Mobile traffic forecasting for maximizing 5G network slicing resource utilization

TLDR

The emerging network slicing paradigm for 5G offers new business opportunities but introduces technical challenges that require novel resource allocation algorithms and admission control policies to meet diverse service level agreements. This paper aims to design three key network‑slicing building blocks. The blocks perform traffic analysis and prediction per slice, make admission‑control decisions for slice requests, and adaptively correct forecasted load based on measured deviations. Results demonstrate substantial gains in system utilization and reveal a trade‑off between conservative forecasting configurations and more aggressive ones, which yield higher gains at the cost of increased SLA risk.

Abstract

The emerging network slicing paradigm for 5G provides new business opportunities by enabling multi-tenancy support. At the same time, new technical challenges are introduced, as novel resource allocation algorithms are required to accommodate different business models. In particular, infrastructure providers need to implement radically new admission control policies to decide on network slices requests depending on their Service Level Agreements (SLA). When implementing such admission control policies, infrastructure providers may apply forecasting techniques in order to adjust the allocated slice resources so as to optimize the network utilization while meeting network slices' SLAs. This paper focuses on the design of three key network slicing building blocks responsible for (i) traffic analysis and prediction per network slice, (ii) admission control decisions for network slice requests, and (iii) adaptive correction of the forecasted load based on measured deviations. Our results show very substantial potential gains in terms of system utilization as well as a trade-off between conservative forecasting configurations versus more aggressive ones (higher gains, SLA risk).