【摘要】：無線傳感器網(wǎng)絡(luò)是由部署在監(jiān)控區(qū)域的傳感器節(jié)點(diǎn)采用多跳方式傳輸數(shù)據(jù)而構(gòu)成的自組織網(wǎng)絡(luò),已在諸多領(lǐng)域得到了廣泛應(yīng)用。由于傳感器節(jié)點(diǎn)采用低功耗功率進(jìn)行無線電通信,并且其所處環(huán)境惡劣、復(fù)雜多變,從而導(dǎo)致節(jié)點(diǎn)之間的通信鏈路不穩(wěn)定。若能及時(shí)感知鏈路質(zhì)量信息,為轉(zhuǎn)發(fā)數(shù)據(jù)提供路由參考,則能有效減少數(shù)據(jù)重傳次數(shù),提高網(wǎng)絡(luò)數(shù)據(jù)吞吐率。因此有效的鏈路質(zhì)量預(yù)測(cè)方法對(duì)于提高數(shù)據(jù)傳輸?shù)某晒β�、延長(zhǎng)網(wǎng)絡(luò)生存期非常重要。論文介紹了無線鏈路特性和現(xiàn)有的鏈路質(zhì)量預(yù)測(cè)方法,分析了鏈路質(zhì)量參數(shù)的定義和相關(guān)性。在此分析的基礎(chǔ)上,提出基于高斯過程回歸(Gaussian Process Regression,GPR)的鏈路質(zhì)量預(yù)測(cè)模型。物理層參數(shù)實(shí)時(shí)靈敏,而直接測(cè)量包接收率需要消耗的能量比較多,因此本文構(gòu)建物理層參數(shù)和包接收率之間的非線性映射關(guān)系。由于鏈路質(zhì)量參數(shù)之間存在信息冗余,會(huì)降低模型的訓(xùn)練速度,本文首先利用灰關(guān)聯(lián)分析方法分析鏈路質(zhì)量參數(shù)之間的灰關(guān)聯(lián)度,選取有效影響因子;再結(jié)合鏈路質(zhì)量時(shí)間序列特點(diǎn),選取合適的協(xié)方差函數(shù),構(gòu)建鏈路質(zhì)量預(yù)測(cè)模型。無線鏈路通信易受到所處空間環(huán)境、地理位置、無線信號(hào)的影響和干擾。論文研究對(duì)象為節(jié)點(diǎn)靜止的無線傳感器網(wǎng)絡(luò),選取大學(xué)校園樹林、教學(xué)樓實(shí)驗(yàn)室、圖書館廣場(chǎng)和公路四個(gè)場(chǎng)景部署實(shí)驗(yàn),收集處于不同方向和距離的多對(duì)節(jié)點(diǎn)之間的實(shí)驗(yàn)數(shù)據(jù)。論文分析了不同場(chǎng)景下各節(jié)點(diǎn)對(duì)之間的鏈路波動(dòng)情況以及不同鏈路質(zhì)量參數(shù)之間的灰關(guān)聯(lián)度,確定預(yù)測(cè)模型的輸入?yún)?shù)。論文選取兩種鏈路進(jìn)行實(shí)驗(yàn)分析和模型驗(yàn)證。實(shí)驗(yàn)結(jié)果表明,降維后的實(shí)驗(yàn)數(shù)據(jù)樣本依然涵蓋了鏈路質(zhì)量信息,沒有對(duì)預(yù)測(cè)準(zhǔn)確性造成影響;在兩種鏈路場(chǎng)景下,基于組合協(xié)方差函數(shù)形式的高斯過程回歸模型的預(yù)測(cè)性能強(qiáng)于基于單一協(xié)方差函數(shù)的模型;與基于支持向量回歸機(jī)的模型相比,本文提出的模型具有更好的預(yù)測(cè)精度。
[Abstract]:Wireless sensor network (WSN) is a self-organized network which is composed of sensor nodes deployed in monitoring area and transmits data in multi-hop mode. It has been widely used in many fields. The wireless communication of sensor nodes is based on low power consumption, and the environment is harsh and complex, which leads to the instability of communication links between the nodes. If we can perceive link quality information in time and provide routing reference for forwarding data, we can effectively reduce the number of data retransmissions and improve the throughput of network data. Therefore, effective link quality prediction method is very important to improve the success rate of data transmission and prolong the network lifetime. In this paper, the characteristics of wireless link and the existing link quality prediction methods are introduced, and the definition and correlation of link quality parameters are analyzed. Based on this analysis, a link quality prediction model based on Gao Si process regression (Gaussian Process) is proposed. The physical layer parameters are sensitive in real time, and the direct measurement of packet reception rate requires more energy consumption. Therefore, a nonlinear mapping relationship between physical layer parameters and packet reception rate is constructed in this paper. Because of the information redundancy among the link quality parameters, the training speed of the model will be reduced. Firstly, the grey correlation degree between link quality parameters is analyzed by using the grey correlation analysis method, and the effective influence factors are selected. According to the characteristics of link quality time series, a link quality prediction model is constructed by selecting appropriate covariance function. Wireless link communication is easily affected and interfered by the space environment, geographical location and wireless signal. The research object of this paper is wireless sensor network with static nodes. Four scene deployment experiments are selected, including university campus forest, teaching building laboratory, library square and highway, and the experimental data between multiple pairs of nodes in different directions and distances are collected. In this paper, the link fluctuation between each node pair in different scenarios and the grey correlation between different link quality parameters are analyzed, and the input parameters of the prediction model are determined. In this paper, two kinds of links are selected for experimental analysis and model verification. The experimental results show that the data samples after dimensionality reduction still cover the link quality information and have no effect on the prediction accuracy. The prediction performance of Gao Si process regression model based on combined covariance function is better than that based on single covariance function, and the proposed model has better prediction accuracy than the model based on support vector regression machine.
【學(xué)位授予單位】：南昌航空大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP212.9;TN929.5

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 黃庭培;李棟;張招亮;崔莉;;一種突發(fā)性鏈路感知的自適應(yīng)鏈路質(zhì)量估計(jì)方法[J];計(jì)算機(jī)研究與發(fā)展;2010年S2期

2 黃庭培;李棟;張招亮;崔莉;;突發(fā)性鏈路感知的自適應(yīng)鏈路質(zhì)量估計(jì)方法[J];通信學(xué)報(bào);2012年06期

3 徐佑軍,譚敦茂,朱建武,曹文熙;藍(lán)牙無線鏈路質(zhì)量的分析、測(cè)試與改善[J];計(jì)算機(jī)工程與應(yīng)用;2004年12期

4 王廣杰;曾鵬;肖金超;;面向工業(yè)無線傳感器網(wǎng)絡(luò)的鏈路質(zhì)量實(shí)時(shí)評(píng)估算法[J];小型微型計(jì)算機(jī)系統(tǒng);2012年05期

5 郭志強(qiáng);王沁;萬亞東;李默涵;;基于綜合性評(píng)估的無線鏈路質(zhì)量分類預(yù)測(cè)機(jī)制[J];計(jì)算機(jī)研究與發(fā)展;2013年06期

6 陸飛;樂曉波;向峗松;;基于無線網(wǎng)格網(wǎng)的鏈路質(zhì)量測(cè)量方案與路由尺度性能研究[J];計(jì)算機(jī)應(yīng)用;2007年11期

7 李慕峰;田宇;徐鴻飛;易平;;基于鏈路質(zhì)量的應(yīng)急無線傳感網(wǎng)絡(luò)路由算法研究[J];信息網(wǎng)絡(luò)安全;2014年05期

8 廖欣;;一種鏈路質(zhì)量知曉的多跳無線網(wǎng)絡(luò)路由度量[J];懷化學(xué)院學(xué)報(bào);2014年05期

9 蔣錕;汪蕓;;灰洞檢測(cè):基于鏈路質(zhì)量估計(jì)的看門狗算法[J];計(jì)算機(jī)與現(xiàn)代化;2014年02期

10 戴靠柱;王潛平;;無線傳感網(wǎng)絡(luò)中基于鏈路質(zhì)量的地理路由[J];計(jì)算機(jī)工程與設(shè)計(jì);2011年03期

相關(guān)會(huì)議論文 前2條

1 胡丁丁;;Link Quality Control功能分析與優(yōu)化[A];2012全國(guó)無線及移動(dòng)通信學(xué)術(shù)大會(huì)論文集（下）[C];2012年

2 李婷婷;毛玉明;于秦;;Ad Hoc網(wǎng)絡(luò)無線鏈路質(zhì)量評(píng)估算法研究[A];四川省通信學(xué)會(huì)2007年學(xué)術(shù)年會(huì)論文集[C];2007年

相關(guān)碩士學(xué)位論文 前10條

1 周安;無線傳感器網(wǎng)絡(luò)鏈路質(zhì)量估計(jì)方法研究及應(yīng)用[D];南京信息工程大學(xué);2015年

2 張海洋;WSN中障礙物感知的鏈路質(zhì)量估算方法研究[D];浙江工業(yè)大學(xué);2015年

3 胡剛;無線傳感網(wǎng)絡(luò)鏈路質(zhì)量評(píng)估參數(shù)優(yōu)選模型研究[D];南昌航空大學(xué);2015年

4 湯津;基于模糊支持向量回歸機(jī)的WSN鏈路質(zhì)量預(yù)測(cè)模型[D];南昌航空大學(xué);2015年

5 劉松;基于貝葉斯網(wǎng)絡(luò)的鏈路質(zhì)量預(yù)測(cè)機(jī)制研究[D];南昌航空大學(xué);2016年

6 谷小樂;基于云模型的無線傳感網(wǎng)絡(luò)鏈路質(zhì)量預(yù)測(cè)方法[D];南昌航空大學(xué);2016年

7 趙婷;水下傳感器網(wǎng)絡(luò)基于能量和鏈路質(zhì)量的路徑選擇研究[D];天津大學(xué);2014年

8 尚亞青;基于高斯過程回歸的鏈路質(zhì)量預(yù)測(cè)方法[D];南昌航空大學(xué);2017年

9 李越;基于深度信念網(wǎng)絡(luò)的WSNs鏈路質(zhì)量預(yù)測(cè)機(jī)制研究[D];南昌航空大學(xué);2017年

10 付逸斐;家庭無線場(chǎng)景下鏈路質(zhì)量評(píng)價(jià)與中繼機(jī)會(huì)判斷[D];華中科技大學(xué);2011年

，

本文編號(hào)：2147172