Network Selection in Cognitive Heterogeneous Networks Using Stochastic Learning

Abstract

Abstract-Coexistence of multiple radio access technologies (RATs) is a promising paradigm to improve spectral efficiency. This letter presents a game-theoretic network selection scheme in a cognitive heterogeneous networking environment with timevarying channel availability. We formulate the network selection problem as a noncooperative game with secondary users (SUs) as the players, and show that the game is an ordinal potential game (OPG). A decentralized, stochastic learning-based algorithm is proposed where each SU's strategy progressively evolves toward the Nash equilibrium (NE) based on its own actionreward history, without the need to know actions in other SUs. The convergence properties of the proposed algorithm toward an NE point are theoretically and numerically verified. The proposed algorithm demonstrates good throughput and fairness performances in various network scenarios.

Heterogeneous coexistence between cognitive radio networks: a Markovian jump system method

“…Cheng et al [11] propose a jamming-based probing function that enhances the PU-detection ability and the fairness feature, and a decentralized MAC protocol by combing the probing function and previous CRN MAC protocols. Tseng et al [12] study the problem of self-organized network selection in heterogeneous networks with time-varying channel availability and unknown number of secondary users by an ordinal potential game, and propose a decentralized stochastic learning based algorithm to solve it. Cacciapuoti et al [13] design an optimal coexistence strategy that adaptively and autonomously selects the channel maximizing the expected throughput of multiple heterogeneous and independently-operated unlicensed networks.…”

“…On one hand, autonomous schemes are suitable for the case in which the coordination between coexisting H-CRNs is unavailable [10][11][12][13]. New coexistence protocols [10,11] or novel decision making algo-rithms [12,13] have been proposed to ensure fair channel access for coexisting H-CRNs. On the other hand, centralized schemes are appealing for the case in which a mediator system is available for coordinating the operations of coexisting H-CRNs.…”

Joint Optimization of Interference and Cost in Cognitive Radio Heterogeneous Network Using Fuzzy Logic Powered Ants

“…In CRHN, selection of a suitable network [3], keeping in view the price, interference, and capacity, is thus very important [4,5]. Authors in [6] considered a network selection problem as a noncooperative game in which SUs were considered as players that achieved equilibrium without cooperation. Markov decision process is proposed in [7] to maximize SUs throughput in a cognitive radio heterogeneous network.…”

Heterogeneous coexistence between cognitive radio networks over TV white space: a nonlinear control perspective

“…Due to the incompatible MAC mechanisms, autonomous schemes have to design new coexistence protocols [7,8] or devise novel decision-making algorithms [9,10] to ensure fair channel access for all the coexisting H-CRNs. However, autonomous schemes are always 'specific' solutions to solve the transmission confliction between two given H-CRNs, which prohibits their use in the scenario of heterogeneous coexistence.…”