• 전기학회논문지P
• /
• 제67권4호
• /
• pp.183-190
• /
• 2018

Predicting accurate electricity prices is an important task in the electricity trading market. To address the electricity price forecasting problem, various approaches have been proposed so far and it is known that linear regression-based approaches are the best. However, the use of such linear regression-based methods is limited due to low accuracy and performance. In traditional linear regression methods, it is not practical to find a nonlinear regression model that explains the training data well. If the training data is complex (i.e., small-sized individual data and large-sized features), it is difficult to find the polynomial function with n terms as the model that fits to the training data. On the other hand, as a linear regression model approximating a nonlinear regression model is used, the accuracy of the model drops considerably because it does not accurately reflect the characteristics of the training data. To cope with this problem, we propose a new electricity price forecasting method that divides the entire dataset to multiple split datasets and find the best linear regression models, each of which is the optimal model in each dataset. Meanwhile, to improve the performance of the proposed method, we modify the proposed localized linear regression method in the map and reduce way that is a framework for parallel processing data stored in a Hadoop distributed file system. Our experimental results show that the proposed model outperforms the existing linear regression model. Specifically, the accuracy of the proposed method is improved by 45% and the performance is faster 5 times than the existing linear regression-based model.

• KIEAE Journal
• /
• 제11권5호
• /
• pp.91-96
• /
• 2011

This study is to analysis the characteristics of electric power consumption of apartments complex in Korea. This study shows the pattern of electric power consumption and correlation of each apartment complex's completion year monthly and timely. With this result, we are able to predict the demand pattern of electricity in a house and make the schedule by demand pattern. It is expected this data is used as reference of electric consumption of Daejeon area to operate the simulation tools to predict the building energy. The yearly data of 10 apartment complexes of 2010 are analyzed. The results of this study are followed. The averaged amount of electricity consumption in winter is higher as 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 310.2kWh. 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 0.426kWh. The Saturday consumption is 0.437kWh. The Sunday is 0.445kWh. The peak electricity consumption in summer and winter is measured. The peak consumption on summer season is 1.389kW on 22th August 64% higher than winter season 0.887kW on 3rd January.

• 응용통계연구
• /
• 제32권5호
• /
• pp.703-720
• /
• 2019

최근 빈번하게 발생하는 이상기온과 기후변화로 인하여 전력수요의 변동성이 커지고 있으며 기온 영향의 증가와 함께 기온변화에 대한 전력수요의 반응은 비선형성과 비대칭성으로 나타나고 있다. 정부 에너지 정책의 변화와 4차 산업혁명의 전개에 따라 기온 효과를 보다 정확하게 추정하고 예측하는 것은 안정적 전력수급 관리를 위하여 중요한 과제이다. 본 연구는 기온변화에 대한 전력수요의 비선형적 반응에 대하여 부분선형모형을 이용하여 분석하고자 한다. 기온변화와 전력수요의 비선형·비대칭적 관계를 측정하기 위하여 Robinson의 double residual 준모수적 추정과 스플라인 추정을 적용하였다. 기상변수와 전력 소비에 대한 시간 단위 고주기 자료를 사용하여 부분선형모형으로 추정한 기온변화와 전력 소비의 관계는 기존 모수적 모형과는 다른 비선형성과 비대칭성을 갖고 있음을 확인하였다. 부분선형모형을 이용하여 얻은 전력수요에 대한 표본내·표본외 예측은 이차함수 모형과 냉난방도일 모형과 비교하여 우수한 예측력을 보였다. Diebold-Mariano 검정결과, 부분선형모형에서 얻은 예측력 향상은 통계적으로 유의하였다.

• 대한전기학회논문지:전력기술부문A
• /
• 제53권9호
• /
• pp.521-528
• /
• 2004

The demise of the native franchise markets and the emergence of competitive markets in electricity generation service is substantially altering the way that operation and planning activity is conducted and is making it increasingly difficult for market participants such as generation firms to prospect the future electricity markets. Traditional generation expansion planning (GEP) problems which centrally determine the least-cost capacity addition plan that meets forecasted demand within pre-specified reliability criteria over a planning horizon (typically 10 to 20 years) is becoming no more valid in competitive market environments. Therefore, it requires to develop a new methodology for generation investments, which is applicable to the changed electric industry business environments and is able to address the post-privatization situation where individual generation firms seek to maximize their return on generation investments against uncertain market revenues. This paper formulates a new generation expansion planning problem and solve it in a market-oriented manner.

• 전기학회논문지
• /
• 제56권7호
• /
• pp.1205-1210
• /
• 2007

Several mechanisms are introduced for the procurement of capacity adequacy. In the competitive electricity market, however, it is a GENCO that makes generation investment decision. A GENCO will invest a new generator when it can get more profit than cost. There requires a model to evaluate profit with respect to a new generation investment. In the view of long-term investment, evaluation of a profit of a generator in the electricity market is quite different from that of short-term operation. In this paper, a new profit-evaluation model is proposed for the long-term generation investment. It can treat the probabilistic characteristics of generators, ie, forced-outage-rates, which affect profit of generators.

• KDI Journal of Economic Policy
• /
• 제41권4호
• /
• pp.67-99
• /
• 2019

This paper, focusing on the renewable portfolio standard (RPS), evaluates alternative renewable energy policies. We propose a tractable equilibrium model which provides a structural representation of Korea's electricity market, including its energy settlement system and renewable energy certificate (REC) transactions. Arbitrage conditions are used to define the core value of REC prices to identify relevant competitive equilibrium conditions. The model considers R&D investments and learning effects that may affect the development of renewable energy technologies. The model is parameterized to represent the baseline scenario under the currently scheduled RPS reinforcement for a 20% share of renewable generation, and then simulated for alternative scenarios. The result shows that the reinforcement of the RPS leads to higher welfare compared to weakening it as well as repealing it, though there remains room to enhance welfare. It turns out that subsidies are welfare-inferior to the RPS due to financial burdens and that reducing nuclear power generation from the baseline yields lower welfare by worsening environmental externalities.

