A Bandit Approach to Price-Aware Energy Management in Cellular Networks

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)
189 Downloads (Pure)


We introduce a reinforcement learning algorithm inspired by the combinatorial multi-armed bandit problem to minimize the time-averaged energy cost at individual base stations (BSs), powered by various energy markets and local renewable energy sources, over a finite-time horizon. The algorithm sustains traffic demands by enabling sparse beamforming to schedule dynamic user-to-BS allocation and proactive energy provisioning at BSs to make ahead-of-time price-aware energy management decisions. Simulation results indicate a superior performance of the proposed algorithm in reducing the overall energy cost, as compared with recently proposed cooperative energy management designs.

Original languageEnglish
Article number7887725
Pages (from-to)1609-1612
Number of pages4
Issue number7
Early online date27 Mar 2017
Publication statusPublished - 1 Jul 2017


  • CMAB
  • Energy management
  • online learning


Dive into the research topics of 'A Bandit Approach to Price-Aware Energy Management in Cellular Networks'. Together they form a unique fingerprint.

Cite this