• 산업기술연구
• /
• 제15권
• /
• pp.187-193
• /
• 1995

In this paper, a short-term load forecasting expert system considering the load variation due to the change in temperature is presented. The change in temperature is an important load variation factor that varies the normal load pattern. The conventional load forecasting methods by artificial neural networks have used the technique where the temperature variables were included in the input neurons of artificial neural networks. However, simply adding the input units of temperature data may make the forecasting accuracy worse, since the accuracy of the load forecasting in this method depends on the accuracy of weather forecasting. In this paper, the fuzzy expert system that modifies the forecasted load using fuzzy rules representing the relations of load and temperature is presented and compared with a conventional load forecasting technique. In the test case of 1991, the proposed model provided a more accurate forecast than the conventional technique.

• 산업공학
• /
• 제25권3호
• /
• pp.309-318
• /
• 2012

Forecasting probability or likelihood of technology development success has been a crucial factor for critical decisions in technology management such as R&D project selection and go or no-go decision of new product development (NPD) projects. This paper proposes an analytic network process (ANP) approach to forecasting of technology development success. Reviewing literature on factors affecting technology development success has constructed the ANP model composed of four criteria clusters : R&D characteristics, R&D competency, technological characteristics, and technological environment. An alternative cluster comprised of two elements, success and failure is also included in the model. The working of the proposed approach is provided with the help of a case study example of MRAM (magnetic random access memory) technology.

• 기술혁신연구
• /
• 제15권2호
• /
• pp.83-102
• /
• 2007

This study extends the existing method of Technology Forecasting with Data Envelopment Analysis (TFDEA) by incorporating a ranking method into the model so that we can reduce the required number of DMUs (Decision Making Units). TFDEA estimates technological rate of change with the set of observations identified by DEA(Data Envelopment Analysis) model. It uses an excessive number of efficient DMUs(Decision Making Units), when the number of inputs and outputs is large compare to the number of observations. Hence, we investigated the possibility of incorporating CCCA(Constrained Canonical Correlation Analysis) into TFDEA so that the ranking of DMUs can be made. Using the ranks developed by CCCA(Constrained Canonical Correlation Analysis), we could limit the number of efficient DMUs that are to be used in the technology forecasting process. The proposed hybrid model could establish technology frontiers with the efficient DMUs for each generation of technology with the help of CCCA that uses the common weights. We applied our hybrid model to forecast the technological progress of main battle tank in order to demonstrate its forecasting capability with practical application. It was found that our hybrid model generated statistically more reliable forecasting results than both TFDEA and the regression model.

• 기술혁신학회지
• /
• 제1권2호
• /
• pp.275-284
• /
• 1998

This paper investigates the responding patterns between panelists of high and low expertise, overall consistency in responses and the reliability of a technology forecasting outcomes of the study $\ulcorner$The Industrial Technology Forecasting for 2010 and New Strategies$\lrcorner$. The conclusions, based on various tests, are as follows : panelists' responses are tested to be significantly consistent : the panelist group of high expertise are more confident on their responses than the one of low expertise and the convergence ratio is higher in the latter group than in the first.

• International Journal of Advanced Culture Technology
• /
• 제11권4호
• /
• pp.393-405
• /
• 2023

Accurate prediction of wind speed and power is vital for enhancing the efficiency of wind energy systems. Numerous solutions have been implemented to date, demonstrating their potential to improve forecasting. Among these, deep learning is perceived as a revolutionary approach in the field. However, despite their effectiveness, the noise present in the collected data remains a significant challenge. This noise has the potential to diminish the performance of these algorithms, leading to inaccurate predictions. In response to this, this study explores a novel feature engineering approach. This approach involves altering the data input shape in both Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) and Autoregressive models for various forecasting horizons. The results reveal substantial enhancements in model resilience against noise resulting from step increases in data. The approach could achieve an impressive 83% accuracy in predicting unseen data up to the 24th steps. Furthermore, this method consistently provides high accuracy for short, mid, and long-term forecasts, outperforming the performance of individual models. These findings pave the way for further research on noise reduction strategies at different forecasting horizons through shape-wise feature engineering.

