• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1373-1380
• /
• 2019

In order to increase energy efficiency, developments of the advanced metering infrastructure (AMI) in the smart grid technology have recently been actively conducted. An essential part of AMI is analyzing power consumption and forecasting consumption patterns. In this paper, we analyze the power consumption and summarized the data errors. Monthly power consumption patterns are also analyzed using the k-means clustering algorithm. Forecasting the consumption pattern by each household is difficult. Therefore, we first classify the data into 100 clusters and then predict the average of the next day as the daily average of the clusters based on the deep neural network. Using practically collected AMI data, we analyzed the data errors and could successfully conducted power forecasting based on a clustering technique.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.5
• /
• pp.79-85
• /
• 2019

In this paper, we propose a short-term power forecasting method by applying Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) neural network to Internet of Things (IoT) power meter. We analyze performance based on real power consumption data of households. Mean absolute error (MAE), mean absolute percentage error (MAPE), mean percentage error (MPE), mean squared error (MSE), and root mean squared error (RMSE) are used as performance evaluation indexes. The experimental results show that the GRU-based model improves the performance by 4.52% in the MAPE and 5.59% in the MPE compared to the LSTM-based model.

• Journal of IKEEE
• /
• v.22 no.3
• /
• pp.822-828
• /
• 2018

Recently, energy issues such as massive blackout due to increase in power consumption have been emerged, and it is necessary to improve the accuracy of prediction of power consumption as a solution for these problems. In this study, we investigate the difference between the actual power consumption and the predicted power consumption through the deep learning- based power consumption forecasting experiment, and the possibility of adjusting the power reserve ratio. In this paper, the prediction of the power consumption based on the deep learning can be used as a basis to reduce the power reserve ratio so as not to excessively produce extra power. The deep learning method used in this paper uses a learning model of long-short-term-memory (LSTM) structure that processes time series data. In the computer simulation, the generated power consumption data was learned, and the power consumption was predicted based on the learned model. We calculate the error between the actual and predicted power consumption amount, resulting in an error rate of 21.37%. Considering the recent power reserve ratio of 45.9%, it is possible to reduce the reserve ratio by 20% when applying the power consumption prediction algorithm proposed in this study.

• Smart Media Journal
• /
• v.13 no.1
• /
• pp.18-23
• /
• 2024

Power efficiency management in smart farms is important due to its link to climate change. As climate change negatively impacts agriculture, future agriculture is expected to utilize smart farms to minimize climate impacts, but smart farms' power consumption may exacerbate the climate crisis due to the current electricity production system. Therefore, it is essential to efficiently manage and optimize the power usage of smart farms. In this study, we propose a system that monitors the power usage of smart farm equipment in real time and predicts the power usage one hour later using GRU. CT sensors are installed to collect power usage data, which are analyzed to detect and prevent abnormal patterns, and combined with IoT technology to efficiently manage and monitor the overall power usage. This helps to optimize power usage, improve energy efficiency, and reduce carbon emissions. The system is expected to improve not only the energy management of smart farms, but also the overall efficiency of energy use.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.11
• /
• pp.31-40
• /
• 2024

In the summer, when the cooling load rises due to high temperatures, the hourly demand increases during the day and is relatively less at night compared to the day. These characteristics are considered important information in predicting summer electricity demand. However, if time information is simply expressed as a dummy variable, the model simply recognizes differences between time zones rather than learning changes in time. In this study, we would like to approach this problem by using a time variable using the Fourier transform. Time variables using the Fourier transform will be able to effectively learn differences between times. As a result of evaluating the type of time variable in the summer electricity demand forecast for 2022 and 2023 using the BiGRU model, the model using the time variable using Fourier transform showed the best performance with MAPE of 2.01% and 2.04% confirmed. The results of this study are expected to improve prediction accuracy in the summer when power usage increases and prevent problems such as large-scale power outages.

