Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Data Mining - Concepts and Techniques.

Worst-case bounds on delay and backlog are derived for leaky bucket constrained sessions in arbitrary topology networks of generalized processor sharing (GPS) servers. The inherent flexibility of the service discipline is exploited to analyze broad classes of networks. When only a subset of the sessions are leaky bucket constrained, we give succinct per-session bounds that are independent of the behavior of the other sessions and also of the network topology. However, these bounds are only shown to hold for each session that is guaranteed a backlog clearing rate that exceeds the token arrival rate of its leaky bucket. A much broader class of networks, called consistent relative session treatment (CRST) networks is analyzed for the case in which all of the sessions are leaky bucket constrained. First, an algorithm is presented that characterizes the internal traffic in terms of average rate and burstiness, and it is shown that all CRST networks are stable. Next, a method is presented that yields bounds on session delay and backlog given this internal traffic characterization. The links of a route are treated collectively, yielding tighter bounds than those that result from adding the worst-case delays (backlogs) at each of the links in the route. The bounds on delay and backlog for each session are efficiently computed from a universal service curve, and it is shown that these bounds are achieved by "staggered" greedy regimes when an independent sessions relaxation holds. Propagation delay is also incorporated into the model. Finally, the analysis of arbitrary topology GPS networks is related to Packet GPS networks (PGPS). The PGPS scheme was first proposed by Demers, Shenker and Keshav (1991) under the name of weighted fair queueing. For small packet sizes, the behavior of the two schemes is seen to be virtually identical, and the effectiveness of PGPS in guaranteeing worst-case session delay is demonstrated under certain assignments. >

/pdf/a-generalized-processor-sharing-approach-to-flow-control-in-2dkaey9h9e.pdf

A generalized processor sharing approach to flow control in integrated services networks: the multiple node case

Network arrivals are often modeled as Poisson processes for analytic simplicity, even though a number of traffic studies have shown that packet interarrivals are not exponentially distributed. We evaluate 24 wide area traces, investigating a number of wide area TCP arrival processes (session and connection arrivals, FTP data connection arrivals within FTP sessions, and TELNET packet arrivals) to determine the error introduced by modeling them using Poisson processes. We find that user-initiated TCP session arrivals, such as remote-login and file-transfer, are well-modeled as Poisson processes with fixed hourly rates, but that other connection arrivals deviate considerably from Poisson; that modeling TELNET packet interarrivals as exponential grievously underestimates the burstiness of TELNET traffic, but using the empirical Tcplib interarrivals preserves burstiness over many time scales; and that FTP data connection arrivals within FTP sessions come bunched into "connection bursts", the largest of which are so large that they completely dominate FTP data traffic. Finally, we offer some results regarding how our findings relate to the possible self-similarity of wide area traffic. >

/pdf/wide-area-traffic-the-failure-of-poisson-modeling-3ve28sph9q.pdf

Wide area traffic: the failure of Poisson modeling

This survey characterizes an emerging research area, sometimes called coordination theory, that focuses on the interdisciplinary study of coordination. Research in this area uses and extends ideas about coordination from disciplines such as computer science, organization theory, operations research, economics, linguistics, and psychology.A key insight of the framework presented here is that coordination can be seen as the process of managing dependencies among activities. Further progress, therefore, should be possible by characterizing different kinds of dependencies and identifying the coordination processes that can be used to manage them. A variety of processes are analyzed from this perspective, and commonalities across disciplines are identified. Processes analyzed include those for managing shared resources, producer/consumer relationships, simultaneity constraints, and task/subtask dependencies.Section 3 summarizes ways of applying a coordination perspective in three different domains:(1) understanding the effects of information technology on human organizations and markets, (2) designing cooperative work tools, and (3) designing distributed and parallel computer systems. In the final section, elements of a research agenda in this new area are briefly outlined.

/pdf/the-interdisciplinary-study-of-coordination-22jsxamy1h.pdf

The interdisciplinary study of coordination

In this paper we develop a simple analytic characterization of the steady state throughput, as a function of loss rate and round trip time for a bulk transfer TCP flow, i.e., a flow with an unlimited amount of data to send. Unlike the models in [6, 7, 10], our model captures not only the behavior of TCP's fast retransmit mechanism (which is also considered in [6, 7, 10]) but also the effect of TCP's timeout mechanism on throughput. Our measurements suggest that this latter behavior is important from a modeling perspective, as almost all of our TCP traces contained more time-out events than fast retransmit events. Our measurements demonstrate that our model is able to more accurately predict TCP throughput and is accurate over a wider range of loss rates.

