• 조명전기설비학회논문지
• /
• 제28권1호
• /
• pp.50-56
• /
• 2014

Accurate midterm load forecasting is essential to preventive maintenance programs and reliable demand supply programs. This paper describes a midterm load forecasting method using autoregressive integrated moving average (ARIMA) model which has been widely used in time series forecasting due to its accuracy and predictability. The various ARIMA models are examined in order to find the optimal model having minimum error of the midterm load forecasting. The proposed method is applied to forecast 104-week load pattern using the historical data in Korea. The effectiveness of the proposed method is evaluated by forecasting 104-week load from 2011 to 2012 by using historical data from 2002 to 2010.

• 전기학회논문지
• /
• 제66권3호
• /
• pp.493-499
• /
• 2017

This paper proposes a combined very-short-term and short-term multi-variate time-series model for 24 hour load forecasting. First, the best model for very-short-term and short-term load forecasting is selected by considering the least error value, and then they are combined by the optimal forecasting time. The actual load data of industry complex is used to show the effectiveness of the proposed model. As a result the load forecasting accuracy of the combined model has increased more than a single model for 24 hour load forecasting.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 하계학술대회 논문집 C
• /
• pp.1163-1165
• /
• 1998

This paper presents a method of the regional long-term load forecasting considering economic indicator with the assuption that energy demands proportionally increases with the economic indicators. For the accurate load forecasting, it is very important to scrutinize the correlation among the regional electric power demands, economic indicator and other characteristics because load forecasting results may vary depending on many different factors such as electric power demands, gross products, social trend and so on. Three steps are microscopically and macroscopically used for the regional long-term load forecasting in order to increase the accuracy and practically of the results.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제5권10호
• /
• pp.293-302
• /
• 2016

전기는 생산과 소비가 동시에 이루어지므로 필요한 전력 사용량을 예측하고, 이를 충족시킬 수 있는 충분한 공급능력을 확보해야만 안정적인 전력 공급이 가능하다. 특히, 대학 캠퍼스는 전력 사용이 많은 곳으로 시간과 환경에 따라 전력 변화폭이 다양하다. 이러한 이유로, 효율적인 전력 공급 및 관리를 위해서는 전력 사용량을 실시간으로 예측할 수 있는 모델이 요구된다. 국내외 대학 건물에 대해서는 전력 사용 패턴과 사례 분석을 통해 전력 사용에 영향을 주는 요인들을 파악하기 위한 다양한 연구가 진행되었으나, 전력 사용량의 정량적 예측을 위해서는 더 많은 연구가 필요한 상황이다. 본 논문에서는, 기계 학습 기법을 이용하여 대학 캠퍼스의 전력 사용량 예측 모델을 구성하고 평가한다. 이를 위해, 대학 캠퍼스의 주요 건물 클러스터에 대해 전력 사용량을 15분마다 1년 이상 수집한 데이터 셋을 사용한다. 수집된 전력 사용량 데이터는 수열 형태의 시계열 데이터로 기계 학습 모델에 적용 시 주기성 정보를 반영할 수 없으므로, 2차원 공간의 연속적인 데이터로 증강함으로써 주기성을 반영하였다. 이 데이터와 교육기관의 특성을 반영하기 위한 요일과 공휴일로 구성된 8차원 특성 벡터에 대해 주성분 분석(Principal Component Analysis) 알고리즘을 적용한다. 이어, 인공 신경망(Artificial Neural Network)과 지지 벡터 회귀분석(Support Vector Regression)을 이용하여 전력 사용량 예측 모델을 학습시키고, 5겹 교차검증(5-fold Cross Validation)을 통하여 적용된 기법의 성능을 평가하여, 실제 전력 사용량과 예측 결과를 비교한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 A
• /
• pp.495-497
• /
• 2000

The KEPCO is developing the load forecasting sysetm using land use simulation method and distribution planning system. Distribution planning needs the data of presents loads, forecasted loads sub-statin, and distribution lines. Using the data, determine the sub-station and feeder lines according to the load forecasting data. This paper presents the method of formulation processfor the long term load forecasting and optimal distribution planning and optimal distribution planning. And describes the case study of long term distribution planning of Kwangju city accord to the newly applied method.

• 전기학회논문지
• /
• 제63권4호
• /
• pp.451-454
• /
• 2014

Short-term load forecasting(STLF) for electric power demand is essential for stable power system operation and efficient power market operation. We improved STLF method by using hourly temperature as an input data. In order to using hourly temperature to STLF algorithm, we calculated temperature-electric power demand sensitivity through past actual data and combined this sensitivity to exponential smoothing method which is one of the STLF method. The proposed method is verified by case study for a week. The result of case study shows that the average percentage errors of the proposed load forecasting method are improved comparing with errors of the previous methods.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권3호
• /
• pp.163-172
• /
• 2016

Electric load forecasting is essential for effective power system planning and operation. Complex and nonlinear relationships exist between the electric loads and their exogenous factors. In addition, time-series load data has non-stationary characteristics, such as trend, seasonality and anomalous day effects, making it difficult to predict the future loads. This paper proposes a locally-weighted polynomial neural network (LWPNN), which is a combination of a polynomial neural network (PNN) and locally-weighted regression (LWR) for daily shortterm peak load forecasting. Model over-fitting problems can be prevented effectively because PNN has an automatic structure identification mechanism for nonlinear system modeling. LWR applied to optimize the regression coefficients of LWPNN only uses the locally-weighted learning data points located in the neighborhood of the current query point instead of using all data points. LWPNN is very effective and suitable for predicting an electric load series with nonlinear and non-stationary characteristics. To confirm the effectiveness, the proposed LWPNN, standard PNN, support vector regression and artificial neural network are applied to a real world daily peak load dataset in Korea. The proposed LWPNN shows significantly good prediction accuracy compared to the other methods.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.1386-1388
• /
• 1996

In this paper, a recurrent neural network using polynomial is proposed for electric load forecasting. Since the proposed algorithm is based on the bilinear polynomial, it can model nonlinear systems with much more parsimony than the higher order neural networks based on the Volterra series. The proposed Bilinear Recurrent Neural Network(BLRNN) is compared with Multilayer Perceptron Type Neural Network(MLPNN) for electric load forecasting problems. The results show that the BLRNN is robust and outperforms the MLPNN in terms of forecasting accuracy.

• 대한산업공학회지
• /
• 제28권1호
• /
• pp.63-75
• /
• 2002

To improve the efficiency of the electric power generation, monthly maximum electric power consumptions for a next one year should be forecasted in advance and used as the fundamental input to the yearly electric power-generating master plan, which has a greatly influence upon relevant sub-plans successively. In this paper, we analyze the past 22-year hourly maximum electric load data available from KEPCO(Korea Electric Power Corporation) and select necessary data from the raw data for our model in order to reflect more recent trends and seasonal components, which hopefully result in a better forecasting model in terms of forecasted errors. After analyzing the selected data, we recommend to KEPCO the Winters' multiplicative model with decomposition and exponential smoothing technique among many candidate forecasting models and provide forecasts for the electric power consumptions and their 95% confidence intervals up to December of 1999. It turns out that the relative errors of our forecasts over the twelve actual load data are ranged between 0.1% and 6.6% and that the average relative error is only 3.3%. These results indicate that our model, which was accepted as the first statistical forecasting model for monthly maximum power consumption, is very suitable to KEPCO.

• 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% ...