| dc.description.abstract | This Master’s thesis addresses the problem of resource allocation in Network Function
Virtualization (NFV) within the context of a smart city considering isolation. The
objective of the thesis is to minimize the long-term cost and maximize the revenue and
acceptance rate of the infrastructure provider. A resource allocation model is proposed,
utilizing a state-of-the-art proximal policy optimization (PPO) training algorithm, and
its performance is evaluated under decreasing available resources.
In this thesis, we first introduce the smart city and the basic NFV and reinforcement
learning (RL) concepts. Then we review the existing literature on resource allocation in
NFV. Further, we introduce our problem definition and solution as well as our proposed
NFV-compatible isolation levels.
The results we produce demonstrate that the proposed solution exhibits increased
performance overall compared to a leading heuristic algorithm called global resource
capacity (GRC), especially in terms of the long-term revenue-to-cost ratio (LTRCR) of
at the most 20%, and in terms of the 25x reduction in time spent allocating per slice
request (SR). | |
