Detecting network anomalies is a fundamental part of day to day operations for Internet Service Providers and enterprises to maintain the efficiency and reliability of computer networks. Network anomaly detection is based on data... more
Detecting network anomalies is a fundamental part of day to day operations for Internet Service Providers and enterprises to maintain the efficiency and reliability of computer networks. Network anomaly detection is based on data characteristics of normal and anomalous network behaviors. Although many existing studies report univariate data characteristics of normal and anomalous network behaviors, there are few studies on multivariate data characteristics of normal and anomalous network behaviors. The goal of this study is to investigate multivariate data characteristics of normal and anomalous network behaviors using the Partial-Value Association Discovery (PVAD) algorithm. This paper illustrates the use of the PVAD algorithm to analyze network flow data of a medium size enterprise under the normal condition and an anomalous condition and reveal multivariate data characteristics of the normal and anomalous network flows in the form of multivariate data associations.
Research Interests:
Research Interests:
Driven by the needs to monitor, detect, and prevent catastrophic failures for complex information systems in real-time, we develop in this paper a discrete-time queuing network simulator. The dynamic model for the simulator abstracts... more
Driven by the needs to monitor, detect, and prevent catastrophic failures for complex information systems in real-time, we develop in this paper a discrete-time queuing network simulator. The dynamic model for the simulator abstracts network dynamics by taking an aggregated and layered structure. Comparative studies verify capabilities of the simulator in terms of accuracy and computational efficiency. We illustrate the model structure, flow processing mechanisms, and simulator implementation. We also illustrate the use of this simulator to detect distributed denial-of-service (DDoS) flooding attacks, based on a cross-correlation-based measure. Finally, we show that the layered structure provides new insights on the spatiotemporal spread patterns of cascading failure, by revealing spreads both horizontally within a sub-network and vertically across sub-networks.
Research Interests:
1. Status of this Memo Explaining the Role of GOSIP This informational RFC represents the official view of the Internet Activities Board (IAB), after coordination with the Federal Networking Council (FNC). This RFC does not specify a... more
1. Status of this Memo Explaining the Role of GOSIP This informational RFC represents the official view of the Internet Activities Board (IAB), after coordination with the Federal Networking Council (FNC). This RFC does not specify a standard.
Experimenters characterize the behavior of simulation models for data communications networks by measuring multiple responses under selected parameter combinations. The resulting multivariate data may include redundant responses... more
Experimenters characterize the behavior of simulation models for data communications networks by measuring multiple responses under selected parameter combinations. The resulting multivariate data may include redundant responses reflecting aspects of a smaller number of underlying behaviors. Reducing the dimension of multivariate responses can reveal the most significant model behaviors, allowing subsequent analyses to focus on one response per behavior. This paper investigates two methods for reducing dimension in multivariate data generated from simulation models. One method combines correlation analysis and clustering. The second method uses principal components analysis. We apply both methods to reduce a 22-dimensional dataset generated by a network simulator. We identify issues that an analyst must decide, and we compare the reductions suggested by the methods. We have used these methods to identify significant behaviors in simulated networks, and we suspect they may be applied...
Research Interests:
Research Interests:
A communication network, such as the Internet, comprises a complex system where cooperative phenomena may emerge from interactions among various traffic flows generated and forwarded by individual nodes. To identify and understand such... more
A communication network, such as the Internet, comprises a complex system where cooperative phenomena may emerge from interactions among various traffic flows generated and forwarded by individual nodes. To identify and understand such phenomena, we model a network as a two-dimensional cellular automaton. We suspect such models can promote better understanding of the spatial-temporal evolution of network congestion, and other emergent phenomena in communication networks. To search the behavior space of the model, we study dynamic patterns arising from interactions among traffic flows routed across shared network nodes, as we employ various configurations of parameters and two different congestion-control algorithms. In this paper, we characterize correlation in congestion behavior within the model at different system sizes and time granularities. As expected, we find that long-range dependence (LRD) appears at some time granularities, and that for a given network size LRD decays as ...
