Mobile Network Slicing under Demand Uncertainty: A Stochastic Programming Approach

Abstract

Constant temporospatial variations in the user demand complicate the end-to-end (E2E) network slice (NS) resource provisioning beyond the limits of the existing best-effort schemes that are only effective under accurate demand forecasts for all NSs. This paper proposes a practical two-time-scale resource allocation framework for E2E network slicing under demand uncertainty. At each macro-scale instance, we assume that only the spatial probability distribution of the NS demands is available. We formulate the NSs resource allocation problem as a stochastic mixed integer program (SMIP) with the objective of minimizing the total CN and RAN resource costs. At each microscale instance, given the exact NSs demand profiles known at operation time, a linear program is solved to jointly minimize the unsupported traffic and RAN cost. We verify the effectiveness of our resource allocation scheme through numerical experiments.