Network Operations Center Research Articles

Unraveling the root causes of faults in mobile communications: A comparative analysis of different model explainability techniques

The escalating demand and complexity of monitoring services handled by Network Operations Centers (NOCs) have led Mobile Network Operators (MNOs) to prioritize automated solutions for network fault detection and diagnosis. Consequently, various Machine Learning (ML)-based Root Cause Analysis (RCA) systems have been developed, however their lack of explainability poses a challenge due to the predominantly black-box nature of ML models. This paper addresses this issue by presenting a supervised clustering methodology capable of integrating both glass-box and black-box models, the latter complemented by post-hoc explainability techniques. While black-box models excel in predictive capabilities, necessitating post-hoc techniques for explainability, glass-box models prioritize transparent decision-making, fostering a clearer understanding of the model’s behavior. This work delineates a methodology for performing RCA of faults in the User Downlink (DL) Average Throughput Key Performance Indicator (KPI), simultaneously comparing the performance of black-box models (Light Gradient-Boosting Machine (LightGBM) and Extreme Gradient Boosting (XGBoost)) with glass-box models (Logistic Regression (LR) and Explainable Boosting Machine (EBM)). Results revealed that the LightGBM black-box algorithm coupled with the SHapley Additive exPlanations (SHAP) method demonstrated superior performance in fault detection and diagnosis, without compromising the overall explainability. Consequently, it was possible to identify faults related to radio conditions, low network usage in specific user groups, low network capacity, and mobility issues. The paper concludes with practical mitigation strategies for each identified fault cluster.

Artificial Intelligence: Real Challenge or Boon for Network Operation Center and Network security

Artificial intelligence has emerged as a game-changer in every domain, and network operation center and network security are no exception. This paper critically evaluates the dual impact of AI as a daunting challenge and a blissful boon in the context of NOCs, network security, and their overlap. As firms increasingly rely on ever more sophisticated and complex networks to run their business, the need for effective network management and security has become a top priority. Correspondingly, controlling such complex networks, an analyzing their performance and status, and safeguarding them from rapidly evolving threats have grown more difficult than ever. AI-powered solutions have the potential to considerably improve NOC efficiency and effectiveness. Introduce automated automation of routine processes, facilitate network performance optimization, and help in forecasting of most network abnormalities. Consequently, these can drastically cut NOC operational costs and network uninsured losses and enhance network dependability. However, and exposure of AI technologies to an entire new category of challenges, such as the potential of AI-based cyberattacks, algorithmic discrimination, and the ethical insinuations of fully autonomous NOCs, also imply that many possible risks and risks are taking into account.

Testbed of an Integrated Network Operations Center and a Security Operations Center Based on Open-Source Tools

Testbed of an Integrated Network Operations Center and a Security Operations Center Based on Open-Source Tools

Over-threshold multi-party private set operation protocols for lightweight clients

The problem of private set operation (PSO) can realize the function of data set analysis on the premise of privacy protection, which has been widely concerned by researchers in academia and industry. Over-threshold multi-party private set operation (OT-MP-PSO) is a special class of PSO, where multiple parties hold their own private set respectively and want to securely compute which element appears in at least t private sets of all parties for an adjustable threshold t. In practical scenarios, this primitive has many applications, such as voting systems and network operations centers collaborating to identify common threats. However, in current studies, the computational costs of existing protocols are exponentially related to the threshold t thus the range of t is limited to keep the protocols efficient. In this paper, we designed an efficient OT-MP-PSO protocol in a dual cloud setting and the range of t is not limited. In addition, we also design a series of private set fine-grained computation protocols that combine threshold, such as the cardinality of the result set and the sum of the element labels that satisfy the threshold condition. Moreover, we give formal security proofs for the proposed protocols and validate the efficiency of our protocols through experiments. On small data sets, our protocol has very little computational and communication overhead. When the set size ranges from 101 to 103, the experimental results show that our protocol is significantly better than the state-of-the-art approach. Finally, we introduce a typical application of our protocols in the field of voting.

Workforce capacity planning for proactive troubleshooting in the Network Operations Center

Modern data centers require that a Network Operations Center is continuously monitoring network health, desirably in order to take proactive action before potential trouble occurs. In this paper, we contribute to the capacity planning of the workforce in charge. To this end, we have extensively analyzed, with real-world data, behavioral changes in a large server population in a data center. Our findings allow classifying such behavioral changes, which may be indicative of potential trouble, into relevance regions using a ranking mechanism. Then, the proposed methodology allows, together with an estimation of the time to analyze, assessing the workforce necessary to proactively tackle the behavioral changes observed. We conclude with a case study from a working data center, including a hands-on implementation of a traffic analysis solution to detect such behavioral changes and an estimation of the needed workforce to analyze them. Our results show that between 4 and 5 network managers are an adequate number for handling behavioral-changes analysis in a large enterprise data center.

