The integration of advanced technologies into telecommunication networks complicates troubleshooting, posing challenges for manual error identification in Packet Capture (PCAP) data. This manual approach, requiring substantial resources, becomes impractical at larger scales. Machine learning (ML) methods offer alternatives, but the scarcity of labeled data limits accuracy. In this study, we propose a self-supervised, large language model-based (LLMcap) method for PCAP failure detection. LLMcap leverages language-learning abilities and employs masked language modeling to learn grammar, context, and structure. Tested rigorously on various PCAPs, it demonstrates high accuracy despite the absence of labeled data during training, presenting a promising solution for efficient network analysis. Index Terms: Network troubleshooting, Packet Capture Analysis, Self-Supervised Learning, Large Language Model, Network Quality of Service, Network Performance.

Statistical inference involves estimation of parameters of a model based on observations. Building on the recently proposed Equilibrium Expectation approach and Persistent Contrastive Divergence, we derive a simple and fast Markov chain Monte Carlo algorithm for maximum likelihood estimation (MLE) of parameters of exponential family distributions. The algorithm has good scaling properties and is suitable for Monte Carlo inference on large network data with billions of tie variables. The performance of the algorithm is demonstrated on Markov random fields, conditional random fields, exponential random graph models and Boltzmann machines.

Complex network data may be analyzed by constructing statistical models that accurately reproduce structural properties that may be of theoretical relevance or empirical interest. In the context of the efficient fitting of models for large network data, we propose a very efficient algorithm for the maximum likelihood estimation (MLE) of the parameters of complex statistical models. The proposed algorithm is similar to the famous Metropolis algorithm but allows a Monte Carlo simulation to be performed while constraining the desired network properties. We demonstrate the algorithm in the context of exponential random graph models (ERGMs) - a family of statistical models for network data. Thus far, the lack of efficient computational methods has limited the empirical scope of ERGMs to relatively small networks with a few thousand nodes. The proposed approach allows a dramatic increase in the size of networks that may be analyzed using ERGMs. This is illustrated in an analysis of several biological networks and one social network with 104,103 nodes.