arXiv subjects

Mohammad Saiful Islam

Publications and source records attributed to Mohammad Saiful Islam.

7 recordsLinked to original sources

arXiv2026

ClouDens: Operational Context-Aware Anomaly Detection for Large-scale Cloud System Monitoring

With the rapid growth of cloud computing infrastructures in scale and complexity, network monitoring for Large-scale Cloud Systems (LCSs) has become increasingly challenging, requiring automated and reliable anomaly detection to maintain service availability. Modern LCSs continuously generate telemetry logs from distributed cloud services, producing high-dimensional multivariate time series that capture system operations. Detecting anomalies in this context is difficult due to extreme dimensionality, complex dependencies among distributed components, and severe sparsity from intermittently active services. Taking these challenges into account, we first conduct an empirical study on telemetry logs from the IBM Cloud Console platform, and then propose ClouDens, an anomaly detection framework tailored to LCS monitoring that leverages operational-context attributes encoded in the telemetry log schema to improve detection accuracy and early identification of anomalies. ClouDens partitions high-dimensional telemetry logs into domain-guided subsets, constructs a context-aware graph modeling operational service dependencies, and employs Spatio-Temporal Graph Neural Networks for forecasting-based anomaly detection. We evaluate ClouDens on the recently released IBM Cloud Telemetry Dataset and provide practical insights into designing reliable anomaly detection solutions for LCS monitoring. Results show ClouDens achieves higher NAB scores in count-based telemetry features, indicating more accurate, earlier anomaly detection with broader coverage than a GRU-based model. Our study further reveals that telemetry feature subsets, operational-context modeling, scoring strategies, and sparsity imputation all substantially influence detection performance, offering practical guidance for designing and fairly benchmarking anomaly detection approaches for LCS monitoring.

cs.NI↗

arXiv2026

Benchmarking Anomaly Detection Across Heterogeneous Cloud Telemetry Datasets

Anomaly detection is important for keeping cloud systems reliable and stable. Deep learning has improved time-series anomaly detection, but most models are evaluated on one dataset at a time. This raises questions about whether these models can handle different types of telemetry, especially in large-scale and high-dimensional environments. In this study, we evaluate four deep learning models, GRU, TCN, Transformer, and TSMixer. We also include Isolation Forest as a classical baseline. The models are tested across four telemetry datasets: the Numenta Anomaly Benchmark, Microsoft Cloud Monitoring dataset, Exathlon dataset, and IBM Console dataset. These datasets differ in structure, dimensionality, and labelling strategy. They include univariate time series, synthetic multivariate workloads, and real-world production telemetry with over 100,000 features. We use a unified training and evaluation pipeline across all datasets. The evaluation includes NAB-style metrics to capture early detection behaviour for datasets where anomalies persist over contiguous time intervals. This enables window-based scoring in settings where anomalies occur over contiguous time intervals, even when labels are recorded at the point level. The unified setup enables consistent analysis of model behaviour under shared scoring and calibration assumptions. Our results demonstrate that anomaly detection performance in cloud systems is governed not only by model architecture, but critically by calibration stability and feature-space geometry. By releasing our preprocessing pipelines, benchmark configuration, and evaluation artifacts, we aim to support reproducible and deployment-aware evaluation of anomaly detection systems for cloud environments.

cs.NI↗

arXiv2024

Anomaly Detection in Large-Scale Cloud Systems: An Industry Case and Dataset

As Large-Scale Cloud Systems (LCS) become increasingly complex, effective anomaly detection is critical for ensuring system reliability and performance. However, there is a shortage of large-scale, real-world datasets available for benchmarking anomaly detection methods. To address this gap, we introduce a new high-dimensional dataset from IBM Cloud, collected over 4.5 months from the IBM Cloud Console. This dataset comprises 39,365 rows and 117,448 columns of telemetry data. Additionally, we demonstrate the application of machine learning models for anomaly detection and discuss the key challenges faced in this process. This study and the accompanying dataset provide a resource for researchers and practitioners in cloud system monitoring. It facilitates more efficient testing of anomaly detection methods in real-world data, helping to advance the development of robust solutions to maintain the health and performance of large-scale cloud infrastructures.

