Evolutionary Optimization for Proactive and Dynamic Computing Resource Allocation in Open Radio Access Network
This work addresses resource allocation inefficiencies in O-RAN to save resources and reduce delays, though it appears incremental as it applies an existing metaheuristic to a reformulated problem.
The authors tackled computing resource allocation in Open Radio Access Networks by proposing a new problem formulation and an evolutionary algorithm, which demonstrated significant superiority over a baseline greedy algorithm in experiments on real-world and artificial datasets.
Intelligent techniques are urged to achieve automatic allocation of the computing resource in Open Radio Access Network (O-RAN), to save computing resource, increase utilization rate of them and decrease the delay. However, the existing problem formulation to solve this resource allocation problem is unsuitable as it defines the capacity utility of resource in an inappropriate way and tends to cause much delay. Moreover, the existing problem has only been attempted to be solved based on greedy search, which is not ideal as it could get stuck into local optima. Considering those, a new formulation that better describes the problem is proposed. In addition, as a well-known global search meta heuristic approach, an evolutionary algorithm (EA) is designed tailored for solving the new problem formulation, to find a resource allocation scheme to proactively and dynamically deploy the computing resource for processing upcoming traffic data. Experimental studies carried out on several real-world datasets and newly generated artificial datasets with more properties beyond the real-world datasets have demonstrated the significant superiority over a baseline greedy algorithm under different parameter settings. Moreover, experimental studies are taken to compare the proposed EA and two variants, to indicate the impact of different algorithm choices.