Significant Sampling for Shortest Path Routing: A Deep Reinforcement Learning Solution
Name
JSAC_2019.pdf
Description
Accepted version
Size
1.26 MB
Format
Adobe PDF
Checksum (MD5)
336a9f441d93ee355466a1938b70953d
Author(s)
Shao, Yulin
Rezaee, Arman
Liew, Soung Chang
Chan, Vincent W. S.
Date Issued
June 2020
Journal
IEEE Journal on Selected Areas in Communications
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Shao, Yulin et al. "Significant Sampling for Shortest Path Routing: A Deep Reinforcement Learning Solution." IEEE Journal on Selected Areas in Communications 38, 10 (October 2020): 2234 - 2248. © 2020 IEEE
Version
Author's final manuscript
Abstract
Significant sampling is an adaptive monitoring technique proposed for highly dynamic networks with centralized network management and control systems. The essential spirit of significant sampling is to collect and disseminate network state information when it is of significant value to the optimal operation of the network, and in particular when it helps identify the shortest routes. Discovering the optimal sampling policy that specifies the optimal sampling frequency is referred to as the significant sampling problem. Modeling the problem as a Markov Decision process, this paper puts forth a deep reinforcement learning (DRL) approach to tackle the significant sampling problem. This approach is more flexible and general than prior approaches as it can accommodate a diverse set of network environments. Experimental results show that, 1) by following the objectives set in the prior work, our DRL approach can achieve performance comparable to their analytically derived policy $\phi '$ - unlike the prior approach, our approach is model-free and unaware of the underlying traffic model; 2) by appropriately modifying the objective functions, we obtain a new policy which addresses the never-sample problem of policy $\phi '$ , consequently reducing the overall cost; 3) our DRL approach works well under different stochastic variations of the network environment - it can provide good solutions under complex network environments where analytically tractable solutions are not feasible.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/jsac.2020.3000364
