.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 하계학술대회 논문집 A
• /
• pp.135-137
• /
• 2004

This paper describes new land use estimation method for long term load forecast using $R\startree$ algorithm. Where $R\startree$ algorithms is a proposed method for efficient spatial search. An estimation result showed that execute time of the proposed method is prior to execute time of conventional method.

• 산업기술연구
• /
• 제15권
• /
• pp.187-193
• /
• 1995

In this paper, a short-term load forecasting expert system considering the load variation due to the change in temperature is presented. The change in temperature is an important load variation factor that varies the normal load pattern. The conventional load forecasting methods by artificial neural networks have used the technique where the temperature variables were included in the input neurons of artificial neural networks. However, simply adding the input units of temperature data may make the forecasting accuracy worse, since the accuracy of the load forecasting in this method depends on the accuracy of weather forecasting. In this paper, the fuzzy expert system that modifies the forecasted load using fuzzy rules representing the relations of load and temperature is presented and compared with a conventional load forecasting technique. In the test case of 1991, the proposed model provided a more accurate forecast than the conventional technique.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.104.1-104
• /
• 2001

This paper presents a technique to development load control and management system in order to limits a maximum load demand and saves electric energy consumption. The computer programming proper load forecasting algorithm associated with programmable logic control and digital power meter through inform of multidrop network RS 485 over the twisted pair, over all are contained in this system. The digital power meter can measure a load data such as V, I, pf, P, Q, kWh, kVarh, etc., to be collected in statistics data convey to data base system on microcomputer and then analyzed a moving linear regression of load to forecast load demand Eventually, the result by forecasting are used for compost of load management and shedding for demand monitoring, Cycling on/off load control, Timer control, and Direct control. In this case can effectively reduce the electric energy consumption cost for 10% ...

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 A
• /
• pp.292-294
• /
• 2000

This paper is presented the method peak load forecast based on multiple regression Model. Forecasting model was composed with the temperature-humidity and the discomfort index. Also the week periodicity was excluded from weekday change coefficient of two types. Forecasting result was good with about 3[%]. And, utility of presented forecast model using statistical tests has been proved. Therefore, This results establish appropriateness and fitness of forecast models using peak power demand forecasting.

• 전자공학회논문지
• /
• 제53권1호
• /
• pp.71-78
• /
• 2016

본 논문은 인공 신경망에 기반을 둔 새로운 전력 수요 예측 모델을 제시한다. 인공 신경망 입력 변수로 시간과 날씨요소를 고려하였다. 시간 요소는 하절기와 동절기 전력수요 데이터의 자기 상관계수를 측정하여 선정하였고, 날씨요소는 피어슨 상관계수를 이용하여 선정하였다. 중요한 날씨요소로는 온도와 이슬점으로 이들은 전력수요와 밀접한 상관관계를 가지고 있다. 반면에 습도, 기압, 풍속 등과 같은 날씨요소는 전력수요와의 상관관계가 높지 않게 나타나 신경망의 입력 변수에서 제외하였다. 실험결과 새로이 제안한 인공 신경망을 이용한 전력수요 모델은 시간요소 및 날씨요소와 이에 대한 가중치를 피크 전력율과 계절에 따라 차등 적용하여 높은 적중률을 보였다.

• 대한임베디드공학회논문지
• /
• 제9권3호
• /
• pp.137-143
• /
• 2014

Demand Controller is a load control device that monitor the current power consumption and calculate the forecast power to not exceed the power set by consumer. Accurate demand forecasting is important because of controlling the load use the way that sound a warning and then blocking the load when if forecasted demand exceed the power set by consumer. When if consumer with fluctuating power consumption use the existing forecasting method, management of demand control has the disadvantage of not stable. In this paper, load forecasting of the unit of seconds using the Exponential Smoothing Methods, ARIMA model, Kalman Filter is proposed. Also simulation of load forecasting of the unit of the seconds methods and existing forecasting methods is performed and analyzed the accuracy. As a result of simulation, the accuracy of load forecasting methods in seconds is higher.

• 전기학회논문지
• /
• 제63권11호
• /
• pp.1503-1510
• /
• 2014

This study organizes scenarios on the power supply plans and electricity load forecasts considering their uncertainties and estimates natural gas quantity for electricity generation, total electricity supply cost and air pollutant emission of each scenario. Also the analysis is performed to check the properness of government's natural gas demand forecast and the possibility of achieving the government's CO2 emission target with the current plan and other scenarios. In result, no scenario satisfies the government's CO2 emission target and the natural gas demand could be doubled to the government's forecast. As under-forecast of natural gas demand has caused the increased natural gas procurement cost, it is required to consider uncertainties of power plant construction plan and electricity demand forecast in forecasting the natural gas demand. In addition, it is found that CO2 emission target could be achieved by enlarging natural gas use and demand-side management without big increase of total costs.