.png){kind=icon}
Return
A many-objective evolutionary algorithm based on constraints for collaborative computation offloading
.png){kind=icon}
PRE
AI
DOI：10.1016/j.swevo.2023.101244.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper designs a many-objective optimized edge and terminal collaborative computation offloading (MaOETCCO) model to give full play to the performance advantages of collaboration and resource sharing be-tween edge server (ES) and intelligent terminal equipment (ITE) for computation offloading, which considers three offloading levels and four objectives: offloading delay minimization, application execution time minimi-zation, energy consumption minimization, and most efficient load balancing. At the same time, a many-objective evolutionary algorithm with load constraints (MaOEA-LC) is designed to solve the model by obtaining Pareto optimal solutions. It consists of a two-layer tournament mating selection based on load constraints, an envi-ronment selection method based on objective value domination, and an evolutionary method of double popu-lation crossover and multipoint mutation. In simulations, the values of the convergence performance evaluation index GD and diversity performance evaluation index Spa are the best in the comparison with other evolutionary algorithms. With optimization of MaOEA-LC, the MaOETCCO model is solved faster with more diverse solutions, and the objective values in the model have been optimized by 31%, 8%, 16%, and 30%, respectively. In addition, the rank value and adjusted p-value of the Friedman statistical test are used to prove the significant advantage of MaOEA-LC.
Keywords:
Load balancing
Many-objective evolutionary algorithm
Collaborative computation offloading
Edge computing
Journal
IF:
8.5
Papers:
2.2K
Citations:
1.0W
Organization
Cited Papers
Multiobjective economic-environmental power dispatch with stochastic wind-solar-small hydro power.png)
ENERGY
OAAI
ENERGYIF9.4
OAAIShareSaveShareSaveDecomposition based multi-objective evolutionary algorithm for windfarm layout optimizationRENEWABLE ENERGY
RENEWABLE ENERGYIF9.1
PREAI
ShareSaveShareSave
View more