상이한 네트워크 서비스 어떻게 향상시킬까?

Besieged by needs for upgrading the current Internet, social pressures, and regulatory concerns, a network operator may be left with few options to improve his services. Yet he can still consider a transition prioritizing network services. In this paper, we describe a transition from a non-priority system to a prioritized one, using non-preemptive M/G/1 model. After reviewing the constraints and theoretical results from past research, we describe steps making the transition Pareto-improving, which boils down to a multi-goal search for a Pareto-improving state. We use a genetic algorithm that captures actual transition costs along with incentive-compatible and Pareto-improving constraints. Simulation results demonstrate that the initial post-transition solutions are typically Pareto-improving. For non Pareto-improving solutions, the heuristic quickly generates Pareto-improving and incentive-compatible solutions.