Robust Adaptive Modulation and Coding (AMC)Selection in LTE Systems using ReinforcementLearning

Antonino Masaracchia, Andrea Passarella, Antonino Masaracchia, Raffaele Bruno

    Risultato della ricerca: Otherpeer review

    17 Citazioni (Scopus)

    Abstract

    Adaptive Modulation and Coding (AMC) in LTE networks is commonly employed to improve system throughput by ensuring more reliable transmissions. Most of existing AMC methods select the modulation and coding scheme (MCS) usingpre-computed mappings between MCS indexes and channel quality indicator (CQI) feedbacks that are periodically sent by the receivers. However, the effectiveness of this approach heavily depends on the assumed channel model. In addition CQI feedback delays may cause throughput losses. In this paperwe design a new AMC scheme that exploits a reinforcement learning algorithm to adjust at run-time the MCS selection rules based on the knowledge of the effect of previous AMC decisions.The salient features of our proposed solution are: i) the lowdimensionalspace that the learner has to explore, and ii) the use of direct link throughput measurements to guide the decision process. Simulation results obtained using ns3 demonstrate the robustness of our AMC scheme that is capable of discovering the best MCS even if the CQI feedback provides a poor prediction of the channel performance.
    Lingua originaleEnglish
    Numero di pagine6
    Stato di pubblicazionePublished - 2014

    All Science Journal Classification (ASJC) codes

    • ???subjectarea.asjc.1700.1706???
    • ???subjectarea.asjc.2200.2208???
    • ???subjectarea.asjc.2600.2604???

    Fingerprint

    Entra nei temi di ricerca di 'Robust Adaptive Modulation and Coding (AMC)Selection in LTE Systems using ReinforcementLearning'. Insieme formano una fingerprint unica.

    Cita questo