Swarm intelligence approaches to estimate electricity energy demand in Turkey

作者:

Highlights:

摘要

This paper proposes two new models based on artificial bee colony (ABC) and particle swarm optimization (PSO) techniques to estimate electricity energy demand in Turkey. ABC and PSO electricity energy estimation models (ABCEE and PSOEE) are developed by incorporating gross domestic product (GDP), population, import and export figures of Turkey as inputs. All models are proposed in two forms, linear and quadratic. Also different neighbor selection mechanisms are attempted for ABCEE model to increase convergence to minimum of the algorithm. In order to indicate the applicability and accuracy of the proposed models, a comparison is made with ant colony optimization (ACO) which is available for the same problem in the literature. According to obtained results, relative estimation errors of the proposed models are lower than ACO and quadratic form provides better-fit solutions than linear form due to fluctuations of the socio-economic indicators. Finally, Turkey’s electricity energy demand is projected until 2025 according to three different scenarios.

论文关键词:Ant colony optimization,Artificial bee colony,Particle swarm optimization,Electricity energy estimation,Swarm intelligence

论文评审过程:Received 10 November 2011, Revised 11 June 2012, Accepted 15 June 2012, Available online 27 June 2012.

论文官网地址:https://doi.org/10.1016/j.knosys.2012.06.009