Research Interests:
The NBS Protocol Performance Laboratory developing class 4 transport efficiency selective shown to improve throughput as 34%. Several alternative mechanisms have demonstrated improvements as great as 38%. Most of the protocol mechanism... more
The NBS Protocol Performance Laboratory developing class 4 transport efficiency selective shown to improve throughput as 34%. Several alternative mechanisms have demonstrated improvements as great as 38%. Most of the protocol mechanism enhancements considered minor changes to the international transport
Research Interests:
Research Interests:
Research Interests: Information Systems, Software Architecture, Flow Control, Control system, Software Design, and 12 moreComputer Software, Design method, Real Time Systems, expert System, Behavior Modeling, Real Time, Knowledge base, Data Flow Diagram, Unified Modeling Language, Graphical Model, Object Oriented, and Rule Based
Automated Generation Of Concurrent Designs For Real-Time Software. Kevin Mills. This dissertation proposes, investigates, and evaluates a method for generating concurrent designs for real-time software, given a flow graph model of system... more
Automated Generation Of Concurrent Designs For Real-Time Software. Kevin Mills. This dissertation proposes, investigates, and evaluates a method for generating concurrent designs for real-time software, given a flow graph model of system behavior. ...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests: Software Engineering, Computer Networks, Resource Allocation, Packet Switching, Heterogeneity, and 12 moreSafety, Problem Solving, Mathematical Models, Nodes, Resource Management, Throughput, Predictive models, Network Architecture, NIST, Intelligent Networks, Central Processing Unit, and Active Networks
Research Interests:
Research Interests:
Research Interests:
Research Interests:
The knowledge plane will be highly dependent upon knowledge derived from infor- mation contained in participating nodes. Such information will comprise data gener- ated by a participating node's hardware (e.g., CPU and network... more
The knowledge plane will be highly dependent upon knowledge derived from infor- mation contained in participating nodes. Such information will comprise data gener- ated by a participating node's hardware (e.g., CPU and network devices) and software (e.g., operating system and network applications) that conforms to one of many dis- tinct ontologies or information models. Before node information can be utilized
Research Interests:
Research Interests:
The authors address the challenge of establishing a test policy and procedures for the US Government OSI Profile (GOSIP). They recount the progress since March 1989, describe the policy and procedures now in place, and look ahead toward... more
The authors address the challenge of establishing a test policy and procedures for the US Government OSI Profile (GOSIP). They recount the progress since March 1989, describe the policy and procedures now in place, and look ahead toward remaining challenges. Specifically, they report on progress on the details of GOSIP testing, including identifying abstract test suites, developing methods to assess
Research Interests:
Research Interests: Computer Architecture, Methodology, Metrics, Hardware Description Languages, Distributed System, and 15 moreMiddleware, Failure Recovery, Msc, Modification, Consistency, Mathematical Models, Efficiency, Network Architecture, Network Topology, NIST, Communications Protocols, Latency, Consistency Maintenance, Measurement System, and Failure rate
Modern communication channels, such as digital cellular telephony, often convey human speech in a highly encoded form. Methods that rely on human subjects to evaluate the quality of such channels are too costly to deploy on a large scale;... more
Modern communication channels, such as digital cellular telephony, often convey human speech in a highly encoded form. Methods that rely on human subjects to evaluate the quality of such channels are too costly to deploy on a large scale; thus, automated methods are often used to model quality as perceived by humans. Traditional automated methods that use Signal to Noise
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Current and future uses suggest that wireless communications and networks should become an essential, possibly predominant, part of the world's global information infrastructure. Do you own a cell phone? If not, do you own a cordless... more
Current and future uses suggest that wireless communications and networks should become an essential, possibly predominant, part of the world's global information infrastructure. Do you own a cell phone? If not, do you own a cordless phone? How about a laptop computer with one or more built-in wireless interfaces, such as WI-FI (wireless fidelity) or Bluetooth? Or maybe you have
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Reuse of software components emerged as an industry goal subsequent to a NATO conference in 1969 where Doug McIlroy first introduced the concept. Over the two decades since, reuse remained a topic of much discussion and some research;... more
Reuse of software components emerged as an industry goal subsequent to a NATO conference in 1969 where Doug McIlroy first introduced the concept. Over the two decades since, reuse remained a topic of much discussion and some research; and, although different views exist on the degree of success enjoyed by software developers in today's industry, most students of the state