• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.18 no.5
• /
• pp.105-111
• /
• 2004

This paper shows that active and reactive power load have significant positive relationship and there exist two types of relationship between them using Test Statistics. In investigating the cross plots at every hour, we found out that from 0 to 8 hours, there relationships are linear, while from 9 to 23 hours, they are two piece-wise linear. Also, reactive power loads was estimated and forecasted using active power load as the explanary variable with OLS (Ordinary Least Squares) regression methods. MAPE (Mean Absolute Percentage Error) for each model is calculated for one-hour ahead forecasting.

• The Journal of the Korea Contents Association
• /
• v.16 no.11
• /
• pp.488-498
• /
• 2016

Much of the information is stored as data, research has been activated for analyzing the data and predicting the special circumstances. In the case of power data, the studies, such as research of renewable energy utilization, power prediction depending on site characteristics, smart grid, and micro-grid, is actively in progress. In this paper, we propose a power prediction model using the substation environment data. In this case, we try to verify the power prediction result to reflect the multiple arguments on the power and weather data, rather than a simple power data. The validation process is the effect of multiple factors compared to other two methods, one of power prediction result considering power data and the other result using power pattern data that have been made in the similar weather data. Our system shows that it can achieve max prediction error of less than 15%.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.7
• /
• pp.1749-1758
• /
• 1997

This paper suggests the development of dynamic forecasting model for short-term power demand based on Radial Basis Function Network and Pal's GLVQ algorithm. Radial Basis Function methods are often compared with the backpropagation training, feed-forward network, which is the most widely used neural network paradigm. The Radial Basis Function Network is a single hidden layer feed-forward neural network. Each node of the hidden layer has a parameter vector called center. This center is determined by clustering algorithm. Theatments of classical approached to clustering methods include theories by Hartigan(K-means algorithm), Kohonen(Self Organized Feature Maps %3A SOFM and Learning Vector Quantization %3A LVQ model), Carpenter and Grossberg(ART-2 model). In this model, the first approach organizes the load pattern into two clusters by Pal's GLVQ clustering algorithm. The reason of using GLVQ algorithm in this model is that GLVQ algorithm can classify the patterns better than other algorithms. And the second approach forecasts hourly load patterns by radial basis function network which has been constructed two hidden nodes. These nodes are determined from the cluster centers of the GLVQ in first step. This model was applied to forecast the hourly loads on Mar. $4^{th},\;Jun.\;4^{th},\;Jul.\;4^{th},\;Sep.\;4^{th},\;Nov.\;4^{th},$ 1995, after having trained the data for the days from Mar. $1^{th}\;to\;3^{th},\;from\;Jun.\;1^{th}\;to\;3^{th},\;from\;Jul.\;1^{th}\;to\;3^{th},\;from\;Sep.\;1^{th}\;to\;3^{th},\;and\;from\;Nov.\;1^{th}\;to\;3^{th},$ 1995, respectively. In the experiments, the average absolute errors of one-hour ahead forecasts on utility actual data are shown to be 1.3795%.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.3
• /
• pp.51-65
• /
• 2024

Accurate electrical load forecasting is important to the effective operation of power systems in smart grids. With the recent development in machine learning, artificial intelligence-based models for predicting power demand are being actively researched. However, since existing models get input variables as numerical features, the accuracy of the forecasting model may decrease because they do not reflect the semantic relationship between these features. In this paper, we propose a scheme for short-term load forecasting by using features extracted through the large language models for input data. We firstly convert input variables into a sentence-like prompt format. Then, we use the large language model with frozen weights to derive the embedding vectors that represent the features of the prompt. These vectors are used to train the forecasting model. Experimental results show that the proposed scheme outperformed models based on numerical data, and by visualizing the attention weights in the large language models on the prompts, we identified the information that significantly influences predictions.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.69-70
• /
• 2011

