Policy network assisted Monte Carlo Tree search for intelligent service function chain deployment
Fu, Z; Fan, Q; Zhang, X; et al.Li, X; Wang, S; Wang, Y
Date: 9 March 2022
Institute of Electrical and Electronics Engineers (IEEE)
Network function virtualization (NFV) simplifies the configuration and management of security services by migrating the network security functions from dedicated hardware devices to software middle-boxes that run on commodity servers. Under the paradigm of NFV, the service function chain (SFC) consisting of a series of ordered ...
Network function virtualization (NFV) simplifies the configuration and management of security services by migrating the network security functions from dedicated hardware devices to software middle-boxes that run on commodity servers. Under the paradigm of NFV, the service function chain (SFC) consisting of a series of ordered virtual network security functions is becoming a mainstream form to carry network security services. Allocating the underlying physical network resources to the demands of SFCs under given constraints over time is known as the SFC deployment problem. It is a crucial issue for infrastructure providers. However, SFC deployment is facing new challenges in trading off between pursuing the objective of high revenue-to-cost ratio and making decisions in an online manner. In this paper, we investigate the use of reinforcement learning to guide online deployment decisions for SFC requests and propose a Policy network Assisted Monte Carlo Tree search approach named PACT to address the above challenge, aiming to maximize the average revenue-to-cost ratio. PACT combines the strengths of the policy network, which evaluates the placement potential of physical servers and the Monte Carlo Tree Search, which is able to tackle problems with large state spaces. Extensive experimental results demonstrate that our PACT achieves the best performance and superior to other algorithms by up to 30% and 23.8% on average revenue-to-cost ratio and acceptance rate, respectively
College of Engineering, Mathematics and Physical Sciences
Item views 0
Full item downloads 0
Showing items related by title, author, creator and subject.
The Effects of Acutely Administered 3,4-Methylenedioxymethamphetamine on Spontaneous Brain Function in Healthy Volunteers Measured with Arterial Spin Labeling and Blood Oxygen Level-Dependent Resting State Functional Connectivity Carhart-Harris, RL; Murphy, K; Leech, R; et al. (Elsevier for Society of Biological Psychiatry, 10 January 2014)BACKGROUND: The compound 3,4-methylenedioxymethamphetamine (MDMA) is a potent monoamine releaser that produces an acute euphoria in most individuals. METHODS: In a double-blind, placebo-controlled, balanced-order study, ...
An alternative approach to transfer functions? Testing the performance of a functional trait-based model for testate amoebae van Bellen, S; Mauquoy, D; Payne, RJ; et al. (Elsevier, 12 December 2016)Transfer functions are now widely available to infer past environmental conditions from biotic assemblages. Existing transfer functions are based on species assemblages but an alternative is to characterize assemblages ...
Bueno De Andrade, J (Cambridge University Press (CUP) for Royal Society of Edinburgh, 27 December 2018)In this series of papers, we explore moments of derivatives of L-functions in function fields using classical analytic techniques such as character sums and approximate functional equation. The present paper is concerned ...