Quality of Monitoring for Cellular Networks

5G networks and beyond introduce a larger number of Network Elements (NEs) and functions than former cellular generations. The increase in NEs will, thus, result in significantly increasing the Management-Plane (M-Plane) data collected from the NEs. Therefore, the conventional centralized Network Management Systems (NMSs) will face fundamental challenges in processing the M-Plane data. In this paper, we present the concept of Quality of Monitoring (QoM) as a solution, which is able to reduce the M-Plane data already at the NEs. First, QoM aggregates the raw M-Plane data into Key Performance Indicators (KPIs). To these KPIs, the QoM applies a data-driven algorithm to define information loss limits for QoM classes specific for each KPI time series. Then, the QoM applies the classes for compressing the KPI data utilizing a lossy-compression method, which is a derivative of the Piece-Wise Constant Approximation (PWCA) algorithm. To evaluate the performance of the QoM solution, we use M-Plane raw data from a live LTE network and calculate four KPIs, while each KPI has different statistical characteristics. We also define three QoM classes named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Exact</i> , <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Optimized</i> , and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sharp</i> . For all KPIs, the class <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Optimized</i> has a higher compression rate than the class <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Exact</i> , while the class <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sharp</i> has the highest compression rate. Assuming that, for example, NEs of a network produce 280 MB of raw data containing information that needs to be transferred to the network operations center; we use KPIs to represent the information contents of the data, and QoM solution to transfer the data over the network. As a result, the QoM solution achieves an estimated 95% compression gain from the raw data in transfer.

Integrated Network and Security Operation Center: A Systematic Analysis

Traditionally, network and security operation center teams have worked in silos despite commonalities. The network operating center (NOC) team is to provide operationality and availability of information technology (IT) assets, while the security operation center (SOC) team is to ensure IT assets security and protect them from cyber-security attacks. The convergence in IT assets and exponential growth in cyber-security threats in the present digital-online scenario have created many challenges in maintaining network and IT assets effectively and protecting them. It is vital to break these silos and bring them under one integrated unit to effectively counter cyber-security attacks, threats, and vandalism at a reduced operational cost. Despite its necessity, the relevant literature lacks an opinion. It focuses mainly on conceptual segments instead of a holistic view of an integrated NOC and SOC architecture, limiting further innovations in the field. A systematic literature review and analysis is conducted to collate and understand current research ideas in this paper. The mapped relevant literature and our expertise have been then used to propose the implementable state-of-the-art architecture of an integrated NOC and SOC, its definition, the main building blocks and its usefulness for the organizations. Only explicit knowledge of people is considered while neglecting the tacit knowledge in automating and integrating the processes of NOC and SOC, which is the major limitation of the relevant literature. Taping people tacit knowledge is necessary for utilizing the entire caliber of the NOC and SOC integration in the future.

Workforce Capacity Planning for Proactive Troubleshooting in the Network Operations Center

Workforce Capacity Planning for Proactive Troubleshooting in the Network Operations Center

Implementasi Sistem Monitoring Jaringan Kantor PT Mitra Solusi Infokom Menggunakan Manageengine Opmanager dengan Metode SNMP Protocol

PT Mitra Solusi Infokom (MSInfokom) is an IT System Integrator company engaged in Technology and Communication Infrastructure. Network monitoring in MSInfokom is still done manually and still relies on conventional methods, so it has an impact on the efficiency of the time used by the Network Operation Center (NOC) because it has to do direct tracking on existing devices. This thesis aims to design and build a network monitoring system using ManageEngine OpManager with the SNMP Protocol method. The result obtained from the use of this network monitoring application is to monitor the device in real time, where the system will send notifications via email in case of a malfunction or downtime on the existing device.

PENERAPAN METODE PER CONNECTION CLASSIFIER (PCC) PADA PERANCANGAN LOAD BALANCING DENGAN ROUTER MIKROTIK

The NOC (Network Operation Center) Division is highly dependent on the availability of internet access in carrying out its duties to monitor and maintain the network remotely. Therefore, the absence of adequate internet access will determine the performance of the work performed by the NOC division. However, problems often occur on computer networks or the internet that can hinder the work done by the NOC division, these problems include, such as the process of uploading or downloading files from the server feeling slow, unable to send emails smoothly, connections often experiencing time-out, There is a long network downtime, as well as traffic congestion on the network which can reduce network reliability. To solve this problem, one solution that can be done is to implement load balancing and failover mechanisms on the network using a MikroTik router. This study aims to design a load balancing scheme using the per connection classifier (PCC) method to overcome traffic congestion problems on the network. The research was conducted using field research methods using observation and interview techniques which were conducted from August to December 2020. The results showed that the application of the load balance technique on the xMikrotik router with the PCC (Per Connection Classifier) method can separate the internet connection through the two available ISP lines so that it can solve the problem of traffic buildup on one of the ISP links to reduce latency and improve existing network performance.

