An official website of the United States government
Here’s how you know
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
Poster: Green Network Optimization with Multi-Agent Reinforcement Learning: Work in Progress
Published
Author(s)
Vladimir Marbukh
Abstract
This paper proposes a distributed Green Network Optimization (GNO) with Multi-Agent Reinforcement Learning (MARL). GNO-MARL combines: (a) Network Utility Maximization (NUM) based network management, given the capacity constraints, on a "fast" time scale, and (b) network dimensioning which balances the maximal network utility with the "carbon cost" of the transmissions on "slower" time scales. Inherent non-convexity of the GNO due to dominance of the idle power in network devices, including routers, makes exact solution of the GNO even by centralized algorithms for realistic size networks intractable. It is known that distributed algorithms may introduce additional to the duality gap loss in the performance due to oscillatory instability. We advocate that this additional loss may be significantly reduced or even eliminated with MARL. This possibility is based on properties of Lagrange multipliers and suggested by known results on reducing the corresponding additional loss in network performance.
Conference Dates
August 19-22, 2024
Conference Location
Copenhagen, DK
Conference Title
The 2024 IEEE International Conference on Cyber, Physical and Social Computing (CPSCom 2024)
Marbukh, V.
(2024),
Poster: Green Network Optimization with Multi-Agent Reinforcement Learning: Work in Progress, The 2024 IEEE International Conference on Cyber, Physical and Social Computing (CPSCom 2024), Copenhagen, DK
(Accessed December 10, 2024)