• 한국수소및신에너지학회논문집
• /
• 제33권5호
• /
• pp.591-597
• /
• 2022

Recently, technologies for efficient power grid operation have become important due to climate change. For this reason, predicting power demand using deep learning is being considered, and it is necessary to understand the influence of characteristics of each region, industrial structure, and climate. This study analyzed the power demand of New Jersey in US, with a high urbanization rate and a large service industry, and West Virginia in US, a low urbanization rate and a large coal, energy, and chemical industries. Using recurrent neural network algorithm, the power demand from January 2020 to August 2022 was learned, and the daily and weekly power demand was predicted. In addition, the power grid operation based on the power demand forecast was discussed. Unlike previous studies that have focused on the deep learning algorithm itself, this study analyzes the regional power demand characteristics and deep learning algorithm application, and power grid operation strategy.

• 농업과학연구
• /
• 제46권1호
• /
• pp.67-78
• /
• 2019

The purpose of this study was to predict the water quality using the RNN (recurrent neutral network) and LSTM (long short-term memory). These are advanced forms of machine learning algorithms that are better suited for time series learning compared to artificial neural networks; however, they have not been investigated before for water quality prediction. Three water quality indexes, the BOD (biochemical oxygen demand), COD (chemical oxygen demand), and SS (suspended solids) are predicted by the RNN and LSTM. TensorFlow, an open source library developed by Google, was used to implement the machine learning algorithm. The Okcheon observation point in the Geum River basin in the Republic of Korea was selected as the target point for the prediction of the water quality. Ten years of daily observed meteorological (daily temperature and daily wind speed) and hydrological (water level and flow discharge) data were used as the inputs, and irregularly observed water quality (BOD, COD, and SS) data were used as the learning materials. The irregularly observed water quality data were converted into daily data with the linear interpolation method. The water quality after one day was predicted by the machine learning algorithm, and it was found that a water quality prediction is possible with high accuracy compared to existing physical modeling results in the prediction of the BOD, COD, and SS, which are very non-linear. The sequence length and iteration were changed to compare the performances of the algorithms.

• 전기전자학회논문지
• /
• 제23권1호
• /
• pp.127-133
• /
• 2019

미래에 스마트 그리드 도입을 위해 전력수요예측은 중요한 연구 분야 중 하나이다. 하지만 전력데이터는 많은 외부적 요소들에 영향을 받기 때문에 예측하기 어렵다. 기존의 전력수요예측 방법들은 가공되지 않은 전력데이터를 그대로 이용하기 때문에 정확도 높은 예측을 하는데 한계가 있어왔다. 본 논문에서는 가공되지 않은 전력데이터를 이용하는 전력수요예측의 문제를 해결하기 위해 확률기반 학습알고리즘을 제안한다. 확률 모델은 전력데이터의 확률적 특성을 분석하기에 적합하다. 제안한 모델의 중기 전력수요예측 성능을 비교하기 위해 신경망 네트워크 중 하나인 순환신경망과 성능 비교를 해보았다. 매사추세츠 대학에서 제공한 전력데이터를 이용하여 성능 비교를 한 결과 본 논문에서 제안한 확률기반 학습알고리즘이 중기 수요예측에 더 좋은 성능을 나타냄을 확인하였다.

• 한국인공지능학회지
• /
• 제10권1호
• /
• pp.9-14
• /
• 2022

The demand for public bicycles operated by the Seoul Metropolitan Government is increasing every year. The size of the Seoul public bicycle project, which first started with about 5,600 units, increased to 3,7500 units as of September 2021, and the number of members is also increasing every year. However, as the size of the project grows, excessive budget spending and deficit problems are emerging for public bicycle projects, and new bicycles, rental office costs, and bicycle maintenance costs are blamed for the deficit. In this paper, the Azure Machine Learning Studio program and the Boosted Decision Tree Regression technique are used to predict the number of public bicycle rental over environmental factors and time. Predicted results it was confirmed that the demand for public bicycles was high in the season except for winter, and the demand for public bicycles was the highest at 6 p.m. In addition, in this paper compare four additional regression algorithms in addition to the Boosted Decision Tree Regression algorithm to measure algorithm performance. The results showed high accuracy in the order of the First Boosted Decision Tree Regression Algorithm (0.878802), second Decision Forest Regression (0.838232), third Poison Regression (0.62699), and fourth Linear Regression (0.618773). Based on these predictions, it is expected that more public bicycles will be placed at rental stations near public transportation to meet the growing demand for commuting hours and that more bicycles will be placed in rental stations in summer than winter and the life of bicycles can be extended in winter.

• 한국융합학회논문지
• /
• 제8권1호
• /
• pp.19-23
• /
• 2017

전력은 모든 나라에서 사회 발전과 경제 성장에 가장 기본적인 자원이다. 산업이 고도화 되고 경제의 규모가 발전하면서 전력의 소비량은 점점 증가하고 있다. 전력을 공급하는 쪽에서는 전력을 생산할 때 자원의 낭비를 줄이기 위해 전력 사용량을 예측하는 것은 중요한 일이다. 또한 전력 수요 예측을 통해 여름과 겨울의 피크 타임에서의 전력 수요를 분산하는 것이 가능하다. 그리고 소비 전력의 예측은 국내에서 수요자원 거래시장(Negawatt market)이 본격화되면서 더욱 중요하게 되었다. 더구나 전력 소비량 예측은 소비자가 전력 시장에 직간접적으로 참여하는 수요관리 방법을 제공해준다. 본 연구에서는 1999년부터 2011년까지의 국내총생산, 1인당 국민총소득, 부가세, 국내전력소비량을 이용하여 제주도의 어업 전력 사용량을 예측하는데 유전자 알고리즘을 사용하고 있다. 유전자 알고리즘은 다양한 조합 최적화 분야에서 최적해를 찾는데 유용하게 사용되는 알고리즘이다. 본 논문에서 유전자 알고리즘에서 최적의 동작을 위한 파라미터들을 찾는다. 그리고 실제 전력 소비량 예측을 위해 사용되는 계수(coefficient)들의 최적값을 찾아 예측값과 실제 전력 소비량의 오차를 최소화하는데 목적이 있다.

