Distributed power control based on linear quadratic optimal controller for cognitive radio network

Zhang, Shuying; Zhao, Xiaohui

doi:10.1109/cc.2018.8438275

Cited by 9 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LQG (Linear Quadratic Gaussian) regulator: the stochastic distribution of the exogenous disturbance is assumed as the Gaussian while the transmit power constraints of CUs are not considered [6]. Q-learning: State and Action are built into a Q-table to store Q values which is hard to handle the case with highdimension data.…”

Section: Simulation Results and Analysismentioning

confidence: 99%

See 1 more Smart Citation

Power Control for Cognitive Users of Perception Layer in Complex Industrial CPS Based on DQN

Zhang

2021

IEEE Access

View full text Add to dashboard Cite

Wireless communication is a significant auxiliary technology of data transmission for industrial Cyber-Physical system (CPS). While for the complex industrial scenario of coal mine with long and narrow laneway, lifetime of wireless perception nodes is a potential and nonnegligible problem for safety production. In order to deal with this problem, a power control algorithm based on deep Q network (DQN) is adopted to train micro base station (MBS) by two steps so that the MBS can learn an optimal policy to help the cognitive users (CUs) communicate with a proper transmit power. Firstly, the selection range of transmit power for CUs is calculated by the lower bound of Signal-to-Interference plus-Noise Ratio (SINR) to guarantee the transmission condition of both users. Then, the power control problem is modeled as a Markov Decision Process (MDP) with unknown transition function, where the energy consumption is decreased by giving the upper bound of CUs' SINR or threshold of transmit power in formulation of reward. In modeled MDP, the system state, which collected by primary users (PUs) and fed back to MBS, is reduced dimension by method of principal component analysis and then treated as the input of DQN. After that, DQN is used to train a power control optimal policy by minimizing the loss function. Simulation results demonstrate that the proposed power control algorithm based on DQN has a good performance that the average transition step and energy utility are 3.56 and 1580h, which is better than the existing solutions.

show abstract

Section: Simulation Results and Analysismentioning

confidence: 99%

“…Generally, energy of the nodes is supplied by external wire or battery. For the transmit power of these battery-supplied nodes, it needs to be restricted to prolong the lifetime [6].…”

Section: Introductionmentioning

confidence: 99%