Network Protection Tools for Network Security Intelligence Centers

Continuing our research on designing a Network Security Intelligence Center as a combination of a Security Intelligence Center and a Network Operations Center we propose the NSIC’s security zone infrastructure with five zones, a few subzones and sandboxing, and network protection tools (NPTs) recommended for use to secure resilient NSIC’s operation.

The application of activity-based costing in the cost calculation of thermal-power enterprise

The advantages of activity-based costing include promoting the basic budget of activities and improving the management of activities, process and activity chain (value chain). Activity-based costing method, as an important tool of cost management in management accounting, extends the management of cost to the whole value-chain in the enterprise, and it also effectively changes the limitation of the focus of the law of manufacture costing on the study of the process concerning the making of certain products, thus offering adequate help to the enterprise in establishing systematic cost management. This paper, starting from the construction of thermal-power enterprises and through an analysis of the application of activity-based costing method in improving the quality and increasing the efficiency of the thermal enterprise, aims to point out the ways to eliminate the non-value-added activities so as to improve the management of value chain of the construction of the thermal-power enterprises by setting up multi-thermal-resource network operation center, thermal provision center and thermal-power enterprises.

Abstract IA37: Survival by race and ethnicity in pediatric and adolescent patients with Hodgkin lymphoma: A report from the Children’s Oncology Group

Abstract IA37: Survival by race and ethnicity in pediatric and adolescent patients with Hodgkin lymphoma: A report from the Children’s Oncology Group

Security Zone Infrastructure for Network Security Intelligence Centers

Abstract Today’s businesses need to enhance their security via quick adaptation to the challenges of modern perimeterless network security. Under numerous targeted network attacks, the lack of advanced threat detection and response capabilities, as well as busy information technology and information security teams, lacked in-depth security expertise exacerbate the situation. In this landscape, the well-known “Detect-Investigate-Respond” triad must be added by the fourth very critical component named “Adapt”, which should be based on Security Intelligence approach. In this paper, continuing our research on designing a Network Security Intelligence Center as a combination of a Security Intelligence Center and a Network Operations Center we propose the NSIC’s security zone infrastructure with five zones, a few subzones and sandboxing. Future areas of research are indicated.

Use of satellite technology for monitoring buildings and structures

Satellite technologies are successfully used in many areas of the economy, allowing you to solve problems that cannot be solved by other methods. The paper explores the possibility of using satellite technologies for monitoring buildings and structures located in remote areas where satellite technologies are the main type of communication (other types of communication are either impossible or economically inexpedient). It is shown that the most rational solution of the tasks set is the use of VSAT (Very Small Aperture Terminal) satellite technology. This technology allows you to deploy a satellite terminal in a short time, to establish communication and transfer data on the state of construction objects to a computer center located at a very large distance from the specified objects. A scheme for monitoring buildings is presented, including a geostationary artificial earth satellite, satellite terminals deployed at remote construction sites, the NOC (Communications control center, Network operations center) and the monitoring Center for all construction sites. The satellite is connected to subscriber terminals using a direct and reverse channel. Data from the NOC is transmitted to the monitoring Center via the Internet through a secure VPN connection. It is noted that the use of certain technical improvements in satellite technology directly depends on economic factors. It is indicated that the monitoring Center of all construction objects receives information on the state not only from remote, but also “ordinary” buildings and structures. It is noted that for efficient information processing it is necessary to use cloud computing, modern intellectual technologies, for large-scale tasks it is most promising to use Big Data technology.

A Technical Overview of the Kentucky Mesonet

The Kentucky Mesonet is a research-grade weather and climate observing network with redundant sensors that monitors the near-surface atmosphere at 71 locations across Kentucky. The network measures temperature, precipitation, solar radiation, relative humidity, barometric pressure, and wind speed and direction every 5 min, with soil moisture and soil temperature measured every 30 min. In addition, it operates a camera at selected locations. All observations are transmitted via cellular modem every 5 min and become available to the general public through the World Wide Web within seconds after arrival at Kentucky Mesonet’s Network Operations Center. In between arriving at the IT division and dissemination to general public, the data also go through automated data quality assurance (QA) procedures. Within that time, the data can be viewed through various graphical/visualization formats, developed based on feedback from the user community. The Kentucky Mesonet produces twice-daily QA reports and its technicians respond to these reports, making site visits when necessary to address issues. Mesonet technicians make regular site visits to all stations during spring, summer, and fall seasons. The network maintains a detailed database of station metadata that includes instrument and site maintenance history. The Mesonet delivers the data to the National Weather Service to aid forecasting. It also works closely with a variety of local, state, and federal entities so that the network can meet diverse needs.

