Network Performance Monitoring Research Articles

A large-scale network diagnosis system based on user-cooperative active measurements

Aiming at large-scale network diagnosis, this paper proposes a user cooperative measurement scheme that utilises many but variable users’ off-the-shelf PCs as active measurement end-point nodes (called ‘beacons’) both for lightly monitoring network performance along many end-to-end paths and for heavily conducting network diagnosis (e.g., identifying degraded links) after detection of an end-to-end performance degradation. In the scheme, the beacons and the measurement paths among them are dynamically selected by considering a trade-off between detection coverage and diagnostic timeliness under operational constraints such as the network resources along the path and the machine resource of the beacons. From an ISP viewpoint, utilising many users’ PCs as a measurement infrastructure will be promising, while challenging, to greatly reduce deployment and maintenance costs if possible variation and instability of individual PCs are mitigated. The effectiveness and feasibility of our scheme are demonstrated through large-scale simulations and preliminary real-world experiments using a prototype implementation.

Analysing 3G radio network performance with fuzzy methods

In comparison to the earlier telecommunications networks, present-day 3rd generation (3G) networks are able to provide more complex and detailed performance data, such as distributions of channel quality indicators. However, the operators lack proper methods and tools to efficiently utilize these data in monitoring and analysis of the networks. In this article, we apply fuzzy computing to channel quality measurement distributions to get the network elements (cells) clustered into groups of similar behavior. Groups and their descriptors provide valuable information for a radio expert, who is responsible for hundreds or thousands of elements. We introduce a fuzzy inference system based on features extracted from the distributional data and provide interpretation of the found categories to demonstrate their usability on network monitoring. Additionally we present how fuzzy clustering can be used in network performance monitoring and anomaly detection. Finally, we introduce further analysis on how time dimension is an interesting perspective to analyze network element behavior. All the achieved results were discussed with radio network performance experts who found them informative and useful.

A Graphical User Interface in WLAN Monitoring and Management System

This paper aims at providing a graphical user interface for WLAN monitoring and management system “WLAN Inspector”, which gives network operators the software and performance management tools necessary to monitor and manage network availability, achieve real-time monitoring (7 × 24 hours) and intelligent management , report on IP networks performance, and troubleshoot issues through a single Web-based graphical user interface. The overall framework design of graphical interface, brief description of each module, and the detailed design in the basic information interface are discussed in this paper. The WLAN monitoring and management system has multiple functions: real-time network monitoring, real-time protocol analysis, information, statistics, safety testing and network performance monitoring, etc. This system can give Video Frame Capture for Mac, analyze the WLAN traffic characteristics, detect possible security vulnerabilities, and give the appropriate solution.

Evolution of a residue laboratory network and the management tools for monitoring its performance

Since 2005 the National Residue & Contaminants Control Plan (NRCCP) in Brazil has been considerably enhanced, increasing the number of samples, substances and species monitored, and also the analytical detection capability. The Brazilian laboratory network was forced to improve its quality standards in order to comply with the NRCP's own evolution. Many aspects such as the limits of quantification (LOQs), the quality management systems within the laboratories and appropriate method validation are in continuous improvement, generating new scenarios and demands. Thus, efficient management mechanisms for monitoring network performance and its adherence to the established goals and guidelines are required. Performance indicators associated to computerised information systems arise as a powerful tool to monitor the laboratories’ activity, making use of different parameters to describe this activity on a day-to-day basis. One of these parameters is related to turnaround times, and this factor is highly affected by the way each laboratory organises its management system, as well as the regulatory requirements. In this paper a global view is presented of the turnaround times related to the type of analysis, laboratory, number of samples per year, type of matrix, country region and period of the year, all these data being collected from a computerised system called SISRES. This information gives a solid background to management measures aiming at the improvement of the service offered by the laboratory network.

