A significant fraction of data traffic is transmitted via cellular networks. When introducing fifth-generation (5G) radio access technology, the maximum bitrate of the radio link increases significantly, and the delay is lowered. Network congestion occurs when the sender attempts to send data at a higher rate than the network link or nodes can handle. In order to improve the performance of the mobile networks, many congestion control techniques and approaches have been developed over the years. Varying radio conditions in mobile networks make it challenging to indicate the occurrence of the congestion using packet loss as congestion indicator. This master thesis develops a congestion control algorithm based on Artificial Intelligence (AI) technologies, evaluates and compares it with existing state-of-the-art congestion control algorithms that are used with TCP today.In this study, we use the abundant readable physical layer information exchanged between the base stations and the user equipment to predict the available bandwidth. Two neural network models, Multi-Layer Perceptron (MLP) and Long Short-Term Memory (LSTM), are introduced as congestion control algorithms based on cross-layer information in order to improve user throughput and utilize the available capacity as much as possible.Evaluation in a Long-Term Evolution (LTE) network system simulator confirms that the estimation of LSTM model is able to track the varying link capacity, while MLP is less accurate and induces higher delay. The sender uses the estimated link capacity to adjust its packet sending behavior. Our evaluation reveals that for large flows, the LSTM model can attain higher throughput than state-of-the-art congestion control algorithms, which are the Google Bottleneck Bandwidth and Round-trip propagation time (BBR) algorithm and the Data Center TCP (DCTCP) algorithm. However, it has higher latency than that of these two algorithms. The MLP based model provides unstable performance compared to LSTM; its prediction is not accurate enough and has the highest latency among the algorithms.In conclusion, the LSTM does not underperform the state-of-the-art congestion control algorithms. However, it does not provide additional performance gains in current settings. The MLP model underperforms BBR and DCTCP with L4S and it is not stable enough to be used as a congestion control algorithms. / En betydande del av datatrafiken överförs via mobilnät. Vid introduktion av femte generationens (5G) radioåtkomstteknik ökar den maximala bithastigheten för radiolänken betydligt och förseningen sänks. Nätstockning uppstår när avsändaren försöker skicka data med högre hastighet än nätverkslänken eller noderna kan hantera. För att förbättra prestandan i mobilnät har många tekniker för trängselkontroll utvecklats under åren. Varierande radioförhållanden i mobilnätet gör det utmanande att indikera förekomsten av trängseln med hjälp av paketförlust som trängselindikator. Detta examensarbete utvecklar en trängselkontrollalgoritm baserad på AI-teknik (Artificial Intelligence), utvärderar och jämför den med befintliga toppmoderna trängselkontrollalgoritmer som används med TCP idag.I denna studie använder vi den rikliga läsbara informationen om fysiskt lager som utbyts mellan basstationerna och användarutrustningen för att förutsäga den tillgängliga bandbredden. Två neurala nätverksmodeller, Multi-Layer Perceptron (MLP) och Long Short-Term Memory (LSTM), introduceras som trängselkontrollalgoritmer baserade på tvärskiktsinformation för att förbättra användarens genomströmning och utnyttja den tillgängliga kapaciteten så mycket som möjligt.Utvärdering i en LTE-nätverkssystemsimulator (Long Term Evolution) bekräftar att uppskattningen av LSTM-modellen kan spåra den varierande länkkapaciteten, medan MLP är mindre exakt och inducerar högre fördröjning. Avsändaren använder den uppskattade länkkapaciteten för att justera sitt paketets sändningsbeteende. Vår utvärdering avslöjar att för stora flöden kan LSTM-modellen uppnå högre genomströmning än modernaste trängselkontrollalgoritmer, som är Google Bottleneck Bandbredd och BBR-algoritm och Data Center TCP (DCTCP) ) algoritm. Men det har högre latens än för dessa två algoritmer. Den MLP-baserade modellen ger instabil prestanda jämfört med LSTM; dess förutsägelse är inte nog noggrann och har den högsta latensen bland algoritmerna.Sammanfattningsvis underpresterar LSTM inte de senaste toppkontrollalgoritmerna. Det ger emellertid inte ytterligare prestationsvinster i de aktuella inställningarna. MLP-modellen underpresterar BBR och DCTCP med L4S och den är inte tillräckligt stabil för att användas som en överbelastningskontrollalgoritm.

