Dynamic node scheduling method based on DQN algorithm in wireless body area network
A wireless body area network and scheduling method technology, which is applied in the field of dynamic node scheduling, can solve problems such as large system delay or energy consumption, cannot meet system service quality requirements, etc., and achieve the effect of improving energy efficiency
Active Publication Date: 2020-07-28
NANJING UNIV OF SCI & TECH
View PDF1 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Existing schemes such as the optimal channel transmission method and polling transmission method only consider the scheduling index when scheduling nodes, which cannot meet all system service quality requirements and may lead to large system delays or energy consumption
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
[0043] In one embodiment, combined with figure 1 A method for dynamic node scheduling based on a DQN algorithm in a wireless body area network is provided, the method comprising the following steps:
[0044] Step 1, build the network architecture of the wireless body area network, and initialize the network parameters;
[0045] Step 2, construct the Markov channel model between nodes, and determine the model parameters;
[0046] Step 3, transforming the node scheduling problem into a Markov decision problem, and determining the parameters of the Markov decision problem model;
[0047] Step 4, using the DQN algorithm to train the Markov decision problem model to obtain a decision network;
[0048] Step 5, using the decision network to perform dynamic node scheduling in the wireless body area network system.
[0049] Further, in one of the embodiments, the network architecture of the wireless body area network in step 1 includes N sensor nodes and 1 coordinator, and its paramet...
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 discloses a dynamic node scheduling method based on a DQN algorithm in a wireless body area network. The method comprises the following steps: establishing a network architecture of a wireless body area network; establishing a Markov channel model between the nodes, performing data acquisition of wireless communication channel quality and calculating model parameters; converting a node scheduling problem into a Markov decision problem, and training by adopting a DQN algorithm based on deep reinforcement learning to obtain a convergent decision network; and carrying out node scheduling by using a decision network, wherein the node accessing the channel and the sending power of the node are determined at each moment according to the channel of the node and the data length of the cache region. On the basis of ensuring the reliability and fairness of wireless body area network data transmission, the energy efficiency of node scheduling is improved, the life cycle of the network is prolonged, and the method can be widely applied to body area network actual application scenes such as medical monitoring and disease prevention and control.
Description
technical field [0001] The invention belongs to the field of wireless communication networks, in particular to a dynamic node scheduling method based on a DQN algorithm in a wireless body area network. Background technique [0002] The wireless body area network originated from the wireless sensor network. The object of its observation is the human body itself. Communications network. The transmission of data in the network depends on the wireless channel established between the sensor nodes and the coordinator. The wireless body area network is composed of nodes that change with the movement posture of the human body. The mobility of the nodes will lead to dynamic changes in the quality of the network channel. Therefore, a reasonable scheduling method must be designed to ensure reliable data transmission. In addition, the nodes in the wireless body area network are usually powered by batteries. The battery capacity is limited by the size, and the energy is very limited. I...
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): H04W16/22H04W52/02H04W72/12H04W84/18
CPCH04W16/22H04W52/0216H04W84/18H04W72/54Y02D30/70
Inventor 王力立张戈林高尚张永
Owner NANJING UNIV OF SCI & TECH