• 한국정밀공학회지
• /
• 제30권5호
• /
• pp.461-466
• /
• 2013

In this paper, main mechanism and measurement method of energy consumption for machine tools are investigated by experiment and simulation. To evaluate total energy consumption of the machine tools, standard test workpiece and measuring method and test procedures are suggested. And, improvement of energy consumption evaluation by the motion kinematics theory is used. In addition, to estimate energy consumption of machine tools in design process, mass distribution of the structure and 5 axis motions are investigated and simulated by numerical analysis.

• 한국정보통신학회논문지
• /
• 제26권4호
• /
• pp.633-636
• /
• 2022

The reduction of energy consumption at the base station (BS) has become more important recently. In this paper, we consider the adaptive muting of the antennas based on the predicted future traffic load to reduce the energy consumption where the number of active antennas is adaptively adjusted according to the predicted future traffic load. Given that traffic load is sequential data, three different RNN structures, namely long-short term memory (LSTM), gated recurrent unit (GRU), and bidirectional LSTM (Bi-LSTM) are considered for the future traffic load prediction. Through the performance evaluation based on the actual traffic load collected from the Afghanistan telecom company, we confirm that the traffic load can be estimated accurately and the overall power consumption can also be reduced significantly using the antenna musing.

• International Journal of Internet, Broadcasting and Communication
• /
• 제7권1호
• /
• pp.23-29
• /
• 2015

Energy constraints of wireless sensor networks are an important challenge. Data Transmission requires energy. Distance between origin and destination has an important role in energy consumption. In addition, the location of base station has a large impact on energy consumption and a specific method not proposed for it. In addition, a obtain model for location of base station proposed. Also a model for distributed clustering is presented by cluster heads. Eventually, a combination of discussed ideas is proposed to improve the energy consumption. The proposed ideas have been implemented over the LEACH-C protocol. Evaluation results show that the proposed methods have a better performance in energy consumption and lifetime of the network in comparison with similar methods.

• 한국정보전자통신기술학회논문지
• /
• 제14권1호
• /
• pp.14-21
• /
• 2021

그린 네트워킹(Green networking)은 유선 데이터 네트워크(Wired data network)에서 통합적인 에너지 관리를 통해 에너지 낭비와 CO2 배출 감소를 유도하기 위해 주요 관심분야가 되었다. 그러나 액세스 네트워크(access networks)는 유선 데이터 네트워크 영역에서 사용자 단말을 제외하면 가장 많은 에너지를 소비하는 영역임에도 불구하고 그 범위가 매우 광대하여 통합적인 관리가 어렵고, 그 에너지 소모량과 에너지 절약 잠재성을 예측하기가 매우 어렵다. 본 논문에서는 기존의 다양한 수학적 예측 모델과 실험 및 실측 데이터를 이용하여 유선 액세스 네트워크의 에너지 소모량 데이터를 수집하고 머신러닝(Machine learning)의 지도학습을 이용한 다중 선형 회귀모델을 생성한다. 또한 생성한 모델로부터 다양한 실험을 통해 회귀모델의 성능을 최적화하여 유선 액세스 네트워크의 에너지 소모량을 예측하였고 생성한 회귀모델은 널리 알려진 평가 지표를 통해 성능을 평가하였다.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.1256-1263
• /
• 2022

With the advent of the Fourth Industrial Revolution, the amount of energy used in buildings has been increasing due to changes in the energy use structure caused by the massive spread of information-oriented equipment, climate change and greenhouse gas emissions. For the efficient use of energy, it is necessary to have a plan that can predict and reduce the amount of energy use according to the type of energy source and the use of buildings. To address such issues, this study presents a model embedded in a digital twin that predicts energy use in buildings. The digital twin is a system that can support a solution of urban problems through the process of simulations and analyses based on the data collected via sensors in real-time. To develop the energy use prediction model, energy-related data such as actual room use, power use and gas use were collected. Factors that significantly affect energy use were identified through a correlation analysis and multiple regression analysis based on the collected data. The proof-of-concept prototype was developed with an exhibition facility for performance evaluation and validation. The test results confirm that the error rate of the energy consumption prediction model decreases, and the prediction performance improves as the data is accumulated by comparing the error rates of the model. The energy use prediction model thus predicts future energy use and supports formulating a systematic energy management plan in consideration of characteristics of building spaces such as the purpose and the occupancy time of each room. It is suggested to collect and analyze data from other facilities in the future to develop a general-purpose energy use prediction model.

• Advances in Energy Research
• /
• 제6권2호
• /
• pp.91-101
• /
• 2019

This paper proposes an efficient data-driven approach to build models for predicting energy consumption in buildings. Data used in this research is collected by installing humidity and temperature sensors at different locations in a building. In addition to this, weather data from nearby weather station is also included in the dataset to study the impact of weather conditions on energy consumption. One of the main emphasize of this research is to make feature selection independent of domain knowledge. Therefore, to extract useful features from data, two different approaches are tested: one is feature selection through principal component analysis and second is relative importance-based feature selection in original domain. The regression model used in this research is gradient boosting regression and its optimal parameters are chosen through a two staged coarse-fine search approach. In order to evaluate the performance of model, different performance evaluation metrics like r2-score and root mean squared error are used. Results have shown that best performance is achieved, when relative importance-based feature selection is used with gradient boosting regressor. Results of proposed technique has also outperformed the results of support vector machines and neural network-based approaches tested on the same dataset.