A Grid resource brokering strategy based on resource and network performance in Grid

To achieve high performance distributed data access and computing in Grid environment, monitoring of resource and network performance is vital. Our proposed Grid network monitoring architecture is modeled by the Grid scheduler. The proposed Grid network monitoring retrieves network metrics using sensors as network monitoring tools. The mobile agents are migrated to start the sensors to measure the network metrics in all Grid Resources from the Resource Broker. The raw data provided by the monitoring tools is used to produce a high level view of the Grid through the set of internal cost functions. The network cost function is formed by combining various network metrics such as bandwidth, Round Trip Time, jitter and packet loss to measure the network performance. This paper presents the Grid Resource Brokering strategy which analyzes the network metrics along with the resource metrics for the selection of the Grid resource to submit the job and the proposed approach is integrated with CARE Resource Broker (CRB) for job submission. The experimental results are evident for the minimization of job completion time for the submitted job. The simulation results also prove that the more number of jobs are completed with the proposed strategy which influences the better utilization of the Grid resources.

A real-life test bed for multi-agent monitoring of road network performance

This paper describes an approach to road network monitoring. The approach has the following main components: a multi-agent hierarchical monitoring system in which the agents are network elements such as crossings, road segments and routes, software engineering techniques to handle legacy sensors and to homogenise their heterogeneous data streams, distributed Kalman filtering to reduce sensor noise, and a traffic simulation model to help in predicting future traffic states and to replace missing physical sensors. The approach has resulted in a real-life test bed for network performance monitoring in which various configurations of agents and various ways of distributed Kalman filtering can be tested. The current, still rather simple monitoring configuration, is already in operational use for traffic management.

Network monitoring and performance evaluation in a 3.5G network

Monitoring network performance and status is a fundamental task for network operators as it directly impacts the quality of the offered services and hence user satisfaction. For this purpose a consolidated approach, which is largely adopted by network operators, is based on the so-called KPIs (key performance indicators). In this paper, we propose and discuss a set of KPIs to monitor network performance of the new HSDPA enhanced UMTS infrastructure. KPI statistics are collected and analysed from the novel HSDPA network of H3G, one of the major Italian mobile network operators.

Evaluation of Speed-Based Travel Time Estimation Models

Travel time estimation models, which rely on speed data provided from point detectors (usually inductive loops), have application in travel time prediction and network performance monitoring. Unfortunately there are limited, and at times counterintuitive, results in the literature about their performance. This paper focuses on the field evaluation of four speed-based travel time estimation models, namely, the instantaneous model, the time slice model, the dynamic time slice model, and the linear model. Those models are evaluated using data from two operational motorways in Melbourne, Australia. Travel time estimation errors are quantified against actual travel times measured using a timed number plate survey and time-stamped toll tag data. There was little difference in the travel time estimation error across the models and they were all found to underestimate actual travel times. Errors ranged from about 7% in the off peak up to 15% in the peak. Marginal improvements in model performance were achieved through careful selection of which detectors provide input for each section (upstream, downstream, or the average of those values) and by conversion of the inputs from time mean speed to an estimate of space mean speed.

Novel dispersive and focusing device configuration based on curved waveguide grating (CWG)

Configuration of a novel compact dispersive and focusing device based on a Curved Waveguide Grating (CWG) is presented, which is essentially an integrated optic wavelength demultiplexer consisting of a curved stripe waveguide with tilted grating, a slab waveguide adjacent to it, and a set of output waveguides locate on focal line of the curved waveguide. Underlying wavelength demultiplexing mechanism of CWG is theoretically illustrated by employing the Fourier optics approach. Analysis shows that device based on CWG possesses fine wavelength resolution, compact configuration, and potentially low cost as well, which make it a promising wavelength demultiplexer, or a network performance monitor, in DWDM optical networks.

Analysis of network congestion inference techniques

Consider a neutral observer monitoring network performance based on external network measurements. Whenever congestion symptoms are observed within the network, the neutral observer would be interested in diagnosing the cause of the symptom, and in particular, identifying the congested link within the network. The neutral observer may contemplate to collect external network measurements reflective of network performance and from those measurements infer link delays to identify the congested link.Given the measurements collected, the following result has been obtained in this article. We prove that it is not possible to determine one-way link delays based on external network delay measurements. It is important to note that it is possible to determine one-way link delays with more information such as historical data or additional assumptions about directional delays.

