• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -1
• /
• pp.262-264
• /
• 2002

The characteristic features of Malaysia's climate is has stable temperature, with high humidity and copious rainfall. Weather forecasting is an important task in Malaysia as it could affetcs man irrespective of mans job, lifestyle and activities especially in the agriculture. In Malaysia, numerical method is the common used method to forecast weather which involves a complex of mathematical computing. The models used in forecasting are supplied by other counties such as Europe and Japan. The goal of this project is to forecast weather using another technology known as artificial neural network. This system is capable to learn the pattern of rainfall in order to produce a precise forecasting result. The supervised learning technique is used in the loaming process.

• 한국정보전자통신기술학회논문지
• /
• 제14권5호
• /
• pp.349-361
• /
• 2021

컴퓨터 기술의 발전과 기상예보 모델 및 예측방식의 고도화에 따라 더 고성능의 기상예측 소프트웨어가 개발되었으며 슈퍼컴퓨터를 활용한 소프트웨어 수행으로 더욱 정밀하고 정확한 기상예보가 가능하게 되었다. 본 논문에서는 주요 6개국이 사용하고 있는 기상예측 예보 모델을 조사하여 그 특징들을 분석하고 현재 한국 기상청에서 영국 기상청과 2012년부터 협업하여 사용하고 GloSea 소프트웨어에 대하여 설명한다. 그런데 기존의 GloSea는 기상청 슈퍼컴퓨터에서만 수행되어 다양한 연구자들의 전문 분야별 세분화된 연구에 어려움이 있었다. 따라서 본 논문에서는 현재 우리나라에서 사용하고 있는 GloSea6 기반의 저해상도 버전을 로컬시스템에 사용할 수 있는 표준 실험환경을 구축하고 이를 테스트해봄으로써 연구실 환경에서 수행 가능한 저해상도 GloSea6의 로컬화를 제시하고자 한다. 즉, 본 논문에서는 사용자 단말기-계산서버-리퍼지토리 서버로 구성되는 기본 아키텍처를 구축하고 해당 소프트웨어의 실행 테스트를 수행함으로써 저해상도 GloSea6의 로컬 이식성을 검증한다.

• 한국산업융합학회 논문집
• /
• 제26권4_2호
• /
• pp.715-724
• /
• 2023

Solar energy forecasting is essential for (1) power system planning, management, and operation, requiring accurate predictions. It is crucial for (2) ensuring a continuous and sustainable power supply to customers and (3) optimizing the operation and control of renewable energy systems and the electricity market. Recently, research has been focusing on developing solar energy forecasting models that can provide daily plans for power usage and production and be verified in the electricity market. In these prediction models, various data, including solar energy generation and climate data, are chosen to be utilized in the forecasting process. The most commonly used climate data (such as temperature, relative humidity, precipitation, solar radiation, and wind speed) significantly influence the fluctuations in solar energy generation based on weather conditions. Therefore, this paper proposes a hybrid forecasting model by combining the strengths of the Prophet model and the GRU model, which exhibits excellent predictive performance. The forecasting periods for solar energy generation are tested in short-term (2 days, 7 days) and medium-term (15 days, 30 days) scenarios. The experimental results demonstrate that the proposed approach outperforms the conventional Prophet model by more than twice in terms of Root Mean Square Error (RMSE) and surpasses the modified GRU model by more than 1.5 times, showcasing superior performance.

• 한국안전학회지
• /
• 제39권1호
• /
• pp.70-81
• /
• 2024

With heavy rainfall due to extreme weather causing increasing damage, the importance of urban flood forecasting continues to grow. To forecast urban flooding accurately and promptly, a sewer network and surface grid with appropriate detail are necessary. However, for urban areas with complex storm sewer networks and terrain structures, high-resolution grids and detailed networks can significantly prolong the analysis. Therefore, determining an appropriate level of network simplification and a suitable surface grid resolution is essential to secure the golden time for urban flood forecasting. In this study, InfoWorks ICM, a software program capable of 1D-2D coupled simulation, was used to examine urban flood forecasting performance for storm sewer networks with various levels of simplification and different surface grid resolutions. The inundation depth, inundation area, and simulation time were analyzed for each simplification level. Based on the analysis, the simulation time was reduced by up to 65% upon simplifying the storm sewer networks and by up to 96% depending on the surface grid resolution; further, the inundation area was overestimated as the grid resolution increased. This study provides insights into optimizing the simplification level and surface grid resolution for storm sewer networks to ensure efficient and accurate urban flood forecasting.

