A Greener Meta-Heuristics Scheduling Algorithm With Energized Optimization Dynamics by Deeper Intelligence Fusion

Abstract

As is known to all, the heterogeneous green scheduling objects have the intelligent feedback related to the efficiencies corresponding to the schemes, which has been largely ignored in most existing studies. That is why the existing optimization dynamics in green meta-heuristics scheduling algorithms, generally appear underpowered and vulnerable in the face of the rapid extension from homogeneity to heterogeneity of scheduling objects. Then, with respecting and ingeniously leveraging hardware (i.e., heterogeneous scheduling objects) intelligence, an efficient meta-heuristics algorithm with re-energized majorization dynamics for heterogeneous greener scheduling (i.e., CAr_FI(HS)), is proposed. The experimental results show that compared with the other meta-heuristics scheduling algorithms, CAr_FI(HS) has obvious advantages in the overall performance and the solution quality, for both data intensive and computing intensive instances.

Keywords

• Greener
• energized optimization dynamics
• fusion intelligence
• meta-heuristics algorithm
• nonlinear heterogeneous scheduling