Chasing errors through the network stack: a testbed for investigating errors in real traffic on optical networks

A testbed is described that allows both physical layer errors to be observed and analyzed, as well as monitoring network performance via frame loss. Real network traffic loads can be used for testing so that all measurements taken are representative of what would be seen in a deployed system. We illustrate our testbed with an examination of the behavior of a well-known networking standard, Gigabit Ethernet, in conditions of reduced receiver power on optical fiber. Our testbed results show that the line codes used to represent the data in the network affect the bit error rate for that data. Along with the previously reported result that bit error rate and packet error rate have only a weakly deterministic relationship, this highlights the need for testing of all network layers within a complete system carrying real-world traffic.

New analysis on mobile agents based network routing

This paper focuses on behavior analysis on mobile agents used in network routing. We describe a general agent-based routing model and classify it into two cases based on the reaction of mobile agents to a system failure, namely mobile agents with weak reaction capability (MWRC) and mobile agents with strong reaction capability (MSRC). For each case, we analyze the probability of success (the probability that an agent can find the destination) and the population distribution (the number of mobile agents) of mobile agents. The probability of success serves as an important measure for monitoring network performance, and the analysis of population distribution provides a useful tool for reducing the computational resource consumption. Our analysis reveals theoretical insights into the statistical behaviors of mobile agents and provides useful tools for effectively managing mobile agents in large networks.

Optimising data processing in network performance monitoring systems

Recent literature on the performance monitoring of communication networks focuses on exploiting compressibility of the collected data and its management on high-performance hardware. An alternative approach is to use summary structures referred to as intermediate information which support the reuse of semiprocessed information to optimise the calculation of nondistributive and nonalgebraic network delay statistics. Different intermediate-information structures possess different performance and accuracy characteristics. By selecting an appropriate structure on the basis of the query and the state of the intermediate-information cache, we show that significant improvements in the processing cost of a database of network measurements can be achieved. An approach to the dynamic selection of such a structure is presented and results showing the subsequent improvement in processing speed are given.

Detecting and classifying delay Data Exceptions on communication networks using rule based algorithms

Network performance monitoring is essential for managing a network efficiently and for ensuring reliable operation of the network. Monitored network performance changes reflect events in the network, such as faults, significant changes in usage patterns or planned alterations. Network managers are interested in how and when the performance of a network changes; however it is inefficient to analyse all the data resulting from the monitoring operation manually. In this paper a rule based algorithm to automate detection of the changes in one of the network performance parameters, namely delay, is presented and described in detail. The nature of the delay pattern in a commercial communication network was the key issue in developing this algorithm. The approach was tested with monitored delay data generated from three different networks and showed good results. Also, the algorithm was tested with sets of delay data which have been already input to a previously developed detector based on a different approach, and the results between the two detectors are compared. In addition to a noticeable improvement in detection performance, the new approach provides more generality and independency of the source of the delay data, making the approach generally applicable to other networks. Copyright © 2004 John Wiley & Sons, Ltd.

Managing ‘downstream’ supply network: A process and tool

A review of literature shows that little is available to assist managers to manage the ‘downstream’ end of a supply network involving manufacturers, dealers, and end-users. The interaction of important strategic factors in this respect is vital to companies but is not well understood by managers. This research proposes a process and tool, i.e. supply network analysis process (SNAP) to assist managers in addressing this issue. SNAP enables managers to visualise the inter-plays of downstream supply network strategic decisions, and to monitor network performance. SNAP was developed through a series of case studies in one specific region. Research was carried out in one industry sector, a ‘downstream’ supply network that consists of a number of manufacturers, dealers, and end-users. Semi-structured interviews and site visits were used to explore and understand the interaction of network decisions. The process discovered many unique interactive relationships among manufacturers, dealers, and end-users. This paper describes the development of SNAP, and explains its functions in a longitudinal case study. The paper concludes by discussing the implications of this research to academics and industrialists.

