• Industrial Engineering and Management Systems
• /
• 제14권3호
• /
• pp.318-324
• /
• 2015

This paper proposes a dynamic short-term load forecasting method that utilizes a new sequential learning algorithm based on Relevance Vector Machine (RVM). The method performs general optimization of weights and hyperparameters using the current relevance vectors and newly arriving data. By doing so, the proposed algorithm is trained with the most recent data. Consequently, it extends the RVM algorithm to real-time and nonstationary learning processes. The results of application of the proposed algorithm to prediction of electrical loads indicate that its accuracy is comparable to that of existing nonparametric learning algorithms. Further, the proposed model reduces computational complexity.

• 융합신호처리학회논문지
• /
• 제2권3호
• /
• pp.73-78
• /
• 2001

특수일 부하를 예측하기 위하여 BP 신경회로망 모형과 다중 회귀모형을 구성한다. 신경회로망 모형은 패턴 변환비를 이용하고, 다중회귀 모형은 평일 환산비를 이용하여 특수일 부하를 예측한다. 주간 피크 부하예측 모형에 패턴 변환비를 이용하여 짧고 긴 특수일 부하를 예측 한 결과 주간 평균 오차율이 1∼2[%]로 나와 본 기법의 적합성을 확인할 수 있다. 하지만, 패턴 변환비 방법으로는 하계의 특수일 부하 예측은 어려웠다. 따라서 기온-습도, 불쾌지수 등을 설명변수로 하는 다중 회귀 모형을 구성하고 평일 환산비를 이용하여 하계의 특수일 부하를 예측한다. 평일만의 예측 모형과 예측 결과를 비교해 보면 월 평균 오차율이 비슷하게 나와 이용한 방법의 적합성을 확인하였다. 그리고, 통계적 검정을 통해 구성한 예측 모형의 유효성을 입증할 수 있었다. 이로서 본 연구에서 제시한 특수일 부하를 예측하는 기법의 적합성을 확인함으로서 피크 부하 예측시 큰 난점 중의 하나가 해결되었다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제51권10호
• /
• pp.453-459
• /
• 2002

This paper proposes an improved algorithm of the daily peak load forecasting for Korean Thanksgiving Day and the Lunar New Year's day. So far, many studies on the short-term load forecasting have been made to improve the accuracy of the load forecasting. However, the large errors of the load forecasting occur i case of Korean Thanksgiving Day and the Lunar New Year's Day. In order to reduce the errors of the load forecasting, the fuzzy linear regression method is introduced and a good selection method of the past load pattern is presented. Test results show that the proposed algorithm improves the accuracy of the load forecasting.

• 한국산업정보학회논문지
• /
• 제29권3호
• /
• pp.51-65
• /
• 2024

스마트 그리드에서 전력 시스템을 효과적으로 운영하기 위해서는 전력 수요량을 정확히 예측하는 것이 중요하다. 최근 기계학습 기술의 발달로, 인공지능 기반의 전력 수요량 예측 모델이 활발히 연구되고 있다. 하지만, 기존 모델들은 모든 입력변수를 수치화하여 입력하기 때문에, 이러한 수치들 사이의 의미론적 관계를 반영하지 못해 예측 모델의 정확도가 하락할 수 있다. 본 논문은 입력 데이터에 대하여 거대언어모델을 통해 추출한 특징을 이용하여 단기 전력 수요량을 예측하는 기법을 제안한다. 먼저, 입력변수를 문장 형식의 프롬프트로 변환한다. 이후, 가중치가 동결된 거대언어모델을 이용하여 프롬프트에 대한 특징을 나타내는 임베딩 벡터를 도출하고, 이를 입력으로 받은 모델을 학습하여 예측을 수행한다. 실험 결과, 제안 기법은 수치형 데이터에 기반한 예측 모델에 비해 높은 성능을 보였고, 프롬프트에 대한 거대언어모델의 주의집중 가중치를 시각화함으로써 예측에 있어 주요한 영향을 미친 정보를 확인하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 A
• /
• pp.295-297
• /
• 2000