• The Korean Journal of Applied Statistics
• /
• v.29 no.1
• /
• pp.193-203
• /
• 2016

This paper forecasts electricity demand as a critical element of a demand management system in Smart Grid environment. We present a prediction method of using a combination of predictive values by time series clustering. Periodogram-based normalized clustering, predictive analysis clustering and dynamic time warping (DTW) clustering are proposed for time series clustering methods. Double Seasonal Holt-Winters (DSHW), Trigonometric, Box-Cox transform, ARMA errors, Trend and Seasonal components (TBATS), Fractional ARIMA (FARIMA) are used for demand forecasting based on clustering. Results show that the time series clustering method provides a better performances than the method using total amount of electricity demand in terms of the Mean Absolute Percentage Error (MAPE).

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.294-295
• /
• 2011

전력수급계획은 소비자의 전력 사용량을 예측하고 적정한 공급능력을 확보하는 것이 목적인데, 수요예측 정확도를 향상시키고 전력설비를 적기에 준공시킬수록 적정공급능력 확보가 용이하다. 그러나 최근 전력수요는 계절적, 시간대별로 경향이 과거와는 상이하게 나타나고 있는데 이로 인해 발전기를 예방 정비할 수 있는 기간이 짧아지고 있다. 한편 향후 몇 년간은 준공되는 발전기가 적어 중/단기 수급계획이 더욱 어려울 전망이다. 따라서 최근 수요추세를 고려하여 수요예측 정확도를 향상시키고 현재보다 탄력적인 부하감축제도 시행이 요구된다.

• Proceedings of the KIEE Conference
• /
• 2002.11b
• /
• pp.114-117
• /
• 2002

국내에서는 전력산업의 구조개편이 한창 진행중에 있다. 과거에는 하나의 전력회사가 발전, 송전, 배전을 함께 운영하면서 소비자에게 전력을 공급하였다. 하지만 매년 전력사용량의 급격한 증가와 전력산업이 규모의 경제이론에서 점차 벗어남에 따라 구조개편에 대한 요구가 일어나기 시작하였다. 발전부문에서 경쟁이 도입되어지며 배전부문도 지역적으로 분할되어져 과거의 전력회사는 송전부문만을 담당하게 될 것이다. 여기에 풀(pool)시장이 생겨 전력의 수급을 담당하는 전력계통의 '운영기능'과 전력을 사고 파는 전력의 '시장 기능'을 함께 담당하게 될 것이다. 특히 전력사용량의 급격한 증가로 인해 머지않은 미래에 전력의 수급에 문제가 생길 것이 예측된다. 이러한 이유로 구조개편 이후에는 발전이나 송전부문에서의 변화보다 배전에서의 변화가 두드러질 것으로 보인다. 구조개편 후 지역적으로 나누어진 배전사업자들은 그들의 이익을 최대화하기 위해 여러 가지 부하삭감을 위한 수요관리 프로그램을 시행할 것이다. 이것은 발전량의 조절만으로 정제급전을 실시한 과거와는 달리 부하량의 감소가 함께 사용됨으로 보다 나은 편익을 발생시킬 수 있다. 이 논문에서는 고효율 전통기를 사용한 부하삭감으로 전력의 생산자 뿐만 아니라 소비자에게도 편익이 발생하여 사회적 후생을 증가시킬 수 있다는 것을 고효율 전동기 수요관리 프로그램에 참여하는 참여자의 비용과 편익을 분석함으로서 나타내었다.

• 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.

• Annual Conference of KIPS
• /
• 2019.05a
• /
• pp.250-252
• /
• 2019

국내의 전력 산업은 부정확한 전력수요 예측으로 전력부족과 공급과잉의 주기적 반복이 발생하여 전력 과생산, 에너지 낭비, 전력 과소비와 요금 체납 등의 문제가 발생하고 있다. 이를 해결하기 위해 본 논문에서는 LSTM 알고리즘을 사용하여 전력사용량 예측하고, 정량의 전력을 선구입 할 수 있도록 설계하였다. 제안하는 시스템은 스마트그리드 환경과 인공지능으로 정량의 전기를 구입 할 수 없는 기존의 전력 산업 문제를 보완하여 소비자의 전기요금 절감과 에너지 절약이 가능하다.