Managing ‘downstream’ supply network: A process and tool

A review of literature shows that little is available to assist managers to manage the ‘downstream’ end of a supply network involving manufacturers, dealers, and end-users. The interaction of important strategic factors in this respect is vital to companies but is not well understood by managers. This research proposes a process and tool, i.e. supply network analysis process (SNAP) to assist managers in addressing this issue. SNAP enables managers to visualise the inter-plays of downstream supply network strategic decisions, and to monitor network performance. SNAP was developed through a series of case studies in one specific region. Research was carried out in one industry sector, a ‘downstream’ supply network that consists of a number of manufacturers, dealers, and end-users. Semi-structured interviews and site visits were used to explore and understand the interaction of network decisions. The process discovered many unique interactive relationships among manufacturers, dealers, and end-users. This paper describes the development of SNAP, and explains its functions in a longitudinal case study. The paper concludes by discussing the implications of this research to academics and industrialists.

Location-Aided Planning in Mobile Network—Trial Results

Location-Aided Planning (LAP) technique provides possibility to use mobile phone measurements for monitoring network performance and traffic conditions. It enables detection of problem areas in the network, creation of alternative network plans for various traffic conditions as well as tuning and validation of propagation models with measurement data retrieved from the network. The paper reports results of a trial validating the LAP concept performed in standard GSM 1800 network in the frame of the EU IST project Cellular Network Optimization Based on Mobile Location (CELLO) [1]. During the trial, the accuracy of four selected location methods was evaluated. The measurements done during the trial were additionally used for assessment of the propagation model based on the well-known Okumura–Hata model with some corrections due to diffraction, building and land cover effects.

Combining active and passive network measurements to build scalable monitoring systems on the grid

Because the network provides the wires that connect a grid, understanding the performance provided by a network is crucial to achieving satisfactory performance from many grid applications. Monitoring the network to predict its performance for applications is an effective solution, but the costs and scalability challenges of actively injecting measurement traffic, as well as the information access and accuracy challenges of using passively collected measurements, complicate the problem of developing a monitoring solution for a global grid. This paper is a preliminary report on the Wren project, which is focused on developing scalable solutions for network performance monitoring. By combining active and passive monitoring techniques, Wren is able to reduce the need for invasive measurements of the network without sacrificing measurement accuracy on either the WAN or LAN levels. Specifically, we present topology-based steering, which dramatically reduces the number of measurements taken for a system by using passively acquired topology and utilization to select the bottleneck links that require active bandwidth probing. Furthermore, by using passive measurements while an application is running and active measurements when none is running, we preserve our ability to offer accurate, timely predictions of network performance, while eliminating additional invasive measurements.

Switch monitoring-The new generation of monitoring for local area networks

Network performance monitoring is an important part of effective network management. In a traditional shared-media local area network (LAN), probes connected to the network's segments perform the tasks of network monitoring. The control of such probes in the network-management framework based on simple network management protocol (SNMP) is specified in the Internet Engineering Task Force (IETF) remote monitoring (RMON) standards. In modern LANs, the shared-media infrastructure has been replaced by switches. Standard RMON probes are insufficient to monitor switched LANs. Thus, we have developed new methods to perform switch monitoring (SMON). SMON provides views of the traffic flowing through a switch, views of specific switch-related entities such as virtual LANs, and control of monitoring-related switch functions. SMON has recently been transformed into an IETF standard. Work on improving SMON has continued. A method to organize data-collection reports in switches is proposed, as well as extensions to handle statistics from Layer 3 and above at the switch level. The enterprise SMON application provides a way to monitor multiple switches simultaneously. This paper reviews the development of current and future standards in the area of LAN switch monitoring.

OWDP and its secure implementation

Here we present one design based on OWDP for secure high-speed IP network performance monitor system. Based on the analysis of OWDP protocol and the high-speed IP network performance's real-time monitor infrastructure, the paper illustrates the potential security problems in OWDP and its possible weakness when applied in the monitor infrastructure. One secure improvement design based on Otway-Rees authentication protocol is put forward, which can improve the security of the implementation of OWDP and the monitor architecture. Having kept OWDP's simplicity and efficiency, the design satisfies the real-time demand of high-speed network performance monitor and will effectively safeguard the monitor procedure against intensive attacks.