An increasing number of complex applications are being executed on resource constrained devices, such as drones and rovers. Such systems often operate in dynamic and unknown environments, and consequently have dynamic performance requirements based on their surroundings. These systems must consider the trade-off between application and platform performance in order to operate within resource means. This thesis proposes a runtime resource management system for a monolithic localization application. The proposed strategy uses gradient boosting regressors to predict localization accuracy and power consumption at runtime for a set of configurable application and platform parameters. A model-based controller selects parameters at runtime to optimize localization accuracy subject to a power constraint. The testbed used for experiments consists of maplab, a visual-inertial localization and mapping framework, executed monolithically on the Nvdia Jetson AGX platform. The results highlight the importance of incorporating dynamic parameters when identifying predictive models for localization systems. The proposed system is able to track a power reference while maintaining reasonable localization accuracy at runtime, for both platform and application parameters. The results demonstrate that runtime control can achieve better performance than alternative solutions which rely on offline profiling of the configuration space. / Ett ökande antal komplexa program körs på resursbegränsade enheter, till exempel drönare och rover. Sådana system fungerar ofta i dynamiska och okända miljöer och har därför dynamiska prestandakrav som är baserade på deras omgivningar. I dessa system måste hänsyn tas till skillnaden mellan applikations- och plattformsprestanda för att kunna fungera med hjälp av resurser. I den här tesen föreslås ett resurshanteringssystem för körning av ett monolitiskt lokaliseringsprogram. Den föreslagna strategin använder övertoningsförstärkare för att förutsäga lokaliseringens exakthet och energiförbrukning vid körning för en uppsättning konfigurerbara program- och plattformsparametrar. En modellbaserad styrenhet väljer parametrar under körning för att optimera lokaliseringsnoggrannheten under förutsättning att det finns en energibegränsning. Den testbädd som används för experiment består av maplab, en ram för visuell tröghetslokalisering och kartläggning, som utförts monolitiskt på Nvdia Jetson AGX-plattformen. Resultaten belyser vikten av att införliva dynamiska parametrar när man identifierar förutsägbara modeller för lokaliseringssystem. Det föreslagna systemet kan spåra en energireferens samtidigt som man bibehåller en rimlig lokaliseringsnoggrannhet vid körning, för både plattformsparametrar och programparametrar. Resultaten visar att körningskontroll kan ge bättre prestanda än alternativa lösningar som är beroende av offlineprofilering av konfigurationsutrymmet.

No description available.

In this dissertation, we propose service-oriented sensor-actuator networks (SOSANETs) as a new paradigm for building the next generation of customizable, open, interoperable sensor-actuator networks. In SOSANETs, nodes expose their capabilities to applications in the form of service profiles. A node's service profile consists of a set of services (i.e., sensing and actuation capabilities) that it provides and the quality of service (QoS) parameters associated with those services (delay, accuracy, freshness, etc.). SOSANETs provide the benefits of both application-specific SANETs and generic SANETs. We first define a query model and an architecture for SOSANETs. The proposed query model offers a simple, uniform query interface whereby applications specify sensing and actuation queries independently from any specific deployment of the underlying SOSANET. We then present μRACER (Reliable Adaptive serviCe-driven Efficient Routing), a routing protocol suite for SOSANETs. μRACER consists of three routing protocols, namely, SARP (Service-Aware Routing Protocol), CARP (Context-Aware Routing Protocol), and TARP (Trust-Aware Routing Protocol). SARP uses an efficient service-aware routing approach that aggressively reduces downstream traffic by translating service profiles into efficient paths. CARP supports QoS by dynamically adapting each node's routing behavior and service profile according to the current context of that node, i.e. number of pending queries and number and type of messages to be routed. Finally, TARP achieves high end-to-end reliability through a scalable reputation-based approach in which each node is able to locally estimate the next hop of the most reliable path to the sink. We also propose query optimization techniques that contribute to the efficient execution of queries in SOSANETs. To evaluate the proposed service-oriented architecture, we implemented TinySOA, a prototype SOSANET built on top of TinyOS with uRACER as its routing mechansim. TinySOA is designed as a set of layers with a loose interaction model that enables several cross-layer optimization options. We conducted an evaluation of TinySOA that included a comparison with TinyDB. The obtained empirical results show that TinySOA achieves significant improvements on many aspects including energy consumption, scalability, reliability and response time. / Ph. D.

