[논문]신경회로망을 이용한 마이크로그리드 단기 전력부하 예측

정대원; 양승학; 유용민; 윤근영

doi:10.5370/kiee.2017.66.4.621

신경회로망을 이용한 마이크로그리드 단기 전력부하 예측
Short-Term Load Forecast in Microgrids using Artificial Neural Networks 원문보기

전기학회논문지 = The Transactions of the Korean Institute of Electrical Engineers, v.66 no.4, 2017년, pp.621 - 628

정대원 () , 양승학 (호남대 공대 전기공학과) , 유용민 (호남대학교 미래자동차공학부) , 윤근영

Abstract ▼ AI-Helper

This paper presents an artificial neural network (ANN) based model with a back-propagation algorithm for short-term load forecasting in microgrid power systems. Owing to the significant weather factors for such purpose, relevant input variables were selected in order to improve the forecasting accuracy. As remarked above, forecasting is more complex in a microgrid because of the increased variability of disaggregated load curves. Accurate forecasting in a microgrid will depend on the variables employed and the way they are presented to the ANN. This study also shows numerically that there is a close relationship between forecast errors and the number of training patterns used, and so it is necessary to carefully select the training data to be employed with the system. Finally, this work demonstrates that the concept of load forecasting and the ANN tools employed are also applicable to the microgrid domain with very good results, showing that small errors of Mean Absolute Percentage Error (MAPE) around 3% are achievable.

주제어

AI 본문요약
AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

제안 방법

In this paper, we propose new ANN-based architectural model for STLF in the microgrids by applying new distributed-intelligence technologies, which are expected to be incorporated into different components of the grid. The back-propagation algorithm is proposed an ANN methodology in order to increase the accuracy of the forecast result in case of irregular weather conditions such as typhoons and weekends during the summer season.
This study also shows numerically that there is a close relationship between forecast errors and the number of training patterns used; thus, it is necessary to carefully select the training data to be employed with the system. This demonstration is backed up by a detailed database containing real information of load curves disaggregated up to microgrid level running for the future.
Accurate forecasting in a microgrid will depend on the variables employed and the way they are presented to the ANN. This study also shows numerically that there is a close relationship between forecast errors and the number of training patterns used; thus, it is necessary to carefully select the training data to be employed with the system. This demonstration is backed up by a detailed database containing real information of load curves disaggregated up to microgrid level running for the future.

대상 데이터

5. It has 63 input neurons, 70 hidden neurons, and 24 output neurons. Table 2 defines the input and output of the neural network.

데이터처리

For such purpose, relevant input variables were selected in order to improve the accuracy of forecasting, we not only used weather factors but also a seasonal approach. For recognizing the significant weather factors, the proposed model used the correlation coefficient. Temperature and dew point were selected by the result of the correlation analysis.

이론/모형

An ANN-based model was proposed in this paper for short-term load forecasting in disaggregated, microgrid-sized power systems by incorporating back-propagation algorithm. For such purpose, relevant input variables were selected in order to improve the accuracy of forecasting, we not only used weather factors but also a seasonal approach.
The best results were obtained with a total of 70 neurons in the hidden layer, the Bayesian Regulation Back-propagation training function and the Sum Squared Error network performance function. The proposed architecture is trained by using a back propagation algorithm [4,16] with Matlab SIMULINK NN Toolbox. The performance of the proposed neural network based STLF model was tested using hourly load data.

참고문헌 (16)

J. W. Taylor, P. E. McSharry, "Short-term load forecasting methods: An evaluation based on European data," IEEE Transaction on Power System, no. 22, pp. 2213-2219, 2008.
M. Shelke1, P. D. Thakare, "Short Term Load Forecasting by Using Data Mining Techniques," Int. Journal of Science and Research, ISSN (Online): 2319-7064, vol. 3(9), 2014, pp. 1363-1367
Cheol-Hong Kim, Bon-Gil Koo, JuneHo Park, "Shortterm Electric Load Forecasting Using Data Mining Technique," J Electr Eng Technol, vol. 7(6), pp. 807-813, 2012

원문보기 상세보기
K. Y. Lee, J. H. Park, "Short-term load forecasting using an artificial neural network," Transactions of Power Systems, vol. 7, no. 1, February, 1992.
M.W. Xiao, B.X. Min, M. Shun, "Short-term load forecasting with artificial neural network and fuzzy logic," Internat conference on power system technology, vol. 2, pp 1101-1104, 2002.
A. Jain, B. Satish, "Clustering based Short Term Load Forecasting using Support Vector Machines," Bucharest Power Tech Conference, June 2009.
Kim, H. M.; Kinoshita, T.; Shin, M. C. "A multiagent system for autonomous operation of islanded microgrids based on a power market environment," Energies, 2010, 3, 1972-1990.

상세보기
Kim, H. M.; Lim, Y.; Kinoshita, T. "An intelligent multiagent system for autonomous microgrid operation," Energies 2012, 5, 3347-3362.

상세보기
Xiao, Z.; Li, T.; Huang, M.; Shi, J.; Yang, J.; Yu, J.; Wu, W. "Hierarchical MAS based control strategy for microgrid," Energies 2010, 2, 1622-1638.
A. K. Suykens, T. V. Gestel, J. D. Brabanter, B. D. Moor, J. Vandewalle, "Least Squares Support Vector Machines," World Scientific, Singapore, 2002.
N. Kandil, R. Wamkeue, M. Saad, S.Georges, "An effective approach for short term load forecasting using artificial neural network," Electrical Power and Energy Systems, no. 28, pp. 525-530, 2006.

상세보기
D. Niu, Y. Wang, D. Dash Wub, "Power load forecasting using support vector machine and ant colony optimization," Expert Systems with Applications, no. 37, pp. 2531-2539, 2010.

상세보기
D. C. Park, et. el "Electric load forecasting using an artificial neural network, IEEE Trans. Power System, 6 1991, pp. 442-449
Ronak K Patel, Ankit V Gajjar, "Short term load forecasting using artificial neural network technique," International Jouranl for Tech. Research Eng'g, vol. 1, no. 9, 2014, pp. 736-740.
L. Hernandez, C. Baladron, J. M. Aguiar, Belen Carro, "Short-Term Load Forecasting for Microgrids Based on Artificial Neural Networks," Journal of Energies, vol. 6, 2013, ISSN 1996-1073, pp. 1385-1408

상세보기
D. Kown, M. Kim, C. Hong, S. Cho, "Short Term Load Forecasting based on BPL Neural Network with Weather Factors," Int. Journal of Multimedia and Ubiquitous, vol. 9, no.1, 2014, pp. 415-424

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증