vix.ing · top · new · best · stats · spec

Reinforcement learning based sensing policy optimization for energy\n efficient cognitive radio networks

2011/06/09 by Jan Oksanen, Oksanen, Jan, Jarmo Lundén +3
Computer Science · Decision Sciences · Engineering · #Advanced Bandit Algorithms Research #Advanced MIMO Systems Optimization #Cognitive Radio Networks and Spectrum Sensing #Distributed Sensor Networks and Detection Algorithms #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.1106.1770

openalex publication_date 2011/06/09 · openalex created_date 2022/09/25 · openalex updated_date 2026/07/28

Abstract

This paper introduces a machine learning based collaborative multi-band\nspectrum sensing policy for cognitive radios. The proposed sensing policy\nguides secondary users to focus the search of unused radio spectrum to those\nfrequencies that persistently provide them high data rate. The proposed policy\nis based on machine learning, which makes it adaptive with the temporally and\nspatially varying radio spectrum. Furthermore, there is no need for dynamic\nmodeling of the primary activity since it is implicitly learned over time.\nEnergy efficiency is achieved by minimizing the number of assigned sensors per\neach subband under a constraint on miss detection probability. It is important\nto control the missed detections because they cause collisions with primary\ntransmissions and lead to retransmissions at both the primary and secondary\nuser. Simulations show that the proposed machine learning based sensing policy\nimproves the overall throughput of the secondary network and improves the\nenergy efficiency while controlling the miss detection probability.\n

Related