Tarver, ChanceTonnemacher, MatthewChandrasekhar, VikramChen, HaoNg, Boon LoongZhang, JianzhongCavallaro, Joseph R.Camp, Joseph2019-10-232019-10-232019Tarver, Chance, Tonnemacher, Matthew, Chandrasekhar, Vikram, et al.. "Enabling a “Use-or-Share” Framework for PAL–GAA Sharing in CBRS Networks via Reinforcement Learning." <i>IEEE Transactions on Cognitive Communications and Networking,</i> 5, no. 3 (2019) IEEE: 716-729. https://doi.org/10.1109/TCCN.2019.2929147.https://hdl.handle.net/1911/107498By implementing reinforcement learning-aided listen-before-talk (LBT) schemes over a citizens broadband radio service (CBRS) network, we increase the spatial reuse at secondary nodes while minimizing the interference footprint on higher-tier nodes. The federal communications commission encourages “use-or-share” policies in the CBRS band across the priority access license (PAL)-general authorized access (GAA) priority tiers by opportunistically allowing the lower-priority GAA nodes to access unused higher-priority PAL spectrum. However, there is currently no mechanism to enable this cross-tier spectrum sharing. In this paper, we propose and evaluate LBT schemes that allow opportunistic access to PAL spectrum. We find that by allowing LBT in a two carrier, two eNB scenario, we see upward of 50% user perceived throughput (UPT) gains for both eNBs. Furthermore, we examine the use of ${Q}$ -learning to adapt the energy-detection threshold (EDT), combating problematic topologies, such as hidden and exposed nodes. With merely a 4% reduction in primary node UPT, we see up to 350% gains in average secondary node UPT when adapting the EDT of opportunistically transmitting nodes.engThis is an author's peer-reviewed final manuscript, as accepted by the publisher. The published article is copyrighted by IEEE.Journal articlehttps://doi.org/10.1109/TCCN.2019.2929147