Ad hoc networks are emerging as a cost-effective, yet, powerful tool for communication. These systems, where networks can emerge and converge on-the-fly, are guided by the forward-looking goals of providing ubiquitous connectivity and constant access to information. Due to power and bandwidth constraints, the vulnerability of the wireless medium, and the multi-hop nature of ad hoc networks, these networks are becoming increasingly complex dynamic systems. Besides, modern radios are empowered to be reconfigurable, which harbors the temptation to exploit the system. To understand the implications of these issues, some of which pose significant challenges to efficient network design, we study topology control using game theory. We develop a game-theoretic framework of topology control that broadly captures the radio parameters, one or more of which can be tuned under the purview of topology control. In this dissertation, we consider two parameters, viz. transmit power and channel, and study the impact of controlling these on the emergent topologies. We first examine the impact of node selfishness on the network connectivity and energy efficiency under two levels of selfishness: (a) nodes cooperate and forward packets for one another, but selfishly minimize transmit power levels and; (b) nodes selectively forward packets and selfishly control transmit powers. In the former case, we characterize all the Nash Equilibria of the game and evaluate the energy efficiency of the induced topologies. We develop a better-response-based dynamic that guarantees convergence to the minimal maximum power topology. We extend our analysis to dynamic networks where nodes have limited knowledge about network connectivity, and examine the tradeoff between network performance and the cost of obtaining knowledge. Due to the high cost of maintaining knowledge in networks that are dynamic, mobility actually helps in information-constrained networks. In the latter case, nodes selfishly adapt their transmit powers to minimize their energy consumption, taking into account partial packet forwarding in the network. This work quantifies the energy efficiency gains obtained by cooperation and corroborates the need for incentivizing nodes to forward packets in decentralized, energy-limited networks. We then examine the impact of selfish behavior on spectral efficiency and interference minimization in multi-channel systems. We develop a distributed channel assignment algorithm to minimize the spectral footprint of a network while establishing an interference-free connected network. In spite of selfish channel selections, the network spectrum utilization is shown to be within 12% of the minimum on average. We then extend the analysis to dynamic networks where nodes have incomplete network state knowledge, and quantify the price of ignorance. Under the limitations on the number of available channels and radio interfaces, we analyze the channel assignment game with respect to interference minimization and network connectivity goals. By quantifying the interference in multi-channel networks, we illuminate the interference reduction that can be achieved by utilizing orthogonal channels and by distributing interference over multiple channels. In spite of the non-cooperative behavior of nodes, we observe that the selfish channel selection algorithm achieves load balancing. Distributing the network control to autonomous agents leaves open the possibility that nodes can act selfishly and the overall system is compromised. We advance the need for considering selfish behavior from the outset, during protocol design. To overcome the effects of selfishness, we show that the performance of a non-cooperative network can be enhanced by appropriately incentivizing selfish nodes. / Ph. D.

Despite recent advances in wireless local area network (WLAN) technologies, today's WLANs still cannot offer the same data rates as their wired counterparts. The throughput problem is further aggravated in multi-hop wireless environments due to collisions and interference caused by multi-hop routing. Because all current IEEE 802.11 physical (PHY) standards divide the available frequency into several orthogonal channels, which can be used simultaneously within a neighborhood, increasing capacity by exploiting multiple channels becomes particularly appealing. To improve the capacity of wireless ad hoc networks by exploiting multiple available channels, I propose three principles that facilitate the design of efficient distributed channel assignment protocols. Distributed channel assignment problems have been proven to be <i>NP</i>-complete and, thus, computationally intractable. Though being a subject of many years of research, distributed channel assignment remains a challenging problem. There exist only a few heuristic solutions, none of which is efficient, especially for the mobile ad hoc environment. However, protocols that implement the proposed design principles are shown to require fewer channels and exhibit significantly lower communication, computation, and storage complexity, compared with existing approaches. As examples, I present two such protocols that build on standard reactive and proactive routing protocols. In addition, I prove the correctness of the algorithms and derive an upper bound on the number of channels required to both resolve collisions and mitigate interference. A new multi-channel medium access control (MC-MAC) protocol is also proposed for multi-hop wireless ad hoc networks. MC-MAC is compatible with the IEEE 802.11 medium access control (MAC) standard