• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.447-449
• /
• 2022

본 연구는 언제 어디서나 네트워크에 연결되는 특성과 유연한 이동성을 가지고 있는 대표적인 모바일 플랫폼 중 하나인 안드로이드가 기반이 되었다. 또한, AI을 기반으로 불량품들의 데이터를 알 수 있는 수요예측 알고리즘을 이용하여 수요예측 데이터와 회사의 시계열 데이터들을 안드로이드 스튜디오를 기반으로 실시간 모니터링 UI 디자인 방안에 대해서 연구하고자 한다.

• 전기학회논문지P
• /
• 제63권3호
• /
• pp.189-194
• /
• 2014

Due to the increasing of power consumption, it is difficult to construct accurate prediction model for daily peak power demand. It is very important work to know power demand in next day for manager and control power system. In this research, we develop a daily peak power demand prediction method based on hybrid type composed of AR and Neuro-Fuzzy model. Using data sets between 2006 and 2010 in Korea, the proposed method has been intensively tested. As the prediction results, we confirm that the proposed method makes it possible to effective estimate daily peak power demand than conventional methods.

• 전기학회논문지P
• /
• 제63권4호
• /
• pp.307-311
• /
• 2014

Due to the increasing of power consumption, it is difficult to construct accurate prediction model for daily peak power demand. It is very important work to know power demand in next day for manager and control power system. In this research, we develop a daily peak power demand prediction method considering of characteristics of day of week. The proposed method is composed of liner model based on AR model and nonlinear model based on ELM to resolve the limitation of a single model. Using data sets between 2006 and 2010 in Korea, the proposed method has been intensively tested. As the prediction results, we confirm that the proposed method makes it possible to effective estimate daily peak power demand than conventional methods.

• 전기학회논문지P
• /
• 제62권4호
• /
• pp.169-174
• /
• 2013

Due to the increase of power consumption, it is difficult to construct an accurate prediction model for daily peak power demand. It is very important work to know power demand in next day to manage and control power system. In this research, we develop a daily peak power demand prediction method based on Extreme Learning Machine(ELM) with fast learning procedure. Using data sets between 2006 and 2010 in Korea, the proposed method has been intensively tested. As the prediction results, we confirm that the proposed method makes it possible to effective estimate daily peak power demand than conventional methods.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.778-780
• /
• 1996

The predictive maximum demand controllers often bring about large number of control actions during the every integrating period and/or undesirable load-disconnecting operations during the begining stage if the integrating period. To solve these problems, a fuzzy predictive maximum demand control algorithm is proposed, which determines the sensitivity if control action by urgency if the load interrupting action along with the predicted demand reading to the target or the time arriving at the end stage if the integrating period. A prototype controller employing the proposed algorithm also is developed and its performances are tested by PROCOM SYSTEMS Corperation of Korea.

• KEPCO Journal on Electric Power and Energy
• /
• 제5권3호
• /
• pp.157-163
• /
• 2019

현재까지 피크완화 및 에너지 절감을 위해 한국전력공사 120여개 사옥에 K-BEMS (KEPCO Building Energy Management System)가 운영 중이다. 이 시스템은 PV, PCS, BESS, EMS 등으로 구성되어 있으며 건물에너지 수요예측을 기반으로 BESS, PV 등을 활용하여 에너지 관리를 도모하고 있다. 이 시스템은 단기 과거데이터에 신경망기법을 단순 적용하여 수요를 예측함에 따라 예측 정확도가 높지 않고 운영자 수작업을 통한 BESS 충방전으로 피크 저감이 곤란하며 운영 경제성 제고가 어려운 실정이다. 이러한 문제를 해결하기 위해 전력연구원에서는 2016년부터 3년간 연구과제를 수행하였는데 이를 통해 에러를 최소화하며 높은 신뢰도를 가지는 실시간 수요예측기법과 이에 기반한 BESS충방전 최적화 자동화 기술 개발, 성능을 검증하였기에 이를 본 논문에서 소개하고자 한다.

• International journal of advanced smart convergence
• /
• 제10권4호
• /
• pp.104-109
• /
• 2021

In the aftermath of the global pandemic that started in 2019, there have been many changes in the import/export and supply/demand process of agricultural products in each country. Amid these changes, the necessity and importance of each country's food self-sufficiency rate is increasing. There are several conditions that must accompany efficient agricultural activities, but among them, temperature is by far one of the most important conditions. For this reason, the need for high-accuracy climate data for stable agricultural activities is increasing, and various studies on climate prediction are being conducted in Korea, but data that can visually confirm climate prediction data for farmers are insufficient. Therefore, in this paper, we propose an artificial intelligence-based temperature prediction algorithm that can predict future temperature information by collecting and analyzing temperature data of farms in Gyeonggi-do in Korea for the last 10 years. If this algorithm is used, it is expected that it can be used as an auxiliary data for agricultural activities.

• 통합자연과학논문집
• /
• 제12권1호
• /
• pp.20-23
• /
• 2019

Demand response is usually operated through using the power rates and incentives. Demand management based on power charges is the most rational and efficient demand management method, and such methods include rolling base charges with peak time, sliding scaling charges depending on time, sliding scaling charges depending on seasons, and nighttime power charges. Search for other methods to stimulate resources on demand by actively deriving the demand reaction of loads to increase the energy efficiency of loads. In this paper, ESS algorithm for saving energy based on predicting the amount of solar power generation that can be used for buildings with small loads not under electrical grid.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 학술대회 논문집 전문대학교육위원
• /
• pp.97-100
• /
• 2007

There are regulations on each building for its classification and It is corresponding determined contract demand. For transformer's capability calculation algorithm, cumulated power information of each customer is used to analysis the correlation between power usage and Demand Rate. By modeling this using Least Square Method, it can be targeted to recognize the pattern of transformer use in the past and make a prediction on it in the future.

• 조명전기설비학회논문지
• /
• 제23권9호
• /
• pp.108-116
• /
• 2009

본 논문에서는 단기 물 수요 예측에 대한 모델구현을 위해 MLP의 과도학습 문제를 해결할 수 있고 빠른 학습이 가능한 ELM 기반 단기 물 수요 예측 알고리즘을 제안한다. 제시된 알고리즘의 검증을 위해 2007년도와 2008년도 충남지역 광역상수도인 A정수장에서 취득된 데이터를 분석하여 알고리즘 구현의 정확도 분석에 사용하였다. 실험 결과 MLP모델은 MAPE가 5.82[%]인 반면, 제안된 방법인 ELM기반 모델은 5.61[%]로 성능이 향상된 것으로 나타났다. 또한, MLP모델은 학습에 소요된 시간이 7.57초인 반면, ELM 기반 모델은 0.09초로 빠른 학습이 가능함을 알 수 있었다. 따라서 제안된 ELM 기반 알고리즘은 정수장의 효율적 운영을 위한 단기 물 수요 예측에 활용할 수 있음을 보였다.