• 한국산업융합학회 논문집
• /
• 제26권4_2호
• /
• pp.657-668
• /
• 2023

It's important to note that air compressors in the industrial sector are major energy consumers, accounting for a significant portion of total energy costs in manufacturing plants, ranging from 12% to 40%. To address this issue, researchers have compared forecasting models that can predict the power consumption of air compressors. The forecasting models were designed to incorporate variables such as flow rate, pressure, temperature, humidity, and dew point, utilizing statistical methods, machine learning, and deep learning techniques. The model performance was compared using measures such as RMSE, MAE and SMAPE. Out of the 21 models tested, the Elastic Net, a statistical method, proved to be the most effective in power comsumption forecasting.

• International Journal of Computer Science & Network Security
• /
• 제24권3호
• /
• pp.196-200
• /
• 2024

Weather forecasting is considered to be of utmost important among various important sectors such as flood management and hydro-electricity generation. Although there are various numerical methods for weather forecasting but majority of them are reported to be Mechanistic computationally demanding due to their complexities. Therefore, it is necessary to develop and build models for accurately predicting the weather conditions which are faster as well as efficient in comparison to the prevalent meteorological models. The study has been undertaken to forecast various atmospheric parameters in the city of Bangalore using Naïve Bayes algorithms. The individual parameters analyzed in the study consisted of wind speed (WS), wind direction (WD), relative humidity (RH), solar radiation (SR), black carbon (BC), radiative forcing (RF), air temperature (AT), bar pressure (BP), PM₁₀ and PM_2.5 of the Bangalore city collected from Air Quality Monitoring Station for a period of 5 years from January 2015 to May 2019. The study concluded that Naive Bayes is an easy and efficient classifier that is centered on Bayes theorem, is quite efficient in forecasting the various air pollution parameters of the city of Bangalore.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권1호
• /
• pp.1-14
• /
• 2024

Time-series forecasting is extensively used in the actual world. Recent research has shown that Transformers with a self-attention mechanism at their core exhibit better performance when dealing with such problems. However, most of the existing Transformer models used for time series prediction use the traditional encoder-decoder architecture, which is complex and leads to low model processing efficiency, thus limiting the ability to mine deep time dependencies by increasing model depth. Secondly, the secondary computational complexity of the self-attention mechanism also increases computational overhead and reduces processing efficiency. To address these issues, the paper designs an efficient multi-layer attention-based time-series forecasting model. This model has the following characteristics: (i) It abandons the traditional encoder-decoder based Transformer architecture and constructs a time series prediction model based on multi-layer attention mechanism, improving the model's ability to mine deep time dependencies. (ii) A cross attention module based on cross attention mechanism was designed to enhance information exchange between historical and predictive sequences. (iii) Applying a recently proposed sparse attention mechanism to our model reduces computational overhead and improves processing efficiency. Experiments on multiple datasets have shown that our model can significantly increase the performance of current advanced Transformer methods in time series forecasting, including LogTrans, Reformer, and Informer.

• Wind and Structures
• /
• 제38권6호
• /
• pp.461-475
• /
• 2024

A reliable wind speed forecasting method is crucial for the applications in wind engineering. In this study, the generalized S-transform (GST) is innovatively applied for wind speed forecasting to uncover the time-frequency characteristics in the non-stationary wind speed data. The improved grey wolf optimizer (IGWO) is employed to optimize the adjustable parameters of GST to obtain the best time-frequency resolution. Then a hybrid method based on IGWO-optimized GST is proposed to validate the effectiveness and superiority for multi-step non-stationary wind speed forecasting. The historical wind speed is chosen as the first input feature, while the dynamic time-frequency characteristics obtained by IGWO-optimized GST are chosen as the second input feature. Comparative experiment with six competitors is conducted to demonstrate the best performance of the proposed method in terms of prediction accuracy and stability. The superiority of the GST compared to other time-frequency analysis methods is also discussed by another experiment. It can be concluded that the introduction of IGWO-optimized GST can deeply exploit the time-frequency characteristics and effectively improving the prediction accuracy.

• 대한교통학회지
• /
• 제26권5호
• /
• pp.131-141
• /
• 2008

고속도로에서의 지점검지체계로부터 수집 가공 처리된 과거 통행시간 이력자료를 이용한 통행시간 예측시, 사용되는 대표값과 과거 데이터량에 따라 예측의 정확성이 결정되나 이에 대한 체계적인 연구가 없는 실정이다. 따라서 본 연구의 목적은 신뢰성 있는 통행시간 예측을 위해 통행시간 이력자료의 적정 대표간과 과거 데이터량을 결정하기 위한 방법론을 제시하였다. 과거 통행시간 이력자료의 적정 대표값은 예측오차의 평균이 가장 적은 대표값을 선정할 수 있으며, 적정 과거 데이터량은 비슷한 속성을 가진 과거 통행시간 이력자료의 개별간의 차이 또는 집단 간의 차이를 최소화하는 CVMSE(Cross Validated Mean Square Error)방법을 이용하여 결정할 수 있다. 한국도로공사의 고속도로 지점검지기 자료에 적용한 결과, 적절 대표값은 중앙값으로 분석되었으며, 통행시간 예측을 위한 적정 과거 데이터량은 60일로 분석되었다.

