On the Use of Q-Learning to Solve the Selectable Virtual Network Embedding Problem
Sen Wang, Biao Zhang · 2018
The problem of embedding Virtual Networks (VN) in a Substrate Network (SN) is the main resource allocation challenge in network virtualization. In this paper, we try to solve the Selectable Virtual Network Embedding (SVNE) problem where the Infrastructure Provider (InP) can decide whether to accept an incoming Virtual Network Request (VNR) to increase its revenue and decrease Block Ratio. We argue that the major challenge of the SVNE problem lies in the contradiction between making online embedding decisions and pursuing a long-term objective. Therefore, we propose an SVNE algorithm based on Q-learning.