• 한국건축친환경설비학회 논문집
• /
• 제12권6호
• /
• pp.627-640
• /
• 2018

Submetering electricity consumption data enables more detail input of end use components, such as lighting, plug, HVAC, and occupancy in building energy modeling. However, such an modeling efforts and results are rarely tried and published in terms of the estimation accuracy of electricity demand. In this research, actual submetering data obtained from a university building is analyzed and provided for building energy modeling practice. As alternative modeling cases, conventional modeling method (Case-1), using reference schedule per building usage, and main metering data based modeling method (Case-2) are established. Detail efforts are added to derive prototypical schedules from the metered data by introducing variability index. The simulation results revealed that Case-1 showed the largest error as we can expect. And Case-2 showed comparative error relative to Case-3 in terms of total electricity estimation. But Case-2 showed about two times larger error in CV (RMSE) in lighting energy demand due to lack of End Use consumption information.

• 시스템엔지니어링학술지
• /
• 제18권2호
• /
• pp.94-107
• /
• 2022

Accidents prevention and mitigation is the highest priority of nuclear power plant (NPP) operation, particularly in the aftermath of the Fukushima Daiichi accident, which has reignited public anxieties and skepticism regarding nuclear energy usage. To deal with accident scenarios more effectively, operators must have ample and precise information about key safety parameters as well as their future trajectories. This work investigates the potential of machine learning in forecasting NPP response in real-time to provide an additional validation method and help reduce human error, especially in accident situations where operators are under a lot of stress. First, a base-case SGTR simulation is carried out by the best-estimate code RELAP5/MOD3.4 to confirm the validity of the model against results reported in the APR1400 Design Control Document (DCD). Then, uncertainty quantification is performed by coupling RELAP5/MOD3.4 and the statistical tool DAKOTA to generate a large enough dataset for the construction and training of neural-based machine learning (ML) models, namely LSTM, GRU, and hybrid CNN-LSTM. Finally, the accuracy and reliability of these models in forecasting system response are tested by their performance on fresh data. To facilitate and oversee the process of developing the ML models, a Systems Engineering (SE) methodology is used to ensure that the work is consistently in line with the originating mission statement and that the findings obtained at each subsequent phase are valid.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2015년도 춘계학술대회
• /
• pp.629-631
• /
• 2015

최근 전기 사용량의 실제 수요가 예측 수요를 벗어남에 따라 나타나는 전력 수급의 불안감을 해결하기 위하여 정부는 보다 효율적인 에너지 관리에 많이 노력을 하고 있다. 2011년 국내최초의 대규모 정전사태인 블랙아웃 사태이후 현재 우리나라의 전력 설비 예비율은 10% 이하로서 전력수급위기는 반복되고 있다. 또한, 에너지 관리 시스템에 대한 관심과 수요는 사회 전 분야로 확대되고 있다. 본 논문에서는 건물 내 전력수급을 최적화하기 위해 유무선 공유기와 DDNS(Dynamic Domain Name Service)를 이용하여 전기 소비 장치의 원격제어 및 모니터링을 위한 Presonal Energy Management System 설계한다. 향후, 원격제어 및 접속에 대한 사용자의 설정을 최소화할 수 있는 방안에 대한 추가적인 연구가 필요하다.

• 산업경영시스템학회지
• /
• 제41권1호
• /
• pp.84-93
• /
• 2018

In this paper, we propose an Elman recurrent neural network to predict and analyze a time series of power energy consumption. To this end, we consider the volatility of the time series and apply the sample variance and the detrended fluctuation analyses to the volatilities. We demonstrate that there exists a correlation in the time series of the volatilities, which suggests that the power consumption time series contain a non-negligible amount of the non-linear correlation. Based on this finding, we adopt the Elman recurrent neural network as the model for the prediction of the power consumption. As the simplest form of the recurrent network, the Elman network is designed to learn sequential or time-varying pattern and could predict learned series of values. The Elman network has a layer of "context units" in addition to a standard feedforward network. By adjusting two parameters in the model and performing the cross validation, we demonstrated that the proposed model predicts the power consumption with the relative errors and the average errors in the range of 2%~5% and 3kWh~8kWh, respectively. To further confirm the experimental results, we performed two types of the cross validations designed for the time series data. We also support the validity of the model by analyzing the multi-step forecasting. We found that the prediction errors tend to be saturated although they increase as the prediction time step increases. The results of this study can be used to the energy management system in terms of the effective control of the cross usage of the electric and the gas energies.

• 전기전자학회논문지
• /
• 제23권1호
• /
• pp.120-126
• /
• 2019

최근 에너지 인터넷에서 지능형 원격검침 인프라를 이용하여 확보된 대량의 전력사용데이터를 기반으로 효과적인 전력수요 예측을 위해 다양한 기계학습기법에 관한 연구가 활발히 진행되고 있다. 본 연구에서는 전력량 데이터와 같은 시계열 데이터에 대해 효율적으로 패턴인식을 수행하는 인공지능 네트워크인 Gated Recurrent Unit(GRU)을 기반으로 딥 러닝 모델을 제안하고, 실제 가정의 전력사용량 데이터를 토대로 예측 성능을 분석한다. 제안한 학습 모델의 예측 성능과 기존의 Long Short Term Memory (LSTM) 인공지능 네트워크 기반의 전력량 예측 성능을 비교하며, 성능평가 지표로써 Mean Squared Error (MSE), Mean Absolute Error (MAE), Forecast Skill Score, Normalized Root Mean Squared Error (RMSE), Normalized Mean Bias Error (NMBE)를 이용한다. 실험 결과에서 GRU기반의 제안한 시계열 데이터 예측 모델의 전력량 수요 예측 성능이 개선되는 것을 확인한다.