• 한국인터넷방송통신학회논문지
• /
• 제19권5호
• /
• pp.93-99
• /
• 2019

본 논문에서는 효율적 에너지 관리를 위해 인공 신경망 중 하나인 GRU 모델을 사용하여 전력사용량을 예측하고 예측된 전력사용량과 실제 전력사용량의 비교를 통해 부하를 자동 제어 하는 스마트 미터기를 제안한다. 제안한 스마트 미터기를 통해 GRU 모델을 학습시키기 위해 필요한 전력사용량 데이터를 수집했다. 구현된 스마트 미터기가 전력사용량 자동측정 및 실시간 관찰 기능과 전력사용량 예측을 통한 부하 제어 기능을 가지고 있음을 보여준다. 성능평가 지표 중 하나인 Root Mean Squared Error (RMSE) 값에 약 20%의 마진 값을 이용하여 부하 자동 제어를 위한 기준 값으로 설정했다. 부하 자동 제어 기능을 가진 스마트 미터기로 인해 에너지 관리의 효율성이 증대되는 것을 확인하였다.

• KIEAE Journal
• /
• 제17권3호
• /
• pp.75-81
• /
• 2017

Purpose: The energy consumption of apartment units is affected by the lifestyle of the residents rather than system technology. In this study the numerical analysis of assumed energy consumption correlation factors with arbitrary value due to uncertainty. It is intended to be used as a simulation correction value which can be utilized as a predicted value of actual energy usage. The correction value of the simulation is set in the developed form of the existing process that derives the actual usage amount. The simulation results used in the existing evaluation system are used to maintain the useful value as the current system evaluation scale and predict the actual capacity. Method: The method of the study is to statistically analyze the data frames of all complexes capable of collecting the annual energy usage and to reconstruct the population by adding the variables that are expected to be correlated. Repeat the data frame configuration with variables that are assumed to be highly correlated with energy use levels. Determine whether there is correlation or not. The intensity of the external characteristics of the building equipment related to the energy consumption is presented as the quantitative value. Result: The correlation between electricity consumption and trading price since 2010 is analyzed as (Correlation coefficient 0.82). These results are higher than (Correlation coefficient 0.79), which is the correlation between residential area and trading price. This paper signifies the starting point of the methodology that broadens the field of view of verification of simulation feasibility limited to the prediction technique focused on the simulation tool and the element technology scope.The diversified phenomenon reproduction method develops the existing energy simulation method.It can be completed with a simulation methodology that can infer actual energy consumption.

• 전기전자학회논문지
• /
• 제23권1호
• /
• pp.120-126
• /
• 2019

최근 에너지 인터넷에서 지능형 원격검침 인프라를 이용하여 확보된 대량의 전력사용데이터를 기반으로 효과적인 전력수요 예측을 위해 다양한 기계학습기법에 관한 연구가 활발히 진행되고 있다. 본 연구에서는 전력량 데이터와 같은 시계열 데이터에 대해 효율적으로 패턴인식을 수행하는 인공지능 네트워크인 Gated Recurrent Unit(GRU)을 기반으로 딥 러닝 모델을 제안하고, 실제 가정의 전력사용량 데이터를 토대로 예측 성능을 분석한다. 제안한 학습 모델의 예측 성능과 기존의 Long Short Term Memory (LSTM) 인공지능 네트워크 기반의 전력량 예측 성능을 비교하며, 성능평가 지표로써 Mean Squared Error (MSE), Mean Absolute Error (MAE), Forecast Skill Score, Normalized Root Mean Squared Error (RMSE), Normalized Mean Bias Error (NMBE)를 이용한다. 실험 결과에서 GRU기반의 제안한 시계열 데이터 예측 모델의 전력량 수요 예측 성능이 개선되는 것을 확인한다.

• 문화기술의 융합
• /
• 제9권6호
• /
• pp.883-888
• /
• 2023

데이터센터는 24시간 365일 IT 서비스를 제공하는 곳이기 때문에, 2030년에는 데이터센터의 전력 소비량은 약 10%로 증가될 것으로 예측되고, 고밀도 IT장비들의 도입이 점차 증가하면서, IT장비가 안정적으로 운영될 수 있도록 냉방 에너지 절감 및 이를 위한 에너지 관리가 갖춰져야 하기에 다양한 연구가 요구되고 있는 상황이다. 본 연구는 데이터센터의 에너지 절약을 위해 다음과 같은 과정을 제안한다. 데이터센터를 CFD 모델링하고, 인공지능기반 열환경 예측 모델을 제안하였으며, 실측 데이터와 예측 모델 그리고 CFD 결과를 비교하여 최종적으로 데이터 센터의 열관리 성능을 평한 결과 전처리 방식은 정규화 방식으로 사용되었고, 정규화에 따른 RCI, RTI 및 PUE의 예측값 또한 유사한 것을 확인할 수 있다. 따라서 본 연구에서 제안하는 알고리즘으로 데이터센터에 적용될 열환경 예측 모델로 적용 및 제공할 수 있을 것으로 판단된다.