/pdf/modeling-tcp-throughput-a-simple-model-and-its-empirical-1apeszzbnq.pdf

Modeling TCP throughput: a simple model and its empirical validation

The steady-state performance of a bulk transfer TCP flow (i.e., a flow with a large amount of data to send, such as FTP transfers) may be characterized by the send rate, which is the amount of data sent by the sender in unit time. In this paper we develop a simple analytic characterization of the steady-state send rate as a function of loss rate and round trip time (RTT) for a bulk transfer TCP flow. Unlike the models of Lakshman and Madhow (see IEE/ACM Trans. Networking, vol.5, p.336-50, 1997), Mahdavi and Floyd (1997), Mathis, Semke, Mahdavi and Ott (see Comput. Commun. Rev., vol.27, no.3, 1997) and by by Ott et al., our model captures not only the behavior of the fast retransmit mechanism but also the effect of the time-out mechanism. Our measurements suggest that this latter behavior is important from a modeling perspective, as almost all of our TCP traces contained more time-out events than fast retransmit events. Our measurements demonstrate that our model is able to more accurately predict TCP send rate and is accurate over a wider range of loss rates. We also present a simple extension of our model to compute the throughput of a bulk transfer TCP flow, which is defined as the amount of data received by the receiver in unit time.

/pdf/modeling-tcp-reno-performance-a-simple-model-and-its-3zthb2w8t3.pdf

Modeling TCP Reno performance: a simple model and its empirical validation

https://storm.cis.fordham.edu/zhang/papers/Zhang05_epidemic.pdf

Performance modeling of epidemic routing

Understanding and modelling packet loss in the Internet is especially relevant for the design and analysis of delay-sensitive multimedia applications. We present analysis of 128 hours of end-to-end unicast and multicast packet loss measurement. From these we selected 76 hours of stationary traces for further analysis. We consider the dependence as seen in the autocorrelation function of the original loss data as well as the dependence between good run lengths and loss run lengths. The correlation timescale is found to be 1000 ms or less. We evaluate the accuracy of three models of increasing complexity: the Bernoulli model, the 2-state Markov chain model and the k-th order Markov chain model. Out of the 38 trace segments considered, the Bernoulli model was found to be accurate for 7 segments, and the 2-state model was found to be accurate for 10 segments. A Markov chain model of order 2 or greater was found to be necessary to accurately model the rest of the segments. For the case of adaptive applications which track loss, we address two issues of on-line loss estimation: the required memory size and whether to use exponential smoothing or a sliding window average to estimate average loss rate. We find that a large memory size is necessary and that the sliding window average provides a more accurate estimate for the same effective memory size.

Measurement and modelling of the temporal dependence in packet loss

Underwater sensor networks are attracting increasing interest from researchers in terrestrial radio-based sensor networks. There are important physical, technological, and economic differences between terrestrial and underwater sensor networks. Previous surveys have provided thorough background material in underwater communications, and an introduction to underwater networks. This has included detail on the physical characteristics of the channel [1], on underwater acoustic communications [2, 3, 4], and surveys of underwater acoustic networks [5, 6, 7, 8]. In this survey, we highlight a number of important practical issues that are not emphasized in the recent surveys of underwater networks, with an intended audience of researchers who are moving from radio-based terrestrial networks into underwater networks. We focus on issues relevant to medium access control (MAC) protocols, which are an area of continuing work both in terrestrial sensor networks and especially in underwater networks. Underwater networks are often characterized by more expensive equipment, higher mobility, sparser deployments, and different energy regimes when compared with terrestrial sensor networks. We discuss the role of these factors in the different set of challenges that face underwater networks. We identify several of these points in the outline below, and we expand upon them in later sections. In Section 2, we provide a classification scheme for underwater networks. Link-layer range, node density, and geographic coverage of nodes are key factors in determining the type of network deployed. The key differentiating factor for underwater net-

/pdf/a-survey-of-practical-issues-in-underwater-networks-3t1v0coh2p.pdf

Jim Kurose

Papers

Modeling TCP throughput: a simple model and its empirical validation

Modeling TCP Reno performance: a simple model and its empirical validation

Performance modeling of epidemic routing

Measurement and modelling of the temporal dependence in packet loss

A survey of practical issues in underwater networks