In case of power demand forecasting the most important problem is to deal with the load of special-days, Accordingly, this paper presents a method that forecasting special-days load with regression models and neural networks. Special-days load in summer season was forecasted by the multiple regression models using weekday change ratio Neural networks models uses pattern conversion ratio, and orthogonal polynomial models was directly forecasted using past special-days load data. forecasting result obtains % forecast error of about $1{\sim}2[%]$. Therefore, it is possible to forecast long and short special-days load.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 제36회 하계학술대회 논문집 A
• /
• pp.810-812
• /
• 2005

In this paper, the short-term load forecasting of pole-transformer is performed by artificial neural networks. Input parameters of the Nosed algorithm are peak loads of pole-transformer of previous days and their temperatures. The proposed algorithm is tested for ore of the pole-transformers in seoul, korea. Test results show that the proposed algorithm improves the accuracy of the load forecasting of pole-transformer compared with the conventional algorithm.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 추계학술대회 논문집 학회본부 A
• /
• pp.184-186
• /
• 2000

This paper proposes the introduction of TAR(Threshold Autoregressive) model for short-term load forecasting including temperature variable. TAR model is a piecewise linear autoregressive model. In the scatter diagram of daily peak load versus daily maximum or minimum temperature, we can find out that the load-temperature relationship has a negative slope in lower regime and a positive slope in upper regime due to the heating and cooling load, respectively. In this paper, daily peak load was forecasted by applying TAR model using this load-temperature characteristic in these regimes. The results are compared with those of linear and quadratic regression models.

• 한국인공지능학회지
• /
• 제12권1호
• /
• pp.17-24
• /
• 2024

This paper introduces a novel approach to time-series estimation for energy load forecasting within Virtual Power Plant (VPP) systems, leveraging advanced artificial intelligence (AI) algorithms, namely Long Short-Term Memory (LSTM) and Seasonal Autoregressive Integrated Moving Average (SARIMA). Virtual power plants, which integrate diverse microgrids managed by Energy Management Systems (EMS), require precise forecasting techniques to balance energy supply and demand efficiently. The paper introduces a hybrid-method forecasting model combining a parametric-based statistical technique and an AI algorithm. The LSTM algorithm is particularly employed to discern pattern correlations over fixed intervals, crucial for predicting accurate future energy loads. SARIMA is applied to generate time-series forecasts, accounting for non-stationary and seasonal variations. The forecasting model incorporates a broad spectrum of distributed energy resources, including renewable energy sources and conventional power plants. Data spanning a decade, sourced from the Korea Power Exchange (KPX) Electrical Power Statistical Information System (EPSIS), were utilized to validate the model. The proposed hybrid LSTM-SARIMA model with parameter sets (1, 1, 1, 12) and (2, 1, 1, 12) demonstrated a high fidelity to the actual observed data. Thus, it is concluded that the optimized system notably surpasses traditional forecasting methods, indicating that this model offers a viable solution for EMS to enhance short-term load forecasting.

• 전기의세계
• /
• 제31권5호
• /
• pp.368-374
• /
• 1982

This paper describes a combined algorithm for short-term-load forecating. One of the specific features of this algorithm is that the base, weather sensitive and residual components are predicted respectively. The base load is represented by the exponential smoothing approach and residual load is represented by the Box-Jenkins methodology. The weather sensitive load models are developed according to the information of temperature and discomfort index. This method was applied to Korea Electric Company and results for test periods up to three years are given.

• 전기학회논문지
• /
• 제61권12호
• /
• pp.1765-1773
• /
• 2012

The accuracy of load forecast is very important from the viewpoint of economical power system operation. In general, the weekdays' load demand pattern has the continuous time series characteristics. Therefore, the conventional methods expose stable performance for weekdays. In case of special days or weekends, the load demand pattern has the discontinuous time series characteristics, so forecasting error is relatively high. Especially, weekdays near the thanksgiving day and lunar new year's day have the mixed load profile characteristics of both weekdays and weekends. Therefore, it is difficult to forecast these days by using the existing algorithms. In this study, a new load forecasting method is proposed in order to enhance the accuracy of the forecast result considering the characteristics of weekdays and weekends. The proposed method was tested with these days during last decades, which shows that the suggested method considerably improves the accuracy of the load forecast results.