A novel load profile generation method based on the estimation of regional usage habit parameters with genetic algorithm

Yılmaz F., Eren Y.

ELECTRIC POWER SYSTEMS RESEARCH, vol.217, no.109165, pp.1-13, 2023 (SCI-Expanded)

  • Publication Type: Article / Article
  • Volume: 217 Issue: 109165
  • Publication Date: 2023
  • Doi Number: 10.1016/j.epsr.2023.109165
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, PASCAL, Environment Index, INSPEC
  • Page Numbers: pp.1-13
  • Yıldız Technical University Affiliated: Yes


Considering the millions of end-users in a medium-scale city, even achieving a smart price improvement

or imposing incentives for flattening the demands makes millions of saving. Hence, load profiling for

electricity companies has recently emerged as a crucial requirement for commitment agreements, maintenance

programming, and efficient energy management within demand response applications. Those facilities require

load type classification in the customer data set to apply the deterministic and stochastic techniques in the

planning and operation processes. In this manner, we have presented a novel procedure with a customized

genetic algorithm (GA) to generate load profiles without adopting costly techniques. Using the regional survey

or statistical data for generating the profiles, we have considered the real-time scenarios in terms of living

people and household appliances for the residential sector. Namely, the usage habit parameters are estimated

recursively by GA, then those parameters are used to generate near-realistic profiles. The overall scheme is

tested on MATLAB® and remarkable results are illustrated.