The market penetration of mobile access devices with multiple network interfaces has increased dramatically over the last few years. As a consequence, the quest for a widespread multi-path transport protocol that takes advantage of all available interfaces simultaneously to increase data throughput and improve robustness, has received considerable attention. One prominent protocol introduced by the IETF is Multipath TCP (MPTCP). MPTCP is an extension to the predominant single-path transport protocol, the Transport Control Protocol (TCP) that enables multihomed devices to aggregate available resources transparently to the applications. Combining multiple radio access technologies, like LTE and Wi-Fi, with diverse characteristics in terms of transmission rates and fluctuations opens for novel challenges that may disrupt and even harm the data throughput. Therefore MPTCP must take path heterogeneity into account. For MPTCP to supersede single-path TCP it is required that MPTCP always achieve at least the throughput of the best individual TCP path. This thesis investigates if MPTCP with uncoupled congestion control fulfills this condition, and if so, how much it improves the throughput. By examining the protocol in a deterministic emulated environment defined by the characteristics of LTE, we conclude two key factors impacting the outcome: the download size and the difference in characteristics between the paths. Our experiments show that MPTCP overall fulfills this task, especially during path homogeneity with near aggregated results. But we also show that MPTCP may decrease data throughput with 16% compared to TCP during path heterogeneity. Hence MPTCP does not always fulfill the goal of throughput. We therefore conclude further intelligence is needed for the packet scheduling mechanism to avoid throughput degradation in the initial phase of a transmission.

No description available.

No description available.

<p>The most widely used protocol for providing reliable service and congestion control in the Internet is the Transmission Control Protocol (TCP). When the Internet is moving towards more use in mobile applications it is getting more important to know how TCP works for this purpose.</p><p>One of the technologies used for mobile Internet is the Enhanced General Packet Radio Service (EGPRS) extension to the popular GSM system. This thesis presents a low-level analysis of TCP performance in an EGPRS system and an overview of existing TCP, GSM and EGPRS technologies.</p><p>The bottleneck in an EGPRS system is the wireless link – the connection between the mobile phone and the GSM base station. The data transfer over the wireless link is mainly managed by the complex RLC/MAC protocol.</p><p>In this thesis, simulations were made to identify some problems with running TCP and RLC/MAC together. The simulations were made using existing EGPRS testing software together with a new TCP module. The simulation software is also briefly described in the thesis.</p><p>Additionaly, some suggestions are given in order to enhance performance, both by changing the EGPRS system and by modifying the TCP algorithms and parameters.</p>

The most widely used protocol for providing reliable service and congestion control in the Internet is the Transmission Control Protocol (TCP). When the Internet is moving towards more use in mobile applications it is getting more important to know how TCP works for this purpose. One of the technologies used for mobile Internet is the Enhanced General Packet Radio Service (EGPRS) extension to the popular GSM system. This thesis presents a low-level analysis of TCP performance in an EGPRS system and an overview of existing TCP, GSM and EGPRS technologies. The bottleneck in an EGPRS system is the wireless link – the connection between the mobile phone and the GSM base station. The data transfer over the wireless link is mainly managed by the complex RLC/MAC protocol. In this thesis, simulations were made to identify some problems with running TCP and RLC/MAC together. The simulations were made using existing EGPRS testing software together with a new TCP module. The simulation software is also briefly described in the thesis. Additionaly, some suggestions are given in order to enhance performance, both by changing the EGPRS system and by modifying the TCP algorithms and parameters.