• 천문학회보
• /
• 제42권2호
• /
• pp.61.1-61.1
• /
• 2017

As the application of deep-learning methods has been succeeded in various fields, they have a high potential to be applied to space weather forecasting. Convolutional neural network, one of deep learning methods, is specialized in image recognition. In this study, we apply the AlexNet architecture, which is a winner of Imagenet Large Scale Virtual Recognition Challenge (ILSVRC) 2012, to the forecast of daily solar flare occurrence using the MatConvNet software of MATLAB. Our input images are SOHO/MDI, EIT $195{\AA}$, and $304{\AA}$ from January 1996 to December 2010, and output ones are yes or no of flare occurrence. We consider other input images which consist of last two images and their difference image. We select training dataset from Jan 1996 to Dec 2000 and from Jan 2003 to Dec 2008. Testing dataset is chosen from Jan 2001 to Dec 2002 and from Jan 2009 to Dec 2010 in order to consider the solar cycle effect. In training dataset, we randomly select one fifth of training data for validation dataset to avoid the over-fitting problem. Our model successfully forecasts the flare occurrence with about 0.90 probability of detection (POD) for common flares (C-, M-, and X-class). While POD of major flares (M- and X-class) forecasting is 0.96, false alarm rate (FAR) also scores relatively high(0.60). We also present several statistical parameters such as critical success index (CSI) and true skill statistics (TSS). All statistical parameters do not strongly depend on the number of input data sets. Our model can immediately be applied to automatic forecasting service when image data are available.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.1-7
• /
• 2023

Demand prediction is an essential component of any business or supply chain. Large retailers need to keep track of tens of millions of items flows each day to ensure smooth operations and strong margins. The demand prediction is in the epicenter of this planning tornado. For business processes in retail companies that deal with a variety of products with short shelf life and foodstuffs, forecast accuracy is of the utmost importance due to the shifting demand pattern, which is impacted by an environment of dynamic and fast response. All sectors strive to produce the ideal quantity of goods at the ideal time, but for retailers, this issue is especially crucial as they also need to effectively manage perishable inventories. In light of this, this research aims to show how Machine Learning approaches can help with demand forecasting in retail and future sales predictions. This will be done in two steps. One by using historic data and another by using open data of weather conditions, fuel, Consumer Price Index (CPI), holidays, any specific events in that area etc. Several machine learning algorithms were applied and compared using the r-squared and mean absolute percentage error (MAPE) assessment metrics. The suggested method improves the effectiveness and quality of feature selection while using a small number of well-chosen features to increase demand prediction accuracy. The model is tested with a one-year weekly dataset after being trained with a two-year weekly dataset. The results show that the suggested expanded feature selection approach provides a very good MAPE range, a very respectable and encouraging value for anticipating retail demand in retail systems.

• International Journal of Computer Science & Network Security
• /
• 제23권8호
• /
• pp.210-216
• /
• 2023

Demand prediction is an essential component of any business or supply chain. Large retailers need to keep track of tens of millions of items flows each day to ensure smooth operations and strong margins. The demand prediction is in the epicenter of this planning tornado. For business processes in retail companies that deal with a variety of products with short shelf life and foodstuffs, forecast accuracy is of the utmost importance due to the shifting demand pattern, which is impacted by an environment of dynamic and fast response. All sectors strive to produce the ideal quantity of goods at the ideal time, but for retailers, this issue is especially crucial as they also need to effectively manage perishable inventories. In light of this, this research aims to show how Machine Learning approaches can help with demand forecasting in retail and future sales predictions. This will be done in two steps. One by using historic data and another by using open data of weather conditions, fuel, Consumer Price Index (CPI), holidays, any specific events in that area etc. Several machine learning algorithms were applied and compared using the r-squared and mean absolute percentage error (MAPE) assessment metrics. The suggested method improves the effectiveness and quality of feature selection while using a small number of well-chosen features to increase demand prediction accuracy. The model is tested with a one-year weekly dataset after being trained with a two-year weekly dataset. The results show that the suggested expanded feature selection approach provides a very good MAPE range, a very respectable and encouraging value for anticipating retail demand in retail systems.

