• 전기학회논문지
• /
• 제67권10호
• /
• pp.1257-1264
• /
• 2018

This paper proposes Autoregressive Integrated Moving Average (ARIMA)-based forecasting algorithms using meteorological indices to predict seasonal peak load. First of all, this paper observes a seasonal pattern of the peak load that appears intensively in winter and summer, and generates ARIMA models to predict the peak load of summer and winter. In addition, this paper also proposes hybrid ARIMA-based models (ARIMA-Hybrid) using a discomfort index and a sensible temperature to enhance the conventional ARIMA model. To verify the proposed algorithm, both ARIMA and ARIMA-Hybrid models are developed based on peak load data obtained from 2006 to 2015 and their forecasting results are compared by using the peak load in 2016. The simulation result indicates that the proposed ARIMA-Hybrid models shows the relatively improved performance than the conventional ARIMA model.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2011년도 제42회 하계학술대회
• /
• pp.199-200
• /
• 2011

Load forecasting is very important for power system analysis and planning. This paper suggests yearly load forecasting of considering weekly normalization and seasonal load characteristics. Each weekly peak load is normalized and the average value is calculated. The new hourly peak load is seasonally collected. This method was used for yearly load forecasting. The results of the actual data and forecast data were calculated error rate by comparing.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 A
• /
• pp.304-306
• /
• 2000

Load modeling, micro method, needs field test to identify the validity of methodology applied to modeling. This paper presents seasonal field test method and measurement results on serveral substations. Seasonal load characteristics were analyzed by the developed substation load model and correlation coefficients of seasonal load of substation under base, peak and average load time.

• 응용통계연구
• /
• 제32권1호
• /
• pp.161-171
• /
• 2019

일별 최대전력 수요 예측은 국가의 전력 수급운영에 중요한 과제로서 과거부터 다양한 방법들이 끊임없이 연구되어 왔다. 일별 최대전력 수요를 정확히 예측함으로써 발전설비에 대한 일일 운용계획을 작성하고 효율적인 설비 운용을 통해 불필요한 에너지 자원의 소비를 감소하는데 기여할 수 있으며 여름 겨울철 냉난방수요로 인해 발생하는 전력소비 과다로 인한 전력예비율 감소 문제 등에 선제적으로 대비할 수 있는 장점을 가진다. 이러한 일별 최대전력수요 예측을 위하여 본 논문에서는 Seasonal ARIMA, TBATS, Seasonal Reg-ARIMA, NNETAR 모형에 평일, 주말, 특수일에 대한 효과와 온도에 대한 영향을 함께 고려하여 다음날의 일별 최대전력을 예측하는 모형을 연구하였다. 본 논문을 통한 모형들의 예측 성능 평가 결과 요일, 온도를 고려할 수 있는 Seasonal Reg-ARIMA 모형과 NNETAR 모형이 이를 고려할 수 없는 다른 시계열 모형보다 우수한 예측 성능을 나타내었고 그 중 인공신경망을 활용한 NNETAR 모형의 예측 성능이 가장 우수하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 하계학술대회 논문집 D
• /
• pp.2446-2448
• /
• 2001

In addition to the stabilization of electricity supply and the quality management of electricity, load balance has been an important strategy for achieving high quality load management. Among many techniques for load management, direct load management has been actively studied and applied for increasing the efficiency of power facility and suppressing peak load. In Korea, the highest peak load is demanded in summer rather than in winter, and almost 50% of the peak load comes from cooling load. Currently, applicable systems are limited to air conditioners that have the cooling capacity less than 2kW. This paper describes the development of remote controlled air conditioners and the result of the field test of the new type air conditioner. The technical specification based on the test will be applied to the new model of the remote controlled air conditioner. The wide distribution of the air conditioners to the public will be helpful to control peak demand due to cooling load in summer time. Financial investment to generating, transmission, distribution facilities will be decreased from flatting the seasonal power load.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1985년도 하계학술회의논문집
• /
• pp.144-147
• /
• 1985

In electricity industry, the improvement of load factor by flattening of load has been considered to be more important than any other tasks and has received wide concern and interest. Especially while annual peak load had occured early evening in winter during past decades, but we found the trend has changed so that annual peak load occured during the daytime in summer since1981 The useful practicing methods of this load management ale as follows; 1. Inducing of midnight load by thermal storage water heating 2. Seasonal differential rates. 3. Revising the peak load priceing (Time-of -use) It seems hard to expect that load research can be carried out in a short time, and we all have to exert outselves continuously to provide efficient load management method without wasting resources.

• 응용통계연구
• /
• 제26권2호
• /
• pp.349-360
• /
• 2013

최근 일별 최대 전력수요 예측은 전력설비 계획 및 운용에 매우 중요한 사안으로 주목받고 있다. 본 연구는 일별 최대 전력수요 예측을 위하여 대표적 시계열 모형을 소개하고, 예측의 성능 비교를 위하여 RMSE(Root mean squared error)와 MAPE(Mean absolute percentage error)를 사용한다. 연구결과로 보완된 Holt-Winters 모형과 Reg-ARIMA 모형이 다른 모형에 비하여 우수한 예측 성능을 보였다.

• 산업공학
• /
• 제16권1호
• /
• pp.16-26
• /
• 2003

In Korea, cooling power load, which occupies about 20% of peak load in 2000 and fluctuates depending on the popular usage of air conditioning systems, has been recently the focus of the load management. The first work of KEPCO (Korea Electric Power Corporation) to regulate cooling load as low as possible was to estimate its approximate scale and to develop the indirect methods to estimate it from the available time series data for the average hourly loads. However, KEPCO would like to have their methods improved both theoretically and practically. In this paper, we analyze their current indirect methods and detect their faults to design better indirect estimation methods. Under one of the assumptions of "no cooling load in April or May", the linear relationship between basic loads and GDP's, and the normalized seasonal factors of the Winters' multiplicative seasonal model, we provide ten indirect estimation methods in total and suggest the estimated cooling load(1988-1999) based on our various indirect methods.

• 전기학회논문지
• /
• 제60권12호
• /
• pp.2202-2205
• /
• 2011

Demand side management is used to maintain the reliability of power systems and to increase the economic benefits by avoiding power plant construction. This paper presents a systematic method to calculate the quantity of seasonal demand side management using time series. A numerical example is presented to calculate the quantity of demand side management in winter season using time series.

• 한국지능시스템학회논문지
• /
• 제24권2호
• /
• pp.141-146
• /
• 2014

본 논문은 Peak Shaving 알고리즘의 성능 향상을 위한 예측 부하 곡선의 생성의 한 방법을 제시한다. 여기서 논하는 Peak Shaving 알고리즘은 대용량의 배터리 에너지 저장시스템 (BESS, Battery Energy Storage System)을 위한 PMS (Power Management System)의 장주기 스케쥴링 알고리즘을 의미한다. 위의 PMS는 주로 배터리에서 에너지의 입출력을 제어하는 데에 주목적이 있다. 이를 위해서 Peak Shaving 알고리즘이 사용되는데, 여기서 예측 부하곡선과 실제 부하곡선 사이의 불확실성이 나타난다. 원활한 에너지의 충,방전을 위하여 본 논문에서는 주 단위의 표준화 방법과 계절별 부하의 특성을 고려한 예측 부하 곡선 생성 방법을 제안한다.