A Bayesian Argumentation Framework for Distributed Fault Diagnosis in Telecommunication Networks

Abstract

Traditionally, fault diagnosis in telecommunication network management is carried out by humans who use software support systems. The phenomenal growth in telecommunication networks has nonetheless triggered the interest in more autonomous approaches, capable of coping with emergent challenges such as the need to diagnose faults’ root causes under uncertainty in geographically-distributed environments, with restrictions on data privacy. In this paper, we present a framework for distributed fault diagnosis under uncertainty based on an argumentative framework for multi-agent systems. In our approach, agents collaborate to reach conclusions by arguing in unpredictable scenarios. The observations collected from the network are used to infer possible fault root causes using Bayesian networks as causal models for the diagnosis process. Hypotheses about those fault root causes are discussed by agents in an argumentative dialogue to achieve a reliable conclusion. During that dialogue, agents handle the uncertainty of the diagnosis process, taking care of keeping data privacy among them. The proposed approach is compared against existing alternatives using benchmark multi-domain datasets. Moreover, we include data collected from a previous fault diagnosis system running in a telecommunication network for one and a half years. Results show that the proposed approach is suitable for the motivational scenario.

Argumentation Frameworks – A Brief Review

“…It very important to determine the winner from several arguments that attacked between each other [42]. The Bayesian Argumentation Framework (BAF) gives a conflict resolution mechanism and the diagnosis of errors, depending on the argumentation system [45]. The Partial Argumentation System (PAF), extends Dung's argumentation system to represent ignorance concerning the attack relation and depends on the voting system to determine that issue [46].…”

“…In view of the three sorts of explanations, this system defines three types of statements: the first statement represents the set for certain data; the second statement represents the set for questionable data; the third statement represents the remaining one for proposing ends or explanations. The fundamental plan to the BAF gives a compromise component and the conclusion of blunders, contingent upon the argumentation framework [44,45].…”

Decision-Making under Uncertainty for the Deployment of Future Hyperconnected Networks: A Survey

“…However, as nodes are not connected, finding a path from one variable to another may be not feasible. In fact, there are several algorithms that create inferences to learn about Bayesian networks, which may be used to overcome uncertainty in decision-making processes, as in [ 76 , 77 , 78 , 79 , 80 ].…”

FLAM: Locating and Mitigating 5GC Network Failure with Knowledge Graphs in China Telecom’s Network

“…For example, the number of configurable parameters in a typical 5G node had increased to 2000 from 500 in a 2G node [4]. The complexity results in a high level of uncertainty for 5GC operations and maintenance (O&M), making the network vulnerable to significant risks in terms of reliability and stability [5], [6]. When a failure occurs in network nodes, O&M experts may fail to accurately locate the root cause and timely resolve the network failure resulting in bad influences such as network performance degradation, service interruptions, data loss, and higher operating costs.…”