Short-Term Fuzzy Load Forecasting Model Using Genetic-Fuzzy and Ant Colony-Fuzzy Knowledge Base Optimization


Creative Commons License

LÜY M., ATEŞ V., BARIŞÇI N., POLAT H., ÇAM E.

APPLIED SCIENCES-BASEL, cilt.8, sa.6, 2018 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 8 Sayı: 6
  • Basım Tarihi: 2018
  • Doi Numarası: 10.3390/app8060864
  • Dergi Adı: APPLIED SCIENCES-BASEL
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Anahtar Kelimeler: short-term load forecasting, fuzzy logic, genetic algorithm, artificial intelligence, ant colony optimization, ARTIFICIAL NEURAL-NETWORKS, WAVELET TRANSFORM, ARGENTINE ANT, DEMAND, TURKEY
  • Gazi Üniversitesi Adresli: Evet

Özet

The estimation of hourly electricity load consumption is highly important for planning short-term supply-demand equilibrium in sources and facilities. Studies of short-term load forecasting in the literature are categorized into two groups: classical conventional and artificial intelligence-based methods. Artificial intelligence-based models, especially when using fuzzy logic techniques, have more accurate load estimations when datasets include high uncertainty. However, as the knowledge basewhich is defined by expert insights and decisionsgets larger, the load forecasting performance decreases. This study handles the problem that is caused by the growing knowledge base, and improves the load forecasting performance of fuzzy models through nature-inspired methods. The proposed models have been optimized by using ant colony optimization and genetic algorithm (GA) techniques. The training and testing processes of the proposed systems were performed on historical hourly load consumption and temperature data collected between 2011 and 2014. The results show that the proposed models can sufficiently improve the performance of hourly short-term load forecasting. The mean absolute percentage error (MAPE) of the monthly minimum in the forecasting model, in terms of the forecasting accuracy, is 3.9% (February 2014). The results show that the proposed methods make it possible to work with large-scale rule bases in a more flexible estimation environment.