Matheuristic for emergency response in the electric distribution system with unforeseen islanding

Since power supply may suffer interruptions, caused by climate events or even due to equipment and human failures, these interruptions are associated with procedures commonly referred as emergency orders. These emergency orders must be attended by repair crews in an attempt to reestablish the power supply all over the system. Assuming a set of these emergency orders, the network operation center (NOC) must find a scheduling so that they are all attended by the repair crews and the power supply reestablished as soon as possible, while considering the minimization of the total service cost. Distributed generation (DG) may be one alternative for furnishing temporally power supply, such as photovoltaic and wind power generation sources. In such approach, the islanding operation confers such a complexity when considering how much time should be needed to supply the affected loads and which ones may be even selected. This study proposes a novel matheuristic for emergency response to the contingency planning problem related to electric distribution operations, considering unforeseen islanding of DG. From using a mixed integer linear programming (MILP) model, based on the emergency order scheduling problem (EOSP) with islanding operation formulations, the optimization criteria involves the minimization of the cost of non-supplied energy and the penalties related to high important customers, while respecting electrical constraints. Computational results on the IEEE 33-bus system, modified with the insertion of DGs, show the effectiveness of the proposed solution on reducing the total attendance cost when compared to a traditional scheduling solution without considering the islanding operation.

The Children's Oncology Group: Organizational Structure, Membership, and Institutional Characteristics.

The Children's Oncology Group (COG) is the only organization within the National Cancer Institute's National Clinical Trials Network dedicated exclusively to pediatric cancer research. The purpose of this article is to provide an overview of COG's organizational structure, to characterize its institutional and individual membership, and to summarize enrollments onto COG clinical trials. Data from 2013 to 2015 were compiled from sources internal (Network Operations, Statistics and Data Center, Chair's Office) and external (American Hospital Association, American Nurses Credentialing Center) to COG, to present a comprehensive overview of COG's structure, individual and institutional membership, and group operations. In 2016, COG comprised 8,785 individuals from 223 member institutions, across seven countries. An average of 9,661 new patients were registered with COG per year over the most recent (2013-2015) 3-year period. Over the same 3-year time frame, there were an average of 16,836 enrollments onto therapeutic (i.e., treatment) and nontherapeutic (e.g., epidemiology, survivorship, biology) trials per year. COG institutions have diverse characteristics related to size, geographical location, and infrastructure. Individual membership also reflects diversity with representation from over 28 disciplines and groups. The diversity of COG institutions and individual members allows for unique perspectives and contributions to science unified under a common goal to enroll children/adolescents onto clinical trials. COG's collaborative, multidisciplinary approach to science functions to support the development of research that seeks to continually improve outcomes for children and adolescents with cancer.

A fine-grained multi-source measurement platform correlating routing transitions with packet losses

In this paper, we are interested in the relationship between packet losses and routing changes in an operational network. To do so we designed and deployed DCART, a monitoring platform over RENATER, the French research and education network. Our platform collects four data sources using both active and passive measurements in order to unveil their temporal correlations. Active probing allows especially for measuring packet losses on specifically crafted data flows. Those flows explore several load balanced paths and ease the revelation of forwarding loops. Passive monitoring is achieved by listening to all routing updates from IS-IS, the intra-domain routing protocol in use, and by retrieving tickets generated by the Network Operations Center (NOC).During our monitoring campaign, we observe that most of the series of loss were correlated to routing events either because routing changes lead to inconsistent state transitions, or because faulty – and so lossy – links trigger numerous periods of link flapping. In particular, we show that losses due to forwarding loops resulting from inconsistent routing states are quite common when links come back after an outage. We also show that link flapping sometimes induce very long lasting lossy periods frequently unnoticed by the NOC. A lightweight monitoring platform such as DCART could be used to better anticipate recurrent network outages and to improve the ticketing system.

OPERATIONAL RISK ANALYSIS OF NETWORK OPERATION CENTER DIVISION PT. IO

This research is try to identify the operational risks in Network Operation Center division of PT. IO; measure and evaluate the risks, as well as make control and response measures to operational risks. The research method was a survey and Focus Group Discussion, by using a questionnaire as a research tool. The sample selection is done by Quota sampling and Convenience sampling methods to the employees in Division Network Operating Center PT.IO, which has had experience of at least 5 years. The results showed that as many as 40 out of 49 identified risks have been handled properly. Against these risks, the company have 35 standard operating procedure documents (SOPs) as a mitigation of those risks. Nonetheless, efforts are needed to improve and update mitigation strategies because of the possibility of new risks and increased risk levels. It becomes a suggestion for further research as well as suggestion to undertake further research on mitigation at the division and director level.