Tuloli, Mohamad Handri (2019) Firefly Photinus search Algorithm dengan Reduksi Langkah Acak. Sarjana thesis, Universitas Brawijaya.
Abstract
Firefly Algorithm (FA) adalah salah satu algoritma pengoptimalan yang terinspirasi oleh perilaku flashing kunang-kunang. Algoritma kunang-kunang memiliki beberapa kelemahan seperti terjebak ke dalam beberapa optimum lokal, parameter FA ditetapkan tanpa perubahan selama iterasi, dan tidak mengingat sejarah setiap situasi dalam setiap iterasi. Firefly Photinus search Algorithm (FPA) merupakan variasi baru dari Firefly Algorithm (FA) yang bertujuan mengatasi terjebaknya solusi dalam beberapa optimum lokal dan mempelajari sejarah setiap iterasi selama proses pencarian dengan mengembangkan koefisien reduksi arbsorpsi cahaya dan daftar pasangan (mate list). Pada skripsi ini, diusulkan parameter baru yaitu reduksi langkah acak yang bertujuan untuk memaksimalkan kinerja FPA. FPA disimulasikan untuk mengoptimalkan lima fungsi uji dan dibandingkan dengan FA standar dan variasi FA lainnya yaitu Wise Step Strategy for Firefly Algorithm (WSSFA) dan Firefly Algorithm with Random attraction (RaFA). Hasil simulasi tiga dari lima fungsi uji menunjukkan bahwa FPA berhasil mengungguli FA, WSSFA, dan RaFA.
English Abstract
Firefly Algorithm (FA) is one of optimization algorithms inspired by the flashing behavior of fireflies. The firefly algorithm has several disadvantages such as being trapped into several local optimum, the FA parameters are fixed without changes during iterations, and does not remember the history of each situation in each iteration. Firefly Photinus search Algorithm (FPA) was a new variation of the Firefly Algorithm (FA) who goals to overcome the trapping of solutions in some local optimum and remember the history of each iteration during the search process by developing light arbsorption reduction coefficient and mate list. In this paper, a new parameter was proposed that was a random step reduction coefficient to maximize FPA performance. FPA was simulated to optimize five test functions and compared with FA standard and other FA variations namely Wise Step Strategy for Firefly Algorithm (WSSFA) and Firefly Algorithm with Random attraction (RaFA). The simulation results of three of the five test functions indicate that FPA successfully outperformed the FA, WSSFA and RaFA.
Other obstract
-
| Item Type: | Thesis (Sarjana) |
|---|---|
| Identification Number: | SKR/MIPA/2019/194/051910918 |
| Uncontrolled Keywords: | FPA, daftar pasangan, koefisien reduksi absorpsi cahaya, koefisien reduksi langkah acak. FPA, mate list, light absorption reduction coefficient, random step reduction coefficient. |
| Subjects: | 500 Natural sciences and mathematics > 518 Numerical analysis > 518.1 Algorithms |
| Divisions: | Fakultas Matematika dan Ilmu Pengetahuan Alam > Matematika |
| Depositing User: | Budi Wahyono Wahyono |
| Date Deposited: | 05 Aug 2020 08:03 |
| Last Modified: | 05 Aug 2020 08:03 |
| URI: | http://repository.ub.ac.id/id/eprint/178747 |
Actions (login required)
 |
View Item |