• 시스템엔지니어링학술지
• /
• 제16권1호
• /
• pp.84-97
• /
• 2020

This paper aims to develop an optimized inventory management method for safety critical Instrument and Control (I&C) components. In this regard, the paper focuses on estimating the consumption rate of I&C components using demand forecasting methods. The target component for this paper is the Foxboro SPEC-200 controller. This component was chosen because it has highest consumption rate among the safety critical I&C components in Korean OPR-1000 NPPs. Three analytical methods were chosen in order to develop the demand forecasting methods; Poisson, Generalized Linear Model (GLM) and Bootstrapping. The results show that the GLM gives better accuracy than the other analytical methods. This is because the GLM considers the maintenance level of the component by discriminating between corrective and preventive.

• 지능정보연구
• /
• 제4권1호
• /
• pp.133-147
• /
• 1998

Recently, many researchers have been involved in finding deterministic equations which can accurately predict future event, based on chaotic theory, or fractal theory. The theory says that some events which seem very random but internally deterministic can be accurately predicted by fractal equations. In contrast to the conventional methods, such as AR model, MA, model, or ARIMA model, the fractal equation attempts to discover a deterministic order inherent in time series data set. In discovering deterministic order, researchers have found that neural networks are much more effective than the conventional statistical models. Even though prediction accuracy of the network can be different depending on the topological structure and modification of the algorithms, many researchers asserted that the neural network systems outperforms other systems, because of non-linear behaviour of the network models, mechanisms of massive parallel processing, generalization capability based on adaptive learning. However, recent survey shows that prediction accuracy of the forecasting models can be determined by the model structure and data structures. In the experiments based on actual economic data sets, it was found that the prediction accuracy of the neural network model is similar to the performance level of the conventional forecasting model. Especially, for the data set which is deterministically chaotic, the AR model, a conventional statistical model, was not significantly different from the MLP model, a neural network model. This result shows that the forecasting model. This result shows that the forecasting model a, pp.opriate to a prediction task should be selected based on characteristics of the time series data set. Analysis of the characteristics of the data set was performed by fractal analysis, measurement of Hurst index, and measurement of Lyapunov exponents. As a conclusion, a significant difference was not found in forecasting future events for the time series data which is deterministically chaotic, between a conventional forecasting model and a typical neural network model.

• 조명전기설비학회논문지
• /
• 제19권5호
• /
• pp.94-102
• /
• 2005

본 논문은 전력계통에서의 전력수요예측을 하기 위한 네가지중 하나의 방법으로 특수일에 적용기법인 수요예측 담당자의 Know-How를 기반으로 예측하는 전문가법에 대하여 과거 15년간의 수요실적과 기상실적을 근거로 년중 모든 특수일에 대해서 수요패턴 분석을 실시하고 패턴의 변화되는 과정을 살펴보았다. 과거 전력수요 실적의 근거로 산출된 시간대별 상대계수의 수요패턴을 가지고 모의 운영한 결과 설 연휴 수요예측 오차율은 과거 5일간(2002, 2003년도)의 평균값 $3.23{[\%]}$에서 2005년도 설 연휴 실적대비 $1.78{[\%]}$로 상당한 개선효과가 있었다. 본 논문의 내용을 바탕으로 전력수요 예측 편람을 작성하는 것도 입문교재로서 수요예측 전문가 양성에 큰 도움을 줄 수 있을 것으로 기대된다.

• 한국품질경영학회:학술대회논문집
• /
• 한국품질경영학회 2010년도 춘계학술대회
• /
• pp.402-408
• /
• 2010

Forecasting have qualitative and quantitative methods. Quantitative one analyze macro-economic factors such as the rate of exchange, oil price, interest rate and also predict the micro-economic factors such as sales and demands. Applying various statistical methods depends on the type of data. when data has seasonality and trend, Time Series analysis is proper but when it has casual relation, Regression analysis is good for this. Time Series and Regression can be used together. This study investigate artificial neural networks which is predictive technique for casual relation and try to compare the accuracy of forecasting between regression analysis and artificial neural network.

• 한국대기환경학회:학술대회논문집
• /
• 한국대기환경학회 2005년도 추계학술대회 논문집
• /
• pp.289-291
• /
• 2005