Developers widely use actor frameworks to build highly distributed systems. However, modern actor frameworks are limited in their network implementations, with Transmission Control Protocol (TCP) and User Datagram Protocol (UDP) being the main protocols used for network communication. This thesis investigates the use of specialized network protocols to improve the performance of actor frameworks in distributed systems. Message-passing, while commonly based on TCP, needs more performance and security than other protocols; therefore, the focus will be on different low-latency transport protocols that could substitute TCP. This work examines actor communication at the transport layer, considering the constraints of the deployment that often dictate the choice of a transport protocol. We explore how Quick UDP Internet Connections (QUIC), a low-latency transport protocol, affects actor systems performance and reliability by investigating the benefits of replacing TCP with QUIC in Kompact, a component-actor hybrid framework. We provide an overview of other low-latency protocols that fit various actor frameworks and implement QUIC in the networking layer of Kompact. Thereof, we evaluate the performance of QUIC, UDP and TCP in two different scenarios, such as file transfers outside of actor systems and ping-pong latency measurements within Kompact. The results show that glsquic outperforms TCP for larger file transfers outside actor systems, accomplishing higher throughput and faster download times. However, in the Kompact benchmark, QUIC did not outperform TCP due to issues with QUIC’s event loop implementation. The study also highlights the importance of proper synchronization between event loops in distributed systems. The findings suggest that QUIC has the potential to improve performance and reliability in actor systems by reducing latency and enhancing reliability through features such as multiplexing and connection migration. / Utvecklare använder i stor utsträckning actor-ramverk för att bygga väldigt distribuerade system. Moderna actor-ramverk är dock begränsade i sina nätverksimplementationer, med TCP och UDP som de huvudsakliga protokollen för nätverkskommunikation. Denna avhandling undersöker användningen av specialiserade nätverksprotokoll för att förbättra prestandan hos actor-ramverk i distribuerade system. Meddelandehantering, som vanligtvis är baserad på TCP, kräver högre prestanda och säkerhet än andra protokoll. Därför kommer fokus att ligga på olika låg-latens transportprotokoll som kan ersätta TCP. Denna undersökning undersöker actor-kommunikation på transportlagret, med hänsyn till de begränsningar som ofta dikterar valet av transportprotokoll. Vi utforskar hur QUIC, ett låg-latens transportprotokoll, påverkar prestanda och tillförlitlighet i actor-system genom att undersöka fördelarna med att ersätta TCP med QUIC i Kompact, ett komponent-actor hybrid-ramverk. Vi ger en översikt över andra låg-latens protokoll som passar olika actor-ramverk och implementerar QUIC i nätverkslagret av Kompact. Därigenom utvärderar vi prestandan för QUIC, UDP och TCP i två olika scenarier, såsom filöverföringar utanför actor-system och ping-pong-latensmätningar inomKompact. Resultaten visar att QUIC överträffar TCP för större filöverföringar utanför actor-system, uppnår högre genomströmning och snabbare nedladdningstider. Men i Kompact-benchmarken överträffade QUIC inte TCP på grund av problem med QUICs event-loop-implementering. Studien belyser också vikten av korrekt synkronisering mellan event-loops i distribuerade system. Resultaten antyder att QUIC har potential att förbättra prestanda och tillförlitlighet i actor-system genom att minska latens och förbättra tillförlitligheten genom funktioner som multiplexing och anslutningsmigration.

The aim of this work is to understand the requirements behind Quality of Service (QoS) for Multihop Wireless Networks and evaluate the performance of different such strategies. This work starts by establishing the basis for requirement of QoS and evaluates different approaches for providing QoS. Bandwidth is selected as the most important resource amongst the resources identified for ensuring QoS. The problem is modeled as an optimization problem that tries to maximize the amount of bandwidth available in the system while providing bounds over the bandwidth available over a route. Other QoS parameters are bound by hard limits and are not involved in the optimization problem. The existence of spatial reuse rules has been established through simulations for a TCP based network. This establishes that the reuse rules are independent of the MAC and network layer protocols used. This idea is used in designing the simulations for strategies that use controlled spatial reuse and give known bounds for QoS. Simulations take the network and a set of connections to generate the best possible schedule that guarantees bandwidth to individual connections and maximizes the total number of slots used in the entire system. The total number of slots used is a measure of the bandwidth in use. The set of graphs and connections is generated by a random graph and connection generator and the data set is large enough to average the results. There are two different approaches used for scheduling the connections. The first approach uses graph coloring and provides a simpler implementation in terms of network deployments. Second approach uses on-demand slot allocation. The approaches are compared for their pros and cons. The first approach uses graph coloring to allocate fixed number of slots to each link. This makes an equivalent of a wired network with fixed bandwidth over each link. This network is simpler to operate and analyze at the cost of one time expense of graph coloring. The assumption here is that the network is static or has low mobility. The on demand approach is more flexible in terms of slot assignment and is adaptable to the changing traffic patterns. The cons are that connection establishment is more expensive in terms of bandwidth required and is more complicated and difficult to analyze. The advantages include low initial network establishment cost and accommodation of mobility.

ITC/USA 2014 Conference Proceedings / The Fiftieth Annual International Telemetering Conference and Technical Exhibition / October 20-23, 2014 / Town and Country Resort & Convention Center, San Diego, CA / One of the initial control room capabilities to be demonstrated by iNET program is the ability to provide data displays in the control room that do not contain data dropouts. This concept is called PCM Backfill where PCM data is both transmitted via traditional SST and recorded onboard via an iNET compatible recorder. When data dropouts occur, data requests are made over the telemetry network to the recorder for the missing portions of the PCM data stream. The retrieved data is sent over the telemetry network to the backfill application and ultimately delivered to a pristine data display. The integration of traditional SST and the PCM Backfill capability provides both real-time safety of flight data side-by-side with pristine data suitable for advanced analysis.

The Datagram Congestion Control Protocol (DCCP) is a prominent transport protocol that has attracted the attention of the scientific community for its rapid progress and good results. The main novelty of DCCP is the performance priority design, as in UDP, however with congestion control capabilities, as in TCP. Literature about DCCP is still scarce and needs to be complemented to gather enouth scientific elements to support new research properly. In this context, this work joins the efforts of the scientific community to analise, mensure, compare and characterize DCCP in relevant scenarios that cover many real world situations. Three open questions were preliminarly identified in the literature: How DCCP behaves (i) when fighting for the same link bandwidth with other transport protocols; (ii) with highly relevant ones (e.g., Compound TCP, CUBIC) and (iii) fighting for the same link bandwidth with Compound TCP and CUBIC, adopting multimedia applications (e.g., VoIP). In this work, computational simulations are used to compare the performance of two DCCP variants (DCCP CCID2 and DCCP CCID3) with three highly representative TCP variants (Compound TCP, CUBIC and TCP SACK), in real world scenarios, including concurrent use of the same link by protocols, link errors and assorted bandwidths, latencies and traffic patterns. The simulation results show that, under contention, in most scenarios DCCP CCID2 has achieved higher throughput than Compound TCP or TCP SACK. Throughout the simulations there was a tendency of DCCP CCID3 to have lower throughput than the other chosen protocol. However, the results also showed that DCCP CCID3 has achieved significanly better throughput in the presence of link errors and higher values of latency and bandwidth, eventualy outperforming Compound TCP and TCP SACK. Finally, there was a tendency of predominance of CUBIC´ throughtput, which can be explained by its aggressive algorithm (i.e., non-linear) of return of the transmission window to the previous value before the discard event. However, CUBIC has presented the highest packet drop and the lowest delivery rate. / O Datagram Congestion Control Protocol (DCCP) é um proeminente protocolo de transporte que vem atraindo a atenção da comunidade científica pelos seus rápidos avanços e bons resultados. A principal inovação do DCCP é a priorização de desempenho, como ocorre com o UDP, mas com capacidade de realizar controle de congestionamento, como ocorre com o TCP. Entretanto, a literatura sobre o DCCP ainda é escassa e necessita ser complementada para trazer elementos científicos suficientes para novas pesquisas. Neste contexto, este trabalho vem se somar aos esforços da comunidade científica para analisar, mensurar, comparar e caracterizar o DCCP em cenários representativos que incorporem diversas situações de uso. Identificaram-se então três questões alvo, ainda em aberto na literatura: qual é o comportamento do DCCP (i) quando disputa o mesmo enlace com outros protocolos de transporte; (ii) com protocolos de transporte relevantes (e.g., Compound TCP, CUBIC) e (iii) em disputa no mesmo enlace com o Compound TCP e o CUBIC, utilizando aplicações multimídia (e.g., VoIP). Neste trabalho, simulações computacionais são utilizadas para comparar duas variantes do DCCP (CCID2 e CCID3) a três variantes do TCP (Compound TCP, CUBIC e TCP SACK), em cenários onde ocorrem situações de mundo real, incluindo utilização concorrente do enlace pelos protocolos, presença de erros de transmissão no enlace, variação de largura de banda, variação de latência, e variação de padrão e distribuição de tráfego. Os resultados das simulações apontam que, sob contenção, na maioria dos cenários o DCCP CCID2 obteve vazão superior à do Compound TCP, do DCCP CCID3 e do TCP SACK. Ao longo das simulações observou-se uma tendência do DCCP CCID3 a ter vazão inferior à dos demais protocolos escolhidos. Entretanto, os resultados apontaram que o DCCP CCID3 obteve desempenho significativamente melhor na presença de erros de transmissão e com valores maiores de latência e de largura de banda, chegando a ultrapassar a vazão do DCCP CCID2 e do TCP SACK. Por fim, observou-se uma tendência de predominância do protocolo CUBIC no tocante à vazão, que pode ser determinada pelo seu algoritmo agressivo (i.e., não-linear) de retorno da janela de transmissão ao valor anterior aos eventos de descarte. Entretanto, o CUBIC apresentou o maior descarte de pacotes e a menor taxa de entrega.

Along with playing an ever-increasing role in the integration of other communication networks and expanding in application diversities, the current Internet suffers from serious overuse and congestion bottlenecks. Efficient congestion control is fundamental to ensure the Internet reliability, satisfy the specified Quality-of-Service (QoS) constraints and achieve desirable performance in response to varying application scenarios. Active Queue Management (AQM) is a promising scheme to support end-to-end Transmission Control Protocol (TCP) congestion control because it enables the sender to react appropriately to the real network situation. Analytical performance models are powerful tools which can be adopted to investigate optimal setting of AQM parameters. Among the existing research efforts in this field, however, there is a current lack of analytical models that can be viewed as a cost-effective performance evaluation tool for AQM in the presence of heterogeneous traffic, generated by various network applications. This thesis aims to provide a generic and extensible analytical framework for analyzing AQM congestion control for various traffic types, such as non-bursty Poisson and bursty Markov-Modulated Poisson Process (MMPP) traffic. Specifically, the Markov analytical models are developed for AQM congestion control scheme coupled with queue thresholds and then are adopted to derive expressions for important QoS metrics. The main contributions of this thesis are listed as follows: • Study the queueing systems for modeling AQM scheme subject to single-class and multiple-classes Poisson traffic, respectively. Analyze the effects of the varying threshold, mean traffic arrival rate, service rate and buffer capacity on the key performance metrics. • Propose an analytical model for AQM scheme with single class bursty traffic and investigate how burstiness and correlations affect the performance metrics. The analytical results reveal that high burstiness and correlation can result in significant degradation of AQM performance, such as increased queueing delay and packet loss probability, and reduced throughput and utlization. • Develop an analytical model for a single server queueing system with AQM in the presence of heterogeneous traffic and evaluate the aggregate and marginal performance subject to different threshold values, burstiness degree and correlation. • Conduct stochastic analysis of a single-server system with single-queue and multiple-queues, respectively, for AQM scheme in the presence of multiple priority traffic classes scheduled by the Priority Resume (PR) policy. • Carry out the performance comparison of AQM with PR and First-In First-Out (FIFO) scheme and compare the performance of AQM with single PR priority queue and multiple priority queues, respectively.