Channel selection method based on Q learning
A channel selection and channel technology, applied in the field of channel selection based on Q-learning, to achieve the effect of maximizing the detection rate of spectrum resources, improving the energy efficiency of spectrum sensing, and prolonging the network life
Active Publication Date: 2020-06-26
CHONGQING UNIV OF POSTS & TELECOMM
View PDF4 Cites 6 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In view of this, the present invention provides a channel selection method based on Q learning to solve the problem of channel selection in spectrum sensing based on energy harvesting wireless cognitive sensor networks
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0036] The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
[0037] Aiming at the problem of sensor node spectrum sensing sequence selection in a dynamic environment, the invention proposes a channel selection method based on Q learning. Compared with the general channel selection method, it can effectively improve the energy efficiency of spectrum sensing, and can quickly select the spectrum sensing sequence through Q learning, and reduce the cost of spectrum scanning. The model of interaction process based on Q-learning algorithm and changing channel environment is as follows: figure 2 shown.
[0038] like figure 1 Shown, the channel selection method based on Q learning, the method includes the following steps:
[0039] S1: Set the channel state set and action set of the sensor node;
[0040] S2: Initialize the state and behavior Q value of the sensor node, so that the number of iterations k=1...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to a channel selection method based on Q learning, and belongs to the technical field of cognitive radio. The method comprises the following steps: S1, setting a channel state set and an action set of sensor nodes; s2, initializing a state and a behavior Q value of a node, and enabling the number of iterations k to be equal to 1; s3, randomly sensing a channel; and S4, judging the result of the induction channel. If the sensing channel is busy, the node collects energy from the surrounding radio signals, If the sensing channel is idle, the available time of the channel isestimated; s5, calculating a reward value after the action is executed, and selecting a next action; s6, updating a Q value function according to a formula; and S7, enabling k to be equal to k + 1, and repeatedly executing the steps S3 to S6 until the Q matrix is converged. According to the method, the SU can learn and adapt to the dynamic behavior of the channel, the channel with longer available time detected by unit energy consumption is selected through Q learning for preferential sensing, the spectrum resource detection rate is maximized, and the spectrum sensing energy efficiency is improved.
Description
technical field [0001] The invention belongs to the field of cognitive radio and relates to a channel selection method based on Q learning. Background technique [0002] Energy harvesting-based cognitive wireless sensor network (EH-CRSN) is a new type of network that introduces cognitive radio (CR) technology and energy harvesting (EH) technology into traditional WSN. The cognitive function of sensor nodes can opportunistically detect idle licensed spectrum and access it to improve spectrum utilization. But it also increases the energy consumption of nodes. Energy harvesting technology has increasingly attracted the attention of researchers. It absorbs energy from the surrounding environment and converts it into electrical energy. It is especially suitable for low-energy devices. It is not only green and pollution-free, but also can greatly extend the life of the system. At present, the wireless sensor network based on radio frequency energy harvesting is a more active res...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): H04B17/382H04W84/18
CPCH04W84/18H04B17/382Y02D30/70
Inventor 裴二荣刘珊易鑫鹿逊
Owner CHONGQING UNIV OF POSTS & TELECOMM