• 대한임베디드공학회논문지
• /
• 제5권4호
• /
• pp.225-233
• /
• 2010

In this paper, we try to improve the performance of the demand paging loader suggested to use the demand paging way that is not based on operating system. The demand paging switching strategy used in the existing operating system can know the recently used pages by running multi-processing. Then, based on it, some page switching strategies have been made for the recently used pages or the frequently demanded pages. However, the strategies based on operating system cannot be applied in single processing that is not based on operating system because any context switching never occur on the single processing. So, this paper is trying to suggest the demand paging switching strategies that can be applied in paging loader running in single process. In the Return-Prediction-Algorithm, we saw the improved performance in the program that the function call occurred frequently in a long distance. And then, in the Most-Frequently-Used-Page-Remain-Algorithm, we saw the improved performance in the program that the references frequently occurred for the particular pages. Likewise, it had an enormous effect on keeping the memory reduction performance by the demand paging and reducing the running time delay at the same time.

• International journal of advanced smart convergence
• /
• 제10권4호
• /
• pp.98-103
• /
• 2021

Recently, as the need for food resources has increased both domestically and internationally, support for the agricultural sector for stable food supply and demand is expanding in Korea. However, according to recent media articles, the biggest problem in rural communities is the unstable profit structure. In addition, in order to confirm the profit structure, profit forecast data must be clearly prepared, but there is a lack of auxiliary data for farmers or future returnees to predict farm income. Therefore, in this paper we analyzed data over the past 15 years through time series analysis and proposes an artificial intelligence farm income prediction algorithm that can predict farm household income in the future. If the proposed algorithm is used, it is expected that it can be used as auxiliary data to predict farm profits.

• Structural Engineering and Mechanics
• /
• 제23권2호
• /
• pp.177-193
• /
• 2006

Determining the hysteretic energy demand and dissipation capacity and level of damage of the structure to a predefined earthquake ground motion is a highly non-linear problem and is one of the questions involved in predicting the structure's response for low-performance levels (life safe, near collapse, collapse) in performance-based earthquake resistant design. Neural Network (NN) analysis offers an alternative approach for investigation of non-linear relationships in engineering problems. The results of NN yield a more realistic and accurate prediction. A NN model can help the engineer to predict the seismic performance of the structure and to design the structural elements, even when there is not adequate information at the early stages of the design process. The principal aim of this study is to develop and test multi-layered feedforward NNs trained with the back-propagation algorithm to model the non-linear relationship between the structural and ground motion parameters and the hysteretic energy demand in steel moment resisting frames. The approach adapted in this study was shown to be capable of providing accurate estimates of hysteretic energy demand by using the six design parameters.

• ETRI Journal
• /
• 제44권2호
• /
• pp.244-259
• /
• 2022

Bicycle- or bike-sharing systems (BSSs) have received increasing attention as a secondary transportation mode due to their advantages, for example, accessibility, prevention of air pollution, and health promotion. However, in BSSs, due to bias in bike demands, the bike rebalancing problem should be solved. Various methods have been proposed to solve this problem; however, it is difficult to apply such methods to small cities because bike demand is sparse, and there are many practical issues to solve. Thus, we propose a demand prediction model using multiple classifiers, time grouping, categorization, weather analysis, and station correlation information. In addition, we analyze real-world relocation data by relocation managers and propose a relocation algorithm based on the analytical results to solve the bike rebalancing problem. The proposed system is compared experimentally with the results obtained by the real relocation managers.

• 대한전자공학회논문지TC
• /
• 제42권12호
• /
• pp.9-16
• /
• 2005

인터넷 규모의 확장과 트래픽의 증가로 인해 발생하는 망 혼잡 상황을 해결하기 위해 본 연구는 망 제어 기술의 일환책으로서 간섭 예측 정보를 이용한 online 라우팅 알고리듬을 제안한다. 차세대 통합망은 사용자 서비스별 요구 수준에 따라 종단간의 QoS를 보장해야 한다. 이를 위해 동적 대역폭 할당이 효율적으로 이루어져야 하며, 망 전체 성능을 고려한 경로 설정 알고리듬이 필요하다. 본 논문에서 제안한 알고리듬은 현재 라우팅 요청이 요구하는 대역폭의 양이 미래의 잠재적인 트래픽을 간섭하는 정도를 예측하여, 이를 최소화시키는 방안을 제시한다. 망 전체 성능을 최대화하고, 한정된 자원이 낭비되는 것을 방지하기 위해 제안 알고리듬은 요구 대역폭, link 상태정보, 그리고 ingress-egress pair 정보 등을 복합적으로 고려한다. 또한 간섭을 예측하는 것은 동적으로 변화하는 망 상황에서 보장된 대역폭을 제공하게 함으로써 사용자의 요구를 최대한 수용할 수 있게 한다. 본 논문에서는 Internet traffic engineering에 적합한 최적 경로 설정 알고리듬을 제안하기 위해 라우팅 알고리듬이 갖추어야 할 요구 조건과 최근 연구동향을 분석하였으며, QoS 라우팅의 대표적인 연구사례를 분석하였다. 그리고 이를 기반으로 기존의 알고리듬의 문제점을 파악하고 최적의 해결 방안을 제시한다. 개선된 사항은 시뮬레이션을 통해 기존 알고리듬과 비교 및 분석되었다.