• The KIPS Transactions:PartA
• /
• v.19A no.3
• /
• pp.139-146
• /
• 2012

In the server cluster environment, one of the ways saving energy is to control server's power according to traffic conditions. This is to determine the ON/OFF state of servers according to energy usage of data center and each server. To do this, we need a way to estimate each server's energy. In this paper, we use a software-based power consumption estimation model because it is more efficient than the hardware model using power meter in terms of energy and cost. The traditional software-based power consumption estimation model has a drawback in that it doesn't know well the computing status of servers because it uses only the idle status field of CPU. Therefore it doesn't estimate consumption power effectively. In this paper, we present a CPU field based power consumption estimation model to estimate more accurate than the two traditional models (CPU/Disk/Memory utilization based power consumption estimation model and CPU idle utilization based power consumption estimation model) by using the various status fields of CPU to get the CPU status of servers and the overall status of system. We performed experiments using 2 PCs and compared the power consumption estimated by the power consumption model (software) with that measured by the power meter (hardware). The experimental results show that the traditional model has about 8-15% average error rate but our proposed model has about 2% average error rate.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.11-12
• /
• 2018

대부분의 컴퓨팅 장비들은 교류 전력을 공급받지만 실제 직류로 동작하기 때문에 교류를 직류로 변환하는 전원 공급장치가 필수적이다. 문제는 이과정에서 손실 발생하기 때문에 이를 최소한으로 줄이는 방법이 필요한데 이를 위해 본 논문은 OCP에서 제안한 방법대로 랙 수준의 전원 공급 장치와 DC 서버의 전력 공급 연력 방법에 대해 설계하였으며 이렇게 구성하였을 경우 어떻게 에너지 절감량을 측정할 수 있는가에 대해 설명하였다. 이 방법대로 상용 데이터 센터에 실제 도입이 이루어진다면 데이터 센터 산업이 소모하는 에너지 사용량을 줄이는데 기여할 수 있을 것이다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.05a
• /
• pp.537-540
• /
• 2006

실세계의 복잡하고 종합적인 정보를 빠르고 효율적으로 분석 처리할 수 있는 지리정보시스템(GIS : Geographic Information System)의 효용성이 인식되면서 전력산업에서도 전국의 시설물 관리를 위해 수치지리정보를 구축하였다. 한편, 약 10만호의 고압고객을 대상으로 15분 단위의 전력사용량을 무선통신망을 이용하여 자동원격검침(AMR: Automatic Meter Reading)하고 있다. 본 논문에서는 산재된 대용량의 AMR 시계열성 데이터와 공간성을 지니는 전력설비 데이터를 이용하여 시각적 수요분석 및 공간적 분포특성 부하분석을 할 수 있는 새로운 활용모델을 개발하고 그 결과를 제시하고자 한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.89-90
• /
• 2019

본 논문에서는, 에너지 인터넷에서 정밀한 수요반응을 위한 인공지능 알고리즘 모델을 제안한다. 제안하는 인공지능 모델은 시계열 전력사용량 데이터 처리를 위해 딥러닝 기반 long-short term memory (LSTM) 네트워크를 사용한다. 시뮬레이션 결과를 통해 제안한 시스템 모델의 전력사용량 예측 정확도를 확인하였다.

• Smart Media Journal
• /
• v.13 no.7
• /
• pp.9-17
• /
• 2024

Due to the increase in energy consumption, and eco-friendly policies, there is a need for efficient energy consumption in buildings. Anomaly power detection based on deep learning are being used. Because of the difficulty in collecting anomaly data, anomaly detection is performed using reconstruction error with a Recurrent Neural Network(RNN) based autoencoder. However, there are some limitations such as the long time required to fully learn temporal features and its sensitivity to noise in the train data. To overcome these limitations, this paper proposes the TCN-USAD, combined with Temporal Convolution Network(TCN) and UnSupervised Anomaly Detection for multivariate data(USAD). The proposed model using TCN-based autoencoder and the USAD structure, which uses two decoders and adversarial training, to quickly learn temporal features and enable robust anomaly detection. To validate the performance of TCN-USAD, comparative experiments were performed using two building energy datasets. The results showed that the TCN-based autoencoder can perform faster and better reconstruction than RNN-based autoencoder. Furthermore, TCN-USAD achieved 20% improved F1-Score over other anomaly detection models, demonstrating excellent anomaly detection performance.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.24 no.6
• /
• pp.131-137
• /
• 2010

Change of the energy used in a house can be separated from LNG, and electric power. The electric power consumption of a house is more increasing than LNG. The interest for electric houses is rising due to energy saving and low carbon emission. Accordingly, the amount of energies and cost are analyzed consumed in a house using cumulative energy consumption. The result of analysis, amount of electric power, is more increase. In comparison, the use volume of city gas is more decrease. In this paper, the use volume of energy resource is analyzed using historical energy consumption data in the past 25 years. In addition, expected electrical power and heating energy is analysed adopting an Electric Residence.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.544-546
• /
• 2007

본 연구에서는 전력부가서비스 시스템으로 개발한 전력에너지 컨설팅 시스템의 주요 기능과 운영방을 소개한다. 본 시스템의 주요 기능은 전력소비 데이터 분석, 전력사용량 분석, 전력요금 분석, 전력요금 컨설팅 보고서 제공 등 4가지로 구분할 수 있다. 원격검침을 시행중인 고압고객 중 계약전력이 100kW 이상인 대수용가로부터 특히, 전력요금 절감을 필요로 하지만 별도의 설비나 인력을 보유하지 않은 10,000kW 이하 고객을 적용대상으로 하고 있다. 본 시스템은 수용가에게는 전력요금 절감을 전력회사 및 Energy Service Provider에게는 간접적 부하/수요관리 효과를 목표로 개발하였으며, 향후 대수용가를 대상으로 전력부가서비스 적용 사업화 분야에 활용될 수 있을 것이다.

• The Journal of Bigdata
• /
• v.5 no.1
• /
• pp.227-239
• /
• 2020

This paper introduces a method for predicting the maximum power demand despite communication errors in industrial sites. Due to the recent policy of de-nuclearization in Korea, the price of electricity is inevitable, and the amount of electricity used and maximum load management for the management of power demand are becoming important issues. Accordingly, it is important to predict and manage peak power. However, problems such as loss and modulation of measured power data occur at industrial sites due to noise generated by various facilities and sensors. It is difficult to predict the exact value when measured effective power data are lost. The study presents a model for predicting and correcting anomalies and missing values when measured effective power data are lost. The models used in this study are expected to be useful in predicting peak power demand in the event of communication errors at industrial sites.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.900-903
• /
• 2016

A variety of measures in various fields, buildings, factories, offices, supermarkets, etc. through a sensor installed for energy savings and user convenience are transmitted and received by the cloud server. Also, this kind of sensor service increases considering the user's convenience. In this paper, we research a variety of meter data linkage between oracle database and time series database, and data analysis.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.2
• /
• pp.199-204
• /
• 2017

In this study, we present a home appliance load identification algorithm. The algorithm utilizes complex sensory data in order to improve the existing NIALM using total power usage information. We define the influence graph between the appliance status and the measured sensor data. The device identification prediction result is calculated as the weighted sum of the predicted value of the sensor data processing algorithm and the predicted value based on the total power usage. We evaluate proposed algorithm to compare appliance identification accuracy with the existing NIALM algorithm.