• 한국정보통신학회논문지
• /
• 제16권8호
• /
• pp.1701-1710
• /
• 2012

최근 저탄소 녹색성장이 세계적 관심사로 등장하면서 온실가스 배출을 최소화하기 위한 핵심으로 스마트 그리드라는 개념이 출현하게 되었다. 이와 같은 스마트 그리드는 전력 서비스의 효율성, 중요성, 신뢰성, 경제성, 지속성을 향상시키기 위해 모든 공급자와 소비자의 전력 생산, 공급, 소비 등을 기존 전력망과 정보통신기술을 접목하여 제공하는 시스템이다. 스마트 그리드를 통해 사용자는 자신의 집에서 사용하는 가전기기의 개별적 사용량 및 총 사용량을 실시간으로 알아볼 수 있으며, 전력 사용량이 최고에 달할 때에는 공급자가 특정 가전기기의 사용량을 제한하는 방식 등으로 효율적인 전력 공급을 수행할 수 있게 된다. 그러나 이와 같이 수집된 사용자의 정보가 노출될 경우, 전력 소비 양상, 생활 방식, 주거형태 등이 노출되는 심각한 프라이버시 문제가 발생하게 된다. 따라서 본 논문에서는 가정에서 전송되는 정보에서 어떠한 가전기기가 얼마만큼의 전력량을 사용했는지 알 수 없도록 보호하는 프로토콜을 제안한다. 본 제안 방식을 통해 전력회사라 하더라도 사용자의 패스워드 없이 어떠한 가전기기가 전력을 사용한지 알 수 없도록 한다.

• 상하수도학회지
• /
• 제31권2호
• /
• pp.177-186
• /
• 2017

This study concerned the analysis on the efficiency of the conversion of water tank type supply system to direct water supply system to examine the feasibility of the conversion, as well as the calculation of optimal conversion range that enables the supply of safe, high-quality water at stable pressure in accordance with the standards of water supply facility. The results of this research showed that when converting water supply system from water tank type supply system to direct water supply system, more nodal points could be properly converted and more reduction of electricity usage was expected in case water pressure rather than residence time was fixed. This means that higher efficacy can be obtained by fixing water pressure when converting water supply system. However, since the number of the locations that received on-spot inspection was small and the electricity usage measured was not exclusively by water supply facility, it is difficult to judge that such reduction of electricity usage accurately represents reduced electricity usage by water supply facility alone. therefore, after having secured on-spot information about a larger number of locations in apartment complexes that have converted water supply system, and utilizing information about electricity usage exclusively by water supply facility, the proposed method of this research could be applied to accurately deducing expected reduction of electricity usage by water supply facilities of various other apartment complexes. It is also considered possible to deduce an effective operation method of water supply system by finding out an area that shows low pressure or low residual chlorine concentration in the optimal conversion range of water supply, followed by estimating the proper location of pumping station or the proper chlorine dosage at the power purification plant that supply water to the target area.

• 한국태양에너지학회 논문집
• /
• 제26권1호
• /
• pp.13-19
• /
• 2006

The efficiency of building-integrated photovoltaic(BIPV) system is mainly determined by solar radiation and the temperature of PV modules. The performance of BIPV systems is reported to be different from that of conventional PV systems installed in the open-air. This paper presents the relationship of solar radiation and electricity generation from a 2kWp roof-integrated PV system that is applied as building elements on an experimental house, and the energy saving effect of the BIPV system for a typical house. For the performance evaluation of the BIPV system, it produced a regression equation with measured data for winter days. The regression equation showed that a comparison of the measured electricity generation and the predicted electricity generation of the BIPV system were meaningful. It showed that an annual electricity generation of the system appeared to cover around 52% of an annual electricity consumption of a typical domestic house with the floor area of $96m^2$.

• 대한원격탐사학회지
• /
• 제40권1호
• /
• pp.81-91
• /
• 2024

전기 에너지는 현대 문명의 핵심 에너지원으로 발전량, 전력 소모량의 변화 추이는 산업 및 생활 전반과 밀접한 관계가 존재한다. 본 연구에서는 남한 지역의 발전량과 야간광 값 사이의 상관관계를 파악하고 이를 이용하여 북한 지역의 월간 발전량 추이를 예측하였다. 연구 결과 서울시의 경우 야간광과 발전량 사이에는 0.34의 낮은 피어슨(Pearson) 상관계수를 보였으나 월 평균 기온을 이용하여 서울시의 가중치가 적용된 야간광 값과 발전량 사이에는 0.79의 높은 피어슨 상관계수를 보였다. 평양시의 월 평균 기온을 이용한 서울시의 가중치가 적용된 야간광 값을 이용하여 북한 지역의 월간 발전량 추이를 예측한 결과 2020년, 2021년 12월의 전월 대비 발전량 상승폭보다 2022년 12월의 전월 대비 발전량 상승폭이 약 60% 높은 것으로 나타났다. 본 연구의 결과는 월간 발전량 자료가 존재하지 않아 기민한 산업 동향 등의 파악이 힘든 지역의 월간 발전량의 추이를 예측하는데 도움이 될 것으로 기대된다.