• 한국태양에너지학회 논문집
• /
• 제40권5호
• /
• pp.13-22
• /
• 2020

Day ahead forecast is necessary for the electricity market to stabilize the electricity penetration. Numerical weather prediction is usually employed to produce the solar irradiance as well as electric power forecast for longer than 12 hours forecast horizon. Korea Meteorological Administration operates the UM-LDAPS model to produce the 36 hours forecast of hourly total irradiance 4 times a day. This study interpolates the hourly total irradiance into 15 minute instantaneous irradiance and then compare them with observed solar irradiance at four ground stations at 1 minute resolution. Numerical weather prediction model employed here was produced at 00 UTC or 18 UTC from January to December, 2018. To compare the statistical model for the forecast horizon less than 3 hours, smart persistent model is used as a reference model. Relative root mean square error of 15 minute instantaneous irradiance are averaged over all ground stations as being 18.4% and 19.6% initialized at 18 and 00 UTC, respectively. Numerical weather prediction is better than smart persistent model at 1 hour after simulation began.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 추계학술대회 논문집 전력기술부문
• /
• pp.438-440
• /
• 2003

This paper resents an application of an Artificial Neural Network(ANN) technique to forecast the short-term system marginal price(SMP). The forecasting of SMP is a very important factor in an electricity market for the optimal biddings of market participants as well as for the market stabilization of regulatory bodies. The proposed neural network scheme is composed of three layers. In this process, input data are set up to reflect market conditions. And the $\lambda$ that is the coefficient of activation function is modified in order to give a proper signal to each neuron and improve the adaptability for a neural network. The reposed techniques are trained validated and tested with the historical real-world data from korea Power Exchange(KPX).

• 자원ㆍ환경경제연구
• /
• 제28권2호
• /
• pp.177-200
• /
• 2019

전력수급계획의 근간이 되는 전력수요 전망은 GDP와 기상변수 등 다양한 요인에 의해 영향을 받기 때문에 확률 프로세스로 이해할 수 있다. 이 전망치를 바탕으로 전력설비의 구성 방안이 수립되는데, 실제 의사결정 과정은 주어진 확률분포에 대한 정보가 온전하다고 가정한다는 한계를 가진다. 그러나 현실적으로는 확률분포 자체의 중첩 불확실성이 존재하기 때문에 강건한 최적계획(robust optimization)의 수립이 필요하다. 본 논문은 중첩 불확실성을 포함한 발전설비 조정의 최적의사결정을 연구한다. 구체적으로 원자력의 감축투자 관련 실물옵션 모형을 수립하고 우리나라 전력수급기본계획의 특성을 고려한 중첩 불확실성하에서 원전감축 투자를 분석한다. 분석 결과, 현재의 원전축소 정책은 전력수요 증가율이 낮다는 것을 전제로 한 정책으로서 전력수요 증가에 대응할 수 있는 정책 강건성을 갖추지는 못한다는 것을 보여준다.

• 플랜트 저널
• /
• 제14권1호
• /
• pp.47-51
• /
• 2018

본 연구에서는 석탄화력발전의 출력 감소가 계통한계가격과 온실가스감축량에 어떻게 영향을 미치는지 분석하였다. 분석방법은 국영 발전회사에서 이용하는 전력거래예측프로그램을 이용하였으며 전력계통의 운영조건은 제7차 전력수급기본계획의 전력수요와 전원구성을 근거로 하였다. 분석결과 전체 석탄화력발전의 최대출력을 29 [%]까지 감소한 경우 계통한계가격은 감소전과 비교하여 12 [%p] 상승하고 온실가스 배출량은 9,966 [kton] 감축되었다. 또한 석탄화력발전기 전체 용량의 30 [%]에 해당하는 저효율 석탄화력발전기 16기를 정지한 경우 계통한계가격은 14 [%p] 까지 증가하였고 온실가스 배출량은 12,574[kton]까지 감축 가능함을 알 수 있었다.

• 한국시스템다이내믹스연구
• /
• 제5권1호
• /
• pp.49-71
• /
• 2004

Demand-side Management can be defined as'any utility activity aimed at modifying customers' use of energy to produce desired changes in the utility's load shape'. Customers benefit by being able to control energy costs and improve quality of life and become more productive. Utilities benefit from DSM's value as a resource that enhances asset utilization and reduces both fuel costs and environmental emissions. The scope of DSM includes load management through rate schedules and conservation by improving energy effciency and using electricity consumption effectively. This paper study the DSM resource evaluation and customer behavior analysis todesign the DSM Program plan in response to customer needs. We develop basic system dynamics model to analysis the customer behavior based on a survey research. The DSM Program participants in the Hi- efficiency Inverter, Electric motor and efficient lighting applicancies operating by Conservation program 2002 become the survey objects. DSM resource evaluation evaluate firstt the distribution potentialities of each machine and then forecast the degree of diffusion. We apply the system dynamic approach to simulate the dynamic DSM market situation at the domestic beginning. This model will give the energy Planner the opportunity to create different scenarios for DSM program planning. Also it will lead to increased understanding of the dynamic DSM market

