Energy-efficient Dynamic Resource Allocation for Network Functions in Softwarization based Networks

Abstract

Driven by an explosive increase in the number of users and data usage, energy consumption becomes a significant concern for information and communication technology industry. In softwarization based networks, energy-efficient Network Function (NF) resource allocation is imperative yet challenging for service provisioning. In this paper, we investigate dynamic NF resource allocation (NFRA) problem for service function chains (SFCs) with aim to minimize the long-term energy consumption, while guaranteeing the end-to-end delay requirements for the packets traversing the SFCs. We formulate the problem as an infinite horizon Markov Decision Process (MDP) problem and obtain the global optimal solution based on the value iteration algorithm which has high computational complexity. The global optimal solution serves as a performance upper bound due to its high computational complexity. To cater for efficient on-line NFRA decisions, we further design a suboptimal distributed value iteration based dynamic NF resource allocation (DDRA) algorithm. The numerical results based on real-world data traces demonstrate the proposed DDRA algorithm achieves a close-to-optimal performance and a significant performance improvement compared with two known NF resource allocation algorithms.