摘要:
隨著通信網(wǎng)絡(luò)自身規(guī)模、帶寬和復(fù)雜度的不斷增加以及用戶對網(wǎng)絡(luò)服務(wù)質(zhì)量要求的不斷提高,迫切需要智能化的網(wǎng)絡(luò)管理系統(tǒng)對當(dāng)今高速通信網(wǎng)絡(luò)進(jìn)行有效和可靠的管理,而故障管理正在變的比以往任何時(shí)候都更加困難和重要。當(dāng)網(wǎng)絡(luò)產(chǎn)生某一故障或失效時(shí),往往在短時(shí)間內(nèi)產(chǎn)生成千上萬個(gè)告警信息,因而分析這些告警的相關(guān)性也變得更加復(fù)雜?，F(xiàn)有的一些告警分析系統(tǒng)均在不同程度上存在可擴(kuò)充能力差,難于應(yīng)付復(fù)雜局面,缺乏學(xué)習(xí)能力等不足。本文提出了一種基于改進(jìn)遺傳神經(jīng)網(wǎng)絡(luò)模型的故障識別和告警相關(guān)性分析方法。實(shí)驗(yàn)表明,這種方法可克服一般告警相關(guān)性分析方法的局限,不僅簡單,而且在網(wǎng)絡(luò)學(xué)習(xí)和訓(xùn)練效率上也高于傳統(tǒng)的BP算法,標(biāo)準(zhǔn)遺傳算法和一般的自適應(yīng)遺傳算法。
Abstract:
As a result of the rising demand for services and the resulting increase in size,bandwidth and complexity,fault management in todays high speed communication networks is becoming even more difficult.When a network problem or failure occurs,it is possible that a very large volume of alarm messages is generated,while alarm correlation is a potentially complex problem.Though some existing alarm correlation systems nowadays have different drawbacks such as lack of scalability,hindered by solving complexity,or no learning process,etc.This paper presents a fault-identification and alarm-correlation method based on improved GA-NN model in communication networks.The experimental results show that this method is simple,which not only overcomes the disadvantages of normal alarm correlation ways,but also improves the dynamic character,training accuracy and efficiency greatly than BP algorithm,BGA algorithm and AGA algorithm do.
下載:
