Master’s thesis is dedicated to the issue of network element. In the first part are described technological aspects as the internal structure of network elements and control mechanisms that provide differentiaton of services and support their quality requirements. In the first chapter are listed control mechanisms from most simple like FIFO to the more sophisticated like CBWFQ. Active queue managements are not missing and they are described in the section Riadiaci člen. Significant role in the differentiation of services have processes marking and pakets classification. The second chapter is devoted most promising standard DiffServ. Contains section devoted to architecture, paket marking, code point DSCP and the final part is devoted to the types of per-hop behavior and it is expedited forwarding EF and technique assured forwarding AF. The third chapter gives an overview common models of neural networks, their properties and assess their suitability for deployment in network elements. The routher design itself and its structure in programming environment Matlab/Simulink is the subject of the fourth chapter. Except used bloks from Simulink library is described their setting and function in the wiring. Consequently results are reviewied and conclusions drawn.

The dissertation presents a connected vehicle based traffic signal control model (CVTSCM) for signalized arterials. The model addresses different levels of traffic congestion starting with the initial deployment of connected vehicle technologies focusing on two modules created in CVTSCM. For near/under-saturated intersections, an arterial-level traffic progression optimization model (ALTPOM) is being proposed. ALTPOM improves traffic progression by optimizing offsets for an entire signalized arterial simultaneously. To optimize these offsets, splits of coordinated intersections are first adjusted to balance predicted upcoming demands of all approaches at individual intersections. An open source traffic simulator was selected to implement and evaluate the performance of ALTPOM. The case studies’ field signal timing plans were coordinated and optimized using TRANSYT-7F as the benchmark. ALTPOM was implemented with connected vehicles penetration rates at 25% and 50%, ALTPOM significantly outperforms TRANSYT-7F with at least 26.0% reduction of control delay (sec/vehicle) and a 4.4% increase of throughput for both directions of major and minor streets. This technique differs from traditional traffic coordination which prioritizes major street traffic, and thereby generally results in degrading performance on minor streets. ALTPOM also provides smooth traffic progression for the coordinated direction with little impact on the opposite direction. The performance of ALTPOM improves as the penetration rate of connected vehicles increases. For saturated/oversaturated conditions, two queue length management based Active Traffic Management (ATM) strategies are proposed, analytically investigated, and experimentally validated. The first strategy distributes as much green time as possible for approaches with higher saturation discharge rate in order to reduce delay. For the second approach, green times are allocated to balance queue lengths of major and minor streets preventing queue spillback or gridlock. Both strategies were formulated initially using uniform arrival and departure, and then validated using field vehicle trajectory data. After validation of the modules, the effectiveness of CVTSCM is proven. Then, conclusions and recommendations for future researches are presented at the end.

No description available.

Wireless networks are undergoing an unprecedented revolution in the last decade. With the explosion of delay-sensitive applications in the Internet (i.e., online gaming and VoIP), latency becomes a major issue for the development of wireless technology. Taking advantage of the significant decline in memory prices, industrialists equip the network devices with larger buffering capacities to improve the network throughput by limiting packets drops. Over-buffering results in increasing the time that packets spend in the queues and, thus, introducing more latency in networks. This phenomenon is known as “bufferbloat”. While throughput is the dominant performance metric, latency also has a huge impact on user experience not only for real-time applications but also for common applications like web browsing, which is sensitive to latencies in order of hundreds of milliseconds. Concerns have arisen about designing sophisticated queue management schemes to mitigate the effects of such phenomenon. My thesis research aims to solve bufferbloat problem in both traditional half-duplex and cutting-edge full-duplex wireless systems by reducing delay while maximizing wireless links utilization and fairness. Our work shed lights on buffer management algorithms behavior in wireless networks and their ability to reduce latency resulting from excessive queuing delays inside oversized static network buffers without a significant loss in other network metrics. First of all, we address the problem of buffer management in wireless full-duplex networks by using Wireless Queue Management (WQM), which is an active queue management technique for wireless networks. Our solution is based on Relay Full-Duplex MAC (RFD-MAC), an asynchronous media access control protocol designed for relay full-duplexing. Compared to the default case, our solution reduces the end-to-end delay by two orders of magnitude while achieving similar throughput in most of the cases. In the second part of this thesis, we propose a novel design called “LearnQueue” based on reinforcement learning that can effectively control the latency in wireless networks. LearnQueue adapts quickly and intelligently to changes in the wireless environment using a sophisticated reward structure. Testbed results prove that LearnQueue can guarantee low latency while preserving throughput.

Current congestion control approaches that attempt to provide fair bandwidth allocation among competing flows primarily consider only data rate when making decisions on which packets to drop. However, responsive flows with high round trip times (RTTs) can still receive significantly less bandwidth than responsive flows with low round trip times. This paper proposes a congestion control scheme called WHITE that addresses router unfairness in handling flows with significantly different RTTs. Using a best-case estimate of a flow's RTT provided in each packet by the flow source or by an edge router, WHITE computes a stabilized average RTT. The average RTT is then compared with the RTT of each incoming packet, dynamically adjusting the drop probability so as to protect the bandwidth of flows with high RTTs while curtailing the bandwidth of flows with low RTTs. We present simulation results and analysis that demonstrate that WHITE provides better fairness than other rate-based congestion control strategies over a wide-range of traffic conditions. The improved fairness of WHITE comes close to the fairness of Fair Queuing without requiring per flow state information at the router.

Made available in DSpace on 2016-04-28T20:19:18Z (GMT). No. of bitstreams: 1 2007- Eliezer de Oliveira Figueiredo.pdf: 1961844 bytes, checksum: de32c223ac9f98f50331aa303f3973b7 (MD5) Previous issue date: 2007-08-27 / This paper is about Queue Management and Organizational Culture. Its study subject was the Campo Grande Branch of Banco do Brasil, located in the West District of the City of Rio de Janeiro, Brazil. Its general purpose is to investigate and interpret, on a day-to-day basis, how the Organizational Culture, or Subculture, influences Queue Management in a Banking Branch. As specific purposes its aims are: to verify if the existing theory on Queue Perception Management is applied; to present waiting time as a feature that must receive special attention from Bank Managers; to experience, first hand, the displeasure of waiting in line; to compile the gathered information and to suggest measures to mitigate the negative effects on the waiting client, when reducing or eliminating the wait is not possible. Methodologically, the research is classified on its ends as explanatory, whereas as its means it is classified as bibliographic, documental, of case study and field research. The ethnographic method was used on the field work, where the author immersed himself in the researched group, in the context where the social phenomena occurred, for a better understanding of the native point of view , through the process of interactive observation and semi-structured interview. Resulting data, including snapshots of the researched location, were recorded on the field journal. Data from the interviews of 14 customer contact personnel were recorded and fully transcripted. Obtained data went through a non digital analysis process according to a predefined script. The analysis of the speech concluded: concerning Queue Management, that there is a lack of distractions to entertain the client, that the clients notice available resources not being used for their benefits and that there are lonely waits; concerning Organizational Culture, that stress, selfishness, lack of punishment, the cult to foreign culture and the attachment to the internal rules are traits of the internal culture in Banco do Brasil that may be related to Queue Management. The paper concludes that the Bank culture is not concerned with the management of the perceptions of those waiting in line. A complete lack of knowledge about the Queue Management solutions could be easily verified on the customer contact personnel. It is noticed that this research has no signs of duality. The online pool brought to light and the ethnographic research made clear that waiting in line is a major factor on the clients level of satisfaction. The most urgent suggested measure is the implementation of distractions, along with the review of all processes related to customer contact, in order to reduce their duration. The conclusions of this paper are subject to the methodological limitations proper to ethnographic studies. / Esta disserta??o abordou o tema gest?o da fila sob a perspectiva da cultura organizacional. Teve como objeto de estudo a Ag?ncia Campo Grande RJ, do Banco do Brasil, localizada na Zona Oeste da cidade do Rio de Janeiro (RJ). Seu objetivo geral consistiu em interpretar e/ou investigar, na rotina di?ria, como a cultura (ou subcultura) organizacional est? influenciando a gest?o das percep??es nas filas de espera de uma ag?ncia banc?ria. Como objetivos espec?ficos procurou: verificar se h? aplica??o, na pr?tica, da teoria existente sobre a gest?o da percep??o do cliente na fila de espera; apontar o tempo de espera como um atributo que precisa merecer aten??o especial dos gestores das institui??es financeiras; vivenciar ou experimentar, no cotidiano, o desconforto da espera numa fila; compilar as informa??es obtidas sobre o assunto; e, por fim, propor sugest?es para, quando n?o for poss?vel a redu??o ou elimina??o, mitigar os efeitos negativos no cliente que espera na fila. Metodologicamente, a pesquisa foi classificada como explorat?ria, quanto aos fins, e bibliogr?fica, documental, de estudo de caso e de campo, quanto aos meios. No trabalho de campo, utilizou-se um m?todo com inten??o etnogr?fica, onde o pesquisador fez uma imers?o no dia-a-dia do grupo pesquisado, no contexto onde o fen?meno social acontecia, com a finalidade de compreender o chamado ponto de vista nativo , atrav?s do processo da observa??o participante e da entrevista semi-estruturada. Os dados provenientes da observa??o participante, inclusive foto retirada do ambiente, foram registrados no di?rio de campo do pesquisador. Os provenientes das entrevistas, realizadas com os 14 funcion?rios do atendimento (caixas e atendentes), foram gravados e transcritos em sua totalidade. Os dados obtidos foram, ent?o, submetidos ? an?lise de conte?do (sem o aux?lio de software), seguindo rotina definida. Foi apreendido, atrav?s da an?lise do discurso, que: sob o prisma da gest?o da fila, h? aus?ncia de distra??es que entretenham o consumidor, que h? recursos que n?o est?o atendendo aos consumidores ? vista deles e que h? esperas solit?rias; sob o prisma da cultura organizacional, o estresse, o esp?rito individualista, a impunidade, o culto ao estrangeiro e o apego ? norma est?o entre os tra?os culturais percebidos no Banco do Brasil que podem guardar alguma rela??o com a gest?o da fila. Como considera??es e conclus?es ficou evidente que n?o existe na cultura do banco uma preocupa??o com a gest?o das percep??es dos que esperam na fila; verificou-se uma quase completa ignor?ncia, por parte dos atendentes, dos conhecimentos existentes a cerca da gest?o das percep??es nas filas; registrou-se que a pesquisa n?o deixou marcada nos seus resultados a quest?o da dualidade; a pesquisa on line demonstrou, mas foi na viv?ncia do trabalho etnogr?fico que ficou bem caracterizado, que a espera na fila ? fator de grande insatisfa??o por parte dos clientes. Como sugest?o mais urgente, al?m da revis?o, para redu??o, dos tempos de todos os processos que envolvem o atendimento das pessoas, ficou a instala??o de distra??es. Finalmente, sublinhou-se que as conclus?es apresentam as limita??es metodol?gicas pr?prias dos estudos de cunho etnogr?fico.