• 대한전기학회논문지:전력기술부문A
• /
• 제54권3호
• /
• pp.144-151
• /
• 2005

This paper presents a forecasting technique of the short-term marginal price (SMP) using an Artificial Neural Network (ANN). The SW forecasting is a very important element in an electricity market for the optimal biddings of market participants as well as for market stabilization of regulatory bodies. Input data are organized in two different approaches, time-axis and day-axis approaches, and the resulting patterns are used to train the ANN. Performances of the two approaches are compared and the better estimate is selected by a composition rule to forecast the SMP. By combining the two approaches, the proposed composition technique reflects the characteristics of hourly, daily and seasonal variations, as well as the condition of sudden changes in the spot market, and thus improves the accuracy of forecasting. The proposed method is applied to the historical real-world data from the Korea Power Exchange (KPX) to verify the effectiveness of the technique.

• 산업공학
• /
• 제17권3호
• /
• pp.269-281
• /
• 2004

How to maintain the optimal electric power generation mix is one of the important problems in electric power industry. The objective of this study is to develop a computer model which can be used to forecast the investment in power generation unit by the plant owners after restructuring of electric power industry. Restructuring of electric power industry will make difference in decision making process of investment in power generation unit. After Privatiazation of Power Industry, Gencos will think that profit is the most important factor among all others attracting the investment in the industry. Coal power generation is better than LNG CCGT in terms of profit. However, many studies show that LNG CCGT will be main electric power generation source because the rest of factors other than profit in LNG CCGT are superior than Coal power generation. The impacts of the various government policies can be analyzed using the computer model, thus the government can formulate effective policies for achieving the desired electric power generation mix.

• 한국시스템다이내믹스연구
• /
• 제4권1호
• /
• pp.33-53
• /
• 2003

How to maintain the optimal electric power generation mix is one of the important problems in electric power industry. The objective of this study is to develop a computer model which can be used to forecast the investment in power generation unit by the plant owners after restructuring of electric power industry. Restructuring of electric power industry will make difference in decision making process of investment in power generation unit. After Privatiazation of Power Industry, Gencos will think that profit is the most important factor among all others attracting the investment in the industry. Coal power generation is better than LNG CCGT in terms of profit. However, many studies show that LNG CCGT will be main electric power generation source because the rest of factors other than profit in LNG CCGT are superior than Coal power generation. Because the nst of factors other than profit in LNG CCGT are superior than Coal power generation. The impacts of the various government policies can be analyzed using the computer model, thus the government can formulate effective policies for achieving the desired electric power generation mix.

• 전기전자학회논문지
• /
• 제26권3호
• /
• pp.355-363
• /
• 2022

우리나라는 2050년 탄소중립을 목표로 신재생에너지 중심으로 에너지 공급원을 전환하고 확대하는 계획을 추진 중이다. 신재생에너지의 간헐적 특성으로 에너지 공급이 불안정성이 커짐에 따라 정확한 신재생에너지 발전량 예측의 중요성이 함께 커지고 있다. 이에 따라 정부는 신재생에너지를 집합화하여 관리하기 위한 소규모 전력중개시장을 개설하였고, 재생에너지 발전량 예측제도를 도입하여 예측정확도에 따라 정산금을 지급하는 제도를 시행 중이다. 본 논문에서는 우리나라 신재생에너지 전원의 대부분을 차지하는 태양광 발전에 대하여 통계적 및 인공지능 모형을 이용하여 예측모델을 구현하였으며, 각 모형의 예측정확도 결과를 비교 분석하였다. 비교 모델 중에서 CNN-LSTM(Convolutional Long Short-Term Memory Neural Networks) 모형이 가장 높은 성능을 가짐을 확인하였다. 예측정확도에 따른 예측제도 정산금 수익을 추정해보았고, 예측보유 기술 수준에 따라 수익 편차가 24% 정도 커질 수 있음을 확인하였다.

• 전기전자학회논문지
• /
• 제23권3호
• /
• pp.852-857
• /
• 2019

분산자원 집합 거래시장에 참여를 원하는 소비자나 사업자를 위한 가상발전소의 전력거래 플랫폼에서 사업참여자의 수요 자원을 관리하고, 이에 적절한 전략을 제공하기 위해 익일 개별 참여자의 수요와 전체 계통의 전력수요를 예측하는 것이 대단히 중요하다. 이러한 전력거래 플랫폼에서 활용하는 것을 목표로 본 논문은 우선 익일의 24시간 전력계통 전력수요예측 모델을 개발하였다. 본 논문에서는 전력수요예측 데이터의 시계열 특성을 고려하여 딥러닝 기법 중 LSTM 알고리즘을 사용하였고, 전력수요량 등의 입출력 값에 원-핫 인코딩 기법을 적용하는 새로운 시도를 하였다. 성능평가에서 일반 DNN과 본 논문에서 구현된 LSTM 예측모델은 각각 평균 제곱근 오차 4.50, 1.89를 나타내어 LSTM 모델이 예측정확도가 높게 나타났다.