Opportunistic routing protocol based on Markov decision process model
A routing protocol and process model technology, applied in the field of machine learning, can solve the problems of poor performance of routing protocols, prolong network life cycle, unable to achieve global optimal solution, etc., and achieve the effect of good convergence and efficient algorithm
Active Publication Date: 2020-09-04
NANJING UNIV OF SCI & TECH
View PDF1 Cites 6 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005]
The purpose of the present invention is to provide a chance routing protocol based on the Markov decision process model to solve the problem in the prior art that relies on node position information and cannot achieve a global optimal solution, resulting in poor performance of the routing protocol; The Markov decision process of reinforcement learning realizes the design of opportunistic routing protocols, optimizes and balances the energy usage of wireless sensor networks, and achieves the purpose of prolonging the network life cycle
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
[0025] The present invention will be further introduced below in conjunction with the accompanying drawings and specific embodiments.
[0026] The present invention proposes an opportunistic routing protocol based on the Markov decision process model, which utilizes reinforcement learning to find the energy optimal forwarding path, and the specific steps are as follows:
[0027] Step 1. Evaluate the quality of the environmental link, and give the evaluation method of the packet receiving rate:
[0028] Select a certain area as the data collection area, use two sensor nodes in this area to carry out multiple communication experiments at different communication distances, collect the packet reception rate data under the same RSSI value, and the LQI average value and packet reception rate at different communication distances. rate data to establish a sample space. When the link communication quality is good, the RSSI value has the best correlation with the packet receiving rate,...
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 an opportunistic routing protocol based on a Markov decision process model. The method comprises the following steps: firstly, evaluating the environment link quality and evaluating the packet receiving rate: collecting packet receiving rate data under the same RSSI value and LQI mean values and packet receiving rate data under different communication distances to establisha sample space, and performing curve family regression fitting on the LQI mean values and the packet receiving rate data to obtain an estimation formula of the packet receiving rate; spreading wireless sensor nodes, and establishing a wireless sensor network; periodically broadcasting and receiving a detection packet by the sensor nodes, and establishing a neighbor information table; the sensor nodes establishing a candidate node set; and the node where the effective data packet is located broadcasting the data packet, the candidate node receiving the data packet recalculating the state valuecorresponding to the node according to a value iterative formula, and a data packet sender selecting the node with the maximum state value corresponding to the return as a next-hop forwarding node. According to the invention, the energy use of a wireless sensor network is optimized and balanced.
Description
technical field [0001] The invention belongs to the technical field of machine learning, in particular to a chance routing protocol based on a Markov decision process model. Background technique [0002] Wireless sensor network is a network composed of many sensor nodes in a multi-hop self-organizing manner, and its application prospects are very broad. In a large amount of research work on wireless sensor networks, the research on routing protocols has always been the key content, and reasonable routing design can effectively improve network performance. Since sensor nodes are mostly scattered randomly in uninhabited areas, it is difficult to replace batteries. How to save node energy consumption and balance the use of network energy has become an inevitable problem. [0003] Traditional wireless sensor network routing protocols select one or more optimized fixed paths before data transmission starts, and data packets are transmitted along the preset fixed paths. Differen...
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 IPC IPC(8): H04W40/10H04W40/12H04W4/38
CPCH04W40/10H04W40/12H04W4/38Y02D30/70
Inventor 黄成尹政刘子淇刘振光姚文杰徐志良王力立
Owner NANJING UNIV OF SCI & TECH