Search Results

Now showing 1 - 4 of 4

Some of the metrics are blocked by your
consent settings
Improved Rerun Particle Swarm Optimization Algorithm with Harmony Search
(2019-04-10)
Phuchan, Wikrom
;
Kruatrachue, Boontee
;
Siriboon, Kritawan
One of the most crucial problem of the particle swarm optimization is that it can easily trap in local optima. There are some studies tried to resolve the drawback using the reset and mutation mechanism. Although it unraveled the problem well when the optimal position of benchmark function is at zeros in all dimensions. It cannot locate optima when the exact answer randomly shifted over the possible region. This study integrates Harmony Search (HS) to the rerun and reset mechanism to PSO. It performs well with selected benchmark functions, when the optimal position is randomly shifted in most of the test functions. Since it does not favor optimal point at zeroes when the optimal position is not shifted, the number of calls of the evaluation function is more than the other algorithms in some cases.
Some of the metrics are blocked by your
consent settings
Improving Multi-Swarm by Slightly Mutation Particle and GBEST of Stuck Swarm Along with Randomly Selecting GBEST of Other Swarm
(2018-08-21)
Chengkhuntod, Kanokporn
;
Kruatrachue, Boontee
;
Siriboon, Kritawan
This paper proposed another approach in handling trapping in local optimum problem of Particle Swarm Optimization (PSO) using multi-swarm. Since each swarm might trap in different local optimum, the trapped swarm restart with slightly mutation (15% of each particle attributes) along with swaying swarm by randomly use of other swarm GBEST position. In the case of all swarm trapping in the same location, the trap GBEST is also slightly mutate in the same way as particle position. This proposed technique is tested on a set of twenty-four benchmark test functions. The experimental results show that the proposed method is better than other comparing methods.
Some of the metrics are blocked by your
consent settings
Combine multi particle swarm in supporting trapping in local optima
(2018-08-13)
Poempool, Lukkana
;
Kruatrachue, Boontee
;
Siriboon, Kritawan
This paper proposed using multi swarm to lessen trapping in local optima problem of Particle Swarm Optimization (PSO). The use of multiple swarms can increase wider global search at the cost of decrease narrower local search. Hence, the use of multiple swarms alone can't solve the trapping problem. This paper extends the use of multi swarm by merging all the swarm into single group to enhanced local search when needed. This can increase the local search ability of multi swarm and increase the chance of the trapped swarm to move to other nearby local optima. The proposed method is compared to similarly comparable modified PSO and other similarly multi particle swarm without merging using 26 benchmark functions.
Some of the metrics are blocked by your
consent settings
Hybrid multi-swarm with Harmony Search algorithm
(2017-11-03)
Phuchan, Wikrom
;
Kruatrachue, Boontee
;
Siriboon, Kritawan
This paper proposed a new metaheuristic algorithm, Hybrid Multi-swarm with Harmony Search algorithm which combines two famous metaheuristics, particle swarm optimization (PSO) and Harmony Search algorithm (HS). The main advantage of PSO is its convergence speed while its main drawback is trapping in local optimum problem. To improve PSO performance, this research use HS to increase PSO diversity and extend its convergence point to a better local optimum. The proposed algorithm was compared with three related algorithms on the optimization benchmark functions. The experiment results show the proposed algorithm yields better fitness value solution.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results