cs.LG↗

arXiv2021

Anomaly Detection in a Large-scale Cloud Platform

Cloud computing is ubiquitous: more and more companies are moving the workloads into the Cloud. However, this rise in popularity challenges Cloud service providers, as they need to monitor the quality of their ever-growing offerings effectively. To address the challenge, we designed and implemented an automated monitoring system for the IBM Cloud Platform. This monitoring system utilizes deep learning neural networks to detect anomalies in near-real-time in multiple Platform components simultaneously. After running the system for a year, we observed that the proposed solution frees the DevOps team's time and human resources from manually monitoring thousands of Cloud components. Moreover, it increases customer satisfaction by reducing the risk of Cloud outages. In this paper, we share our solutions' architecture, implementation notes, and best practices that emerged while evolving the monitoring system. They can be leveraged by other researchers and practitioners to build anomaly detectors for complex systems.

cs.DC↗

arXiv2020

Anomaly Detection in Cloud Components

Cloud platforms, under the hood, consist of a complex inter-connected stack of hardware and software components. Each of these components can fail which may lead to an outage. Our goal is to improve the quality of Cloud services through early detection of such failures by analyzing resource utilization metrics. We tested Gated-Recurrent-Unit-based autoencoder with a likelihood function to detect anomalies in various multi-dimensional time series and achieved high performance.

cs.SE↗

arXiv2014

A Distributed Framework for Scalable Search over Encrypted Documents

Nowadays, huge amount of documents are increasingly transferred to the remote servers due to the appealing features of cloud computing. On the other hand, privacy and security of the sensitive information in untrusted cloud environment is a big concern. To alleviate such concerns, encryption of sensitive data before its transfer to the cloud has become an important risk mitigation option. Encrypted storage provides protection at the expense of a significant increase in the data management complexity. For effective management, it is critical to provide efficient selective document retrieval capability on the encrypted collection. In fact, considerable amount of searchable symmetric encryption schemes have been designed in the literature to achieve this task. However, with the emergence of big data everywhere, available approaches are insufficient to address some crucial real-world problems such as scalability. In this study, we focus on practical aspects of a secure keyword search mechanism over encrypted data on a real cloud infrastructure. First, we propose a provably secure distributed index along with a parallelizable retrieval technique that can easily scale to big data. Second, we integrate authorization into the search scheme to limit the information leakage in multi-user setting where users are allowed to access only particular documents. Third, we offer efficient updates on the distributed secure index. In addition, we conduct extensive empirical analysis on a real dataset to illustrate the efficiency of the proposed practical techniques.

cs.CR↗

arXiv2012

Effect of Packet Delay Variation on Video-Voice over DiffServ-MPLS in IPv4-IPv6 Networks

Over the last years, we have witnessed a rapid deployment of real-time applications on the Internet as well as many research works about Quality of Service (QoS), in particular IPv4 (Internet Protocol version 4). The inevitable exhaustion of the remaining IPv4 address pool has become progressively evident. As the evolution of Internet Protocol (IP) continues, the deployment of IPv6 QoS is underway. Today, there is limited experience in the deployment of QoS for IPv6 traffic in MPLS backbone networks in conjunction with DiffServ (Differentiated Services) support. DiffServ itself does not have the ability to control the traffic which has been taken for end-to-end path while a number of links of the path are congested. In contrast, MPLS Traffic Engineering (TE) is accomplished to control the traffic and can set up end-to-end routing path before data has been forwarded. From the evolution of IPv4 QoS solutions, we know that the integration of DiffServ and MPLS TE satisfies the guaranteed QoS requirement for real-time applications. This paper presents a QoS performance study of real-time applications such as voice and video conferencing in terms of Packet Delay Variation (PDV) over DiffServ with or without MPLS TE in IPv4/IPv6 networks using Optimized Network Engineering Tool (OPNET). We also study the interaction of Expedited Forwarding (EF), Assured Forwarding (AF) traffic aggregation, link congestion, as well as the effect of performance metric such as PDV. The effectiveness of DiffServ and MPLS TE integration in IPv4/IPv6 network is illustrated and analyzed. This paper shows that IPv6 experiences more PDV than their IPv4 counterparts.

cs.NI↗