Neural network based heuristic fractional order adaptive PID-controller for eliminating communication time delay in multi-area LFC

SAKA M., Gozde H., EKE İ., TAPLAMACIOĞLU M. C.

INTERNATIONAL JOURNAL OF NUMERICAL MODELLING-ELECTRONIC NETWORKS DEVICES AND FIELDS, cilt.35, sa.6, 2022 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 35 Sayı: 6
  • Basım Tarihi: 2022
  • Doi Numarası: 10.1002/jnm.3021
  • Dergi Adı: INTERNATIONAL JOURNAL OF NUMERICAL MODELLING-ELECTRONIC NETWORKS DEVICES AND FIELDS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aerospace Database, Applied Science & Technology Source, Communication Abstracts, Compendex, INSPEC, Metadex, zbMATH, DIALNET, Civil Engineering Abstracts
  • Anahtar Kelimeler: heuristic fractional-order adaptive controller, load frequency control, neural network, stability regions, time delay, LOAD FREQUENCY CONTROL, AUTOMATIC-GENERATION CONTROL, CONTROL-SYSTEM, ALGORITHM, SEARCH
  • Gazi Üniversitesi Adresli: Evet

Özet

Communication of interconnected power system components with each other and with control centers is provided by using various communication links. However, these links can cause significant time delays (TD) depending on the types, distance and conditions of the communication channel. In addition to temporary time delays caused by the time constants of the components due to system failures, this article draws attention to the negative effects that may be caused by permanent communication time delays in particular, as different from the literature. The communication time delays can disrupt the stable operation of power systems and even cause the whole system to breakdown by making it unstable, when combining with other delays. In the study, the fiber-optic (F/O) links are assumed to commonly use in supervisory control and data acquisition (SCADA) systems and the communication time delays are calculated based on this scenario. However, it is no doubt that less used radio frequency (RF)-links will create more time delays. Moreover, to eliminate the negative effects of these types of time delays, a novel neural network based-heuristic fractional order hybrid adaptive proportional-integral-derivative (ML-H-(PID mu)-D-lambda) controller for multi area load frequency control (LFC) scheme is developed and analyzed.