• 한국지능시스템학회논문지
• /
• 제26권2호
• /
• pp.93-98
• /
• 2016

정확한 강수예측을 위해서는 예측인자 선정과 예측방법에 대한 선택이 매우 중요하다. 최근에는 강수예측 방법으로 기계학습 기법이 많이 사용되고 있으며, 그 중에서도 특히 인공신경망을 사용한 강수예측 방법은 좋은 성능을 보였다. 본 논문에서는 딥러닝 기법 중 하나인 DBN(deep belief network)를 이용한 새로운 강수예측 방법을 제안한다. DBN는 비지도 사전 학습을 통해 초기 가중치를 설정하여 기존 인공신경망의 문제점을 보완한다. 예측인자로는 기온, 전일-전주 강수일, 태양과 달 궤도 관련 자료를 선정하였다. 기온과 전일-전주 강수일은 서울에서의 1974년부터 2013년까지 총 40년간의 AWS(automatic weather system) 관측 자료를 사용하였고, 태양과 달의 궤도 관련 자료는 서울을 중심으로 계산한 결과를 사용하였다. 전체 기간에서 일부는 학습 자료로 사용하여 예측모델을 생성하였고, 나머지를 생성한 모델의 검증 자료로 사용하였다. 모델 검증 결과로 나온 예측값들은 확률값을 가지며 임계치를 이용하여 강수유무를 판별하였다. 강수 정확도의 척도로 양분예보기법 중 CSI(critical successive index)와 Bias(frequency bias)를 계산하였다. 이를 통해 DBN와 MLP(multilayer perceptron)의 성능을 비교한 결과 DBN의 강수 예측 정확도가 높았고, 수행속도 또한 2배 이상 빨랐다.

• 디지털융복합연구
• /
• 제12권3호
• /
• pp.211-218
• /
• 2014

최근 풍력에너지는 풍력터빈의 지능화뿐만 아니라 풍력 발전량 예측 부분에서 컴퓨팅과의 결합이 확대되고 있다. 풍력 발전은 기상상태에 따라 출력변동이 심하고 출력 예측이 어려워 효율적인 전력 생산을 위해서 신재생에너지를 전력계통에 안정적으로 연계할 수 있는 기술이 필요하다. 본 논문에서는 분산형 전원의 예측정보를 향상시켜 예측한 발전량과 실제 발전량의 차이를 최소화하기 위한 분산형 전원전력의 단기예측 모델을 설계한다. 제안된 모델은 단기 예측을 위해서 물리모델과 통계모델을 결합하였으며, 물리모델에서 생산된 격자별 예측값 중 예측 지점내 예측지점의 값을 추출하고, 물리 모델 예측값에 통계모델을 적용하여 발전량 산정을 위한 최종 기상 예측값을 생성한다. 또한, 제안 모델에서는 실시간 기상청 관측자료와 실시간 중기 예측 자료를 입력 자료로 사용하여 단기 예측모델을 수행한다.

• 한국철도학회논문집
• /
• 제20권4호
• /
• pp.474-481
• /
• 2017

국내에서 태양광 발전설비 설계 시 설계 단계에서의 태양광발전소의 발전량 예측은 국내 현장임에도 불구하고 PVsyst, PVWatts 등 해외 발전량 예측 프로그램과 해외 기상 자료를 이용하여 발전량을 예측하는 경우가 대부분을 차지하고 있는 실정이다. 본 논문에서는 기상정보를 활용한 발전량 예측 비교 연구를 위하여 현재 운영중인 2개 지역의 국내 태양광발전소를 대상지로 선정하였다. 발전량 예측 프로그램인 PVsyst를 활용하여 Meteonorm 7.1과 NASA-SSE의 해외 기상정보를 이용한 발전량 예측값과 국내 기상청 (Korea Meteorology Administration) 기상정보를 활용한 발전량 예측 정확성을 비교하였다. 추가적으로, 기상자료 비교 분석을 통한 발전량 예측 개선 방안을 연구하고, 최종적으로 실제 발전량과의 비교 분석을 통해 기후요소가 고려된 태양광 발전량 예측 수정 모델을 제시하였다.