Outage Analysis of a University Campus Network

Statistical characteristics of serious network failures in Japan

“…That is, this paper does not discuss statistical characteristics of all possible network failures but focuses on those of serious network failures. This is different from the previous researches on the characteristics of network failures that discussed the analysis of all possible network failures [4][5][6][7][8][9][10]. However, despite the limitations of this paper, due to the novelty of the raw data analyzed, we can expect the analysis results to provide good information for understanding the statistical characteristics of network failures.…”

“…Matz et al derived estimates of mean time to failure and mean time to recover/repair for both hardware and software in a cellular network based on six months of manually recorded failure data [9]. Choi et al carried out an in-depth failure analysis of an access network of the University of Missouri, Kansas City (UMKC) using network data of both node and link failure recorded from April 2005 to March 2007 [10]. They investigated spatial and temporal localities of failures, the relation of link failure and node failure, and the impact of the hierarchical and redundant network design on failure.…”

Understanding the health of an access network

“…The network is designed hierarchically with core, distribution, and access layers, and many link redundancies are added for reliability. This paper extends an earlier work [8] with additional analysis and with more extensive data of longer duration, including the attributes of hardware/software and configurational problems and the characteristics between the non-access layer and the access layer of the hierarchically designed network. We investigate particularly the aspects of i) the attributes of hardware/software and misconfiguration problems; ii) the impact and relation of link failure to node outage; iii) the correlations between access/non-access networks; iv) the impact of the hierarchical and redundant network architecture on outage.…”

Improving Convergence Speed and Scalability in OSPF: A Survey

“…Similarly, an OS reboot in a router would affect just that router but a power outage in a point-of-presence (PoP) may bring down all the routers located there. Sometimes, faulty hardware/software may result in flapping behavior, where one or more links in a router exhibit intermittent failures for extended time periods, resulting in a severe impact on the data traffic [12], [13].…”