基于改進(jìn)的量子粒子群優(yōu)化小波神經(jīng)網(wǎng)絡(luò)的網(wǎng)絡(luò)流量預(yù)測
發(fā)布時間：2018-07-29 11:22
【摘要】：為了改善小波神經(jīng)網(wǎng)絡(luò)(WNN)進(jìn)行流量預(yù)測的性能及避免量子粒子群算法(QPSO)搜索后期的早熟收斂缺陷,提出了一種改進(jìn)的QPSO。該算法定義粒子群聚攏度,改進(jìn)收縮—擴(kuò)張系數(shù)使其表示為聚攏度的函數(shù)并服從隨機(jī)分布,以使粒子群具有動態(tài)自適應(yīng)性,避免陷入局部最優(yōu),并通過搜索使用WNN待優(yōu)化參數(shù)編碼位置向量的粒子群的全局最優(yōu)位置來實(shí)現(xiàn)目標(biāo)參數(shù)的優(yōu)化,使用本算法優(yōu)化WNN參數(shù),建立了基于改進(jìn)的QPSO優(yōu)化WNN的網(wǎng)絡(luò)流量預(yù)測模型。使用真實(shí)網(wǎng)絡(luò)流量通過兩組對比實(shí)驗(yàn)對其預(yù)測精度進(jìn)行驗(yàn)證,證明了該方法的可用性。實(shí)驗(yàn)結(jié)果表明,該方法的預(yù)測精度優(yōu)于WNN和QPSO-WNN方法。
[Abstract]:In order to improve the performance of wavelet neural network (WNN) in traffic prediction and to avoid the premature convergence defects of quantum particle swarm optimization (QPSO) algorithm, an improved QPSO is proposed. The algorithm defines particle swarm cohesion, improves the shrinkage and expansion coefficient to express it as a function of cohesion and obeys random distribution, so that particle swarm has dynamic adaptability and avoids falling into local optimum. The optimization of target parameters is realized by searching the global optimal position of particle swarm optimization (PSO) which encodes position vector with WNN parameters. Using this algorithm to optimize WNN parameters, a network traffic prediction model based on improved QPSO optimization WNN is established. The accuracy of the proposed method is verified by two sets of comparative experiments, and the availability of the method is proved. Experimental results show that the prediction accuracy of this method is better than that of WNN and QPSO-WNN methods.
【作者單位】： 國家數(shù)字交換系統(tǒng)工程技術(shù)研究中心;
【基金】：國家“973”計劃資助項目(2012CB315901,2013CB329104) 國家自然科學(xué)基金資助項目(61372121) 國家“863”計劃資助項目(2013AA013505)
【分類號】：TP183;TP393.06
[Abstract]:In order to improve the performance of wavelet neural network (WNN) in traffic prediction and to avoid the premature convergence defects of quantum particle swarm optimization (QPSO) algorithm, an improved QPSO is proposed. The algorithm defines particle swarm cohesion, improves the shrinkage and expansion coefficient to express it as a function of cohesion and obeys random distribution, so that particle swarm has dynamic adaptability and avoids falling into local optimum. The optimization of target parameters is realized by searching the global optimal position of particle swarm optimization (PSO) which encodes position vector with WNN parameters. Using this algorithm to optimize WNN parameters, a network traffic prediction model based on improved QPSO optimization WNN is established. The accuracy of the proposed method is verified by two sets of comparative experiments, and the availability of the method is proved. Experimental results show that the prediction accuracy of this method is better than that of WNN and QPSO-WNN methods.
【作者單位】： 國家數(shù)字交換系統(tǒng)工程技術(shù)研究中心;
【基金】：國家“973”計劃資助項目(2012CB315901,2013CB329104) 國家自然科學(xué)基金資助項目(61372121) 國家“863”計劃資助項目(2013AA013505)
【分類號】：TP183;TP393.06
【參考文獻(xiàn)】
相關(guān)期刊論文 前4條
1 任崇嶺;曹成鉉;李靜;史文雯;;基于小波神經(jīng)網(wǎng)絡(luò)的短時客流量預(yù)測研究[J];科學(xué)技術(shù)與工程;2011年21期
2 方偉;孫俊;謝振平;須文波;;量子粒子群優(yōu)化算法的收斂性分析及控制參數(shù)研究[J];物理學(xué)報;2010年06期
3 金旗,裴昌幸,朱暢華;ARIMA模型法分析網(wǎng)絡(luò)流量[J];西安電子科技大學(xué)學(xué)報;2003年01期
4 潘玉民;張曉宇;張全柱;薛鵬騫;;基于量子粒子群優(yōu)化的小波神經(jīng)網(wǎng)絡(luò)預(yù)測模型[J];信息與控制;2012年06期
【共引文獻(xiàn)】
相關(guān)期刊論文 前10條
1 張朝龍;江巨浪;李彥梅;陳世軍;gだ，
本文編號：2152524
本文鏈接：http://sikaile.net/guanlilunwen/ydhl/2152524.html
最近更新
教材專著
