DOI QR코드

DOI QR Code

전기 가격 예측을 위한 맵리듀스 기반의 로컬 단위 선형회귀 모델

MapReduce-based Localized Linear Regression for Electricity Price Forecasting

  • Han, Jinju (Dept. of Software Convergence Engineering, Kunsan National University) ;
  • Lee, Ingyu (Sorrell College of Business, Troy University) ;
  • On, Byung-Won (Dept. of Software Convergence Engineering, Kunsan National University)
  • 투고 : 2018.10.17
  • 심사 : 2018.11.30
  • 발행 : 2018.12.01

초록

Predicting accurate electricity prices is an important task in the electricity trading market. To address the electricity price forecasting problem, various approaches have been proposed so far and it is known that linear regression-based approaches are the best. However, the use of such linear regression-based methods is limited due to low accuracy and performance. In traditional linear regression methods, it is not practical to find a nonlinear regression model that explains the training data well. If the training data is complex (i.e., small-sized individual data and large-sized features), it is difficult to find the polynomial function with n terms as the model that fits to the training data. On the other hand, as a linear regression model approximating a nonlinear regression model is used, the accuracy of the model drops considerably because it does not accurately reflect the characteristics of the training data. To cope with this problem, we propose a new electricity price forecasting method that divides the entire dataset to multiple split datasets and find the best linear regression models, each of which is the optimal model in each dataset. Meanwhile, to improve the performance of the proposed method, we modify the proposed localized linear regression method in the map and reduce way that is a framework for parallel processing data stored in a Hadoop distributed file system. Our experimental results show that the proposed model outperforms the existing linear regression model. Specifically, the accuracy of the proposed method is improved by 45% and the performance is faster 5 times than the existing linear regression-based model.

키워드

참고문헌

  1. Rafal Weron, "Electricity Price Forecasting: A Review of the State-of-the-art with a Look into the Future," International Journal of Forecasting, pp. 1030-1081, 2014.
  2. Korea Power Exchange, "A Study on Short-term Load Forecasting Technique and its Application," IEEE Trans. on VLSI Systems, pp. 446-455, 2011.
  3. Kane, M. J. Emerson, J. W, "Bigmemory: Manage Massive Matrices with Shared Memory and Memory-mapped Files," IEEE Trans. on VLSI systems, vol. 1, no. 1, pp. 63-71, March 2012.
  4. Jieun Shin, Byungho Jung, Donghoon Lim, "Big Data Distributed Processing System Using RHadoop," Journal of the Korean Data and Information Science Sociaty, vol. 26, no. 5, pp. 1155-1166, 2015. https://doi.org/10.7465/jkdi.2015.26.5.1155
  5. Michael Milton, "Head First Data Analysis," O'Reilly Media, 2009, pp. 382-385.
  6. Wikipedia, (2018, September 20). Feature Selection [Online]. Available: http://en.wikipedia.org/wiki/Feature_selection
  7. SeonYeongO., "A MapReduce-based Prior Probability Optimization Algorithm for Topic Extraction," Journal of KIISE, vol. 45, no. 5, 2018.
  8. Wikipedia. (2018, September 22). MapReduce [Online]. Available: https://en.wikipedia.org/wiki/MapReduce