Improving network performance in terms of efficiency, fairness in the bandwidth, and system stability has been a research issue for decades. Current Internet traffic control maintains sophistication in end TCPs but simplicity in routers. In each router, incoming packets queue up in a buffer for transmission until the buffer is full, and then the packets are dropped. This router queue management strategy is referred to as Drop Tail. End TCPs eventually detect packet losses and slow down their sending rates to ease congestion in the network. This way, the aggregate sending rate converges to the network capacity. In the past, Drop Tail has been adopted in most routers in the Internet due to its simplicity of implementation and practicability with light traffic loads. However Drop Tail, with heavy-loaded traffic, causes not only high loss rate and low network throughput, but also long packet delay and lengthy congestion conditions. To address these problems, active queue management (AQM) has been proposed with the idea of proactively and selectively dropping packets before an output buffer is full. The essence of AQM is to drop packets in such a way that the congestion avoidance strategy of TCP works most effectively. Significant efforts in developing AQM have been made since random early detection (RED), the first prominent AQM other than Drop Tail, was introduced in 1993. Although various AQMs also tend to improve fairness in bandwidth among flows, the vulnerability of short-lived flows persists due to the conservative nature of TCP. It has been revealed that short-lived flows take up traffic with a relatively small percentage of bytes but in a large number of flows. From the user’s point of view, there is an expectation of timely delivery of short-lived flows. Our approach is to apply artificial intelligence technologies, particularly fuzzy logic (FL), to address these two issues: an effective AQM scheme, and preferential treatment for short-lived flows. Inspired by the success of FL in the robust control of nonlinear complex systems, our hypothesis is that the Internet is one of the most complex systems and FL can be applied to it. First of all, state of the art AQM schemes outperform Drop Tail, but their performance is not consistent under different network scenarios. Research reveals that this inconsistency is due to the selection of congestion indicators. Most existing AQM schemes are reliant on queue length, input rate, and extreme events occurring in the routers, such as a full queue and an empty queue. This drawback might be overcome by introducing an indicator which takes account of not only input traffic but also queue occupancy for early congestion notification. The congestion indicator chosen in this research is traffic load factor. Traffic load factor is in fact dimensionless and thus independent of link capacity, and also it is easy to use in more complex networks where different traffic classes coexist. The traffic load indicator is a descriptive measure of the complex communication network, and is well suited for use in FL control theory. Based on the traffic load indicator, AQM using FL – or FLAQM – is explored and two FLAQM algorithms are proposed. Secondly, a mice and elephants (ME) strategy is proposed for addressing the problem of the vulnerability of short-lived flows. The idea behind ME is to treat short-lived flows preferably over bulk flows. ME’s operational location is chosen at user premise gateways, where surplus processing resources are available compared to other places. By giving absolute priority to short-lived flows, both short and long-lived flows can benefit. One problem with ME is starvation of elephants or long-lived flows. This issue is addressed by dynamically adjusting the threshold distinguishing between mice and elephants with the guarantee that minimum capacity is maintained for elephants. The method used to dynamically adjust the threshold is to apply FL. FLAQM is deployed to control the elephant queue with consideration of capacity usage of mice packets. In addition, flow states in a ME router are periodically updated to maintain the data storage. The application of the traffic load factor for early congestion notification and the ME strategy have been evaluated via extensive experimental simulations with a range of traffic load conditions. The results show that the proposed two FLAQM algorithms outperform some well-known AQM schemes in all the investigated network circumstances in terms of both user-centric measures and network-centric measures. The ME strategy, with the use of FLAQM to control long-lived flow queues, improves not only the performance of short-lived flows but also the overall performance of the network without disadvantaging long-lived flows.

Ce mémoire ne contient pas de résumé.

No description available.

Access to the large web content hosted all over the world by users of the Internet engage many hosts, routers/switches and faster links. They challenge the internet backbone to operate at its capacity to assure e±cient content access. This may result in congestion and raises concerns over various Quality of Service (QoS) issues like high delays, high packet loss and low throughput of the system for various Internet applications. Thus, there is a need to develop effective congestion control mechanisms in order to meet various Quality of Service (QoS) related performance parameters. In this paper, our emphasis is on the Active Queue Management (AQM) mechanisms, particularly Random Early Detection (RED). We propose a threshold based novel analytical model based on standard RED mechanism. Various numerical examples are presented for Internet traffic scenarios containing both the burstiness and correlation properties of the network traffic.