평일의 전력수요는 연속적인 시계열 특성이 뚜렷하여 전력수요예측 오차가 크지 않으나 특수일의 경우는 불연속적인 시계열특성을 가지게 되어 전력수요예측 오차율이 크다. 특히, 연휴의 직전 평일은 평일의 특성과 특수일의 특성이 혼재하고 있어 오차율이 가장 큰 일자 중 하나이다. 따라서 본 논문에서는 연휴 직전 평일과 직전 일요일과의 부하 변동비를 계산하여 전력수요를 예측하는 방법을 제안하고, 추석연휴 직전 평일에 제안한 방법을 적용하여 최대수요예측 오차가 개선됨을 확인하였다.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.608-609
• /
• 2011

전력수요 예측 오차가 큰 추석 연휴 및 전, 후일 전력수요 예측의 정확성을 향상시키기 위해 과거 추석 연휴 및 전, 후일에 대한 전력수요 특성을 분석하고 최대/최소 전력 예측을 위한 퍼지 입력데이터 선정 방법과 24시간 예측을 위한 정규화에 필요한 입력 데이터 선정방법을 개발하여 퍼지 선형회귀분석 모델을 사용하여 2006년에서 2010년까지 5개년의 사례연구를 통해 알고리즘의 우수성을 검증하였다.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.21 no.10
• /
• pp.126-133
• /
• 2007

This paper proposes information technology based data mining to forecast short term power demand. A time-series analyses have been applied to power demand forecasting, but this method needs not only heavy computational calculation but also large amount of coefficient data. Therefore, it is hard to analyze data in fast way. To overcome time consuming process, the author take advantage of universally easily available information technology based data-mining technique to analyze patterns of days and special days(holidays, etc.). This technique consists of two steps, one is constructing decision tree, the other is estimating and forecasting power flow using decision tree analysis. To validate the efficiency, the author compares the estimated demand with real demand from the Korea Power Exchange.

• Journal of Korea Spatial Information System Society
• /
• v.11 no.2
• /
• pp.177-181
• /
• 2009

Developing u-Public facilities for application u-City is to combine both the state-of-the art of the construction and ubiquitous computing and must be flexibly comprised of the facilities for the basic service of the building such as air conditioning, heating, lighting and electric equipments to materialize a new format of spatial planning and the public facilities inside or outside. Accordingly, in this paper we suggested the time pattern system for predicting the most basic power system loads for the basic service. To application the tim e pattern we applied SOM algorithm and k-means method and then clustered the data each weekday and each time respectively. The performance evaluation results of suggestion system showed that the forecasting system better the ARIMA model than the exponential smoothing method. It has been assumed that the plan for power supply depending on demand and system operation could be performed efficiently by means of using such power load forecasting.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.294-295
• /
• 2011

전력수급계획은 소비자의 전력 사용량을 예측하고 적정한 공급능력을 확보하는 것이 목적인데, 수요예측 정확도를 향상시키고 전력설비를 적기에 준공시킬수록 적정공급능력 확보가 용이하다. 그러나 최근 전력수요는 계절적, 시간대별로 경향이 과거와는 상이하게 나타나고 있는데 이로 인해 발전기를 예방 정비할 수 있는 기간이 짧아지고 있다. 한편 향후 몇 년간은 준공되는 발전기가 적어 중/단기 수급계획이 더욱 어려울 전망이다. 따라서 최근 수요추세를 고려하여 수요예측 정확도를 향상시키고 현재보다 탄력적인 부하감축제도 시행이 요구된다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.157-158
• /
• 2019

발전소 관리의 단기 전력 수요에 대한 정확한 예측은 전력 시스템의 안전하고 효율적인 작동을 보장하는데 필수적이다. 따라서 본 연구는 가우스 커널 함수 네트워크 (GKFNs)의 심층 구조를 이용하여 일일 최대 전력 수요를 예측하는 새로운 방법을 제시한다. 제안 된 GKFN의 깊이 구조는 표준 GKFN에 비해 예측 정확도를 향상시킨다. 한국의 일일 최대 전력 수요를 예측하기위한 시뮬레이션은 제안 된 예측 모델이 GKFN 모델, k-NN 및 SVR과 같은 다른 예측 모델에 비해 예측 성능에 이점이 있음을 보여준다. GKFN의 제안된 심층 구조는 시계열 예측 및 회귀 문제의 다양한 문제에 적용될 수 있다.