• 한국안전학회지
• /
• 제32권3호
• /
• pp.83-89
• /
• 2017

A new technology has provided the nation, industry, society, and people with innovative and useful functions. National economy and society has been improved through this technology innovation. Despite the benefit of technology innovation, however, since technology society was sufficiently mature, the unintended side effect and negative impact of new technology on society and human beings has been highlighted. Thus, it is important to investigate a risk of new technology for the future society. Recently, the risks of the new technology are being suggested through a large amount of social data such as news articles and report contents. These data can be used as effective sources for quantitatively and systematically forecasting social risks of new technology. In this respect, this paper aims to propose a data-driven process for forecasting and assessing social risks of future new technology using the text mining, 4M(Man, Machine, Media, and Management) framework, and analytic hierarchy process (AHP). First, social risk factors are forecasted based on social risk keywords extracted by the text mining of documents containing social risk information of new technology. Second, the social risk keywords are classified into the 4M causes to identify the degree of risk causes. Finally, the AHP is applied to assess impact of social risk factors and 4M causes based on social risk keywords. The proposed approach is helpful for technology engineers, safety managers, and policy makers to consider social risks of new technology and their impact.

• 대한임베디드공학회논문지
• /
• 제9권3호
• /
• pp.137-143
• /
• 2014

Demand Controller is a load control device that monitor the current power consumption and calculate the forecast power to not exceed the power set by consumer. Accurate demand forecasting is important because of controlling the load use the way that sound a warning and then blocking the load when if forecasted demand exceed the power set by consumer. When if consumer with fluctuating power consumption use the existing forecasting method, management of demand control has the disadvantage of not stable. In this paper, load forecasting of the unit of seconds using the Exponential Smoothing Methods, ARIMA model, Kalman Filter is proposed. Also simulation of load forecasting of the unit of the seconds methods and existing forecasting methods is performed and analyzed the accuracy. As a result of simulation, the accuracy of load forecasting methods in seconds is higher.

• 한국지능시스템학회논문지
• /
• 제21권3호
• /
• pp.341-346
• /
• 2011

공백기술예측은 기술경영 분야에서 중요하게 다루어지는 주제이다. 다양한 분야에서 현재까지의 기술개발결과를 분석하여 상대적으로 연구개발이 이루어지지 못한 분야를 찾아내어 개발하는 것은 국가와 기업의 발전에 중요한 영향을 미친다. 현재 특허는 기술개발결과에 대한 가장 객관적인 데이터 중 하나이다. 본 논문에서는 특허데이터를 이용하여 공백기술을 정량적으로 예측할 수 있는 방법에 대하여 연구한다. 하나의 정량적 기술예측모형이 완벽하다는 보장을 할 수 없기 때문에 본 연구에서는 여러 가지 모형들의 결과를 결합하여 예측하는 앙상블모형을 제안한다. 통계적 분석기법과 기계학습 알고리즘을 결합하여 보다 객관적이고 정확한 공백기술예측모형을 구축한다. 제안방법의 객관적인 성능평가를 위하여 각 기술분야에 대하여 최초 특허가 이루어진 시점부터 최근까지 출원, 등록된 특허데이터를 이용한다.

• Journal of Electrical Engineering and Technology
• /
• 제5권3호
• /
• pp.363-370
• /
• 2010

Load forecasting has always been essential to the operation and planning of power systems in deregulated electricity markets. Various methods have been proposed for load forecasting, and the neural network is one of the most widely accepted and used techniques. However, to obtain more accurate results, more information is needed as input variables, resulting in huge computational costs in the learning process. In this paper, to reduce training time in multi-layer perceptron-based short-term load forecasting, a graphics processing unit (GPU)-based computing method is introduced. The proposed approach is tested using the Korea electricity market historical demand data set. Results show that GPU-based computing greatly reduces computational costs.

• 산업기술연구
• /
• 제18권
• /
• pp.379-384
• /
• 1998

Conventional short-term load forecasting techniques have limitation in their use on holidays due to dissimilar load behaviors of holidays and insufficiency of pattern data. Thus, a new short-term load forecasting method for special days in anomalous load conditions is proposed in this paper. The proposed method uses two Artificial Neural Networks(ANN); one is for the estimation of load curve, and the other is for the estimation of minimum and maximum value of load. The forecasting procedure is as follows. First, the normalized load curve is estimated by ANN. At next step, minimum and maximum values of load in a special day are estimated by another ANN. Finally, the estimate of load in a whole special day is obtained by combining these two outputs of ANNs. The proposed method shows a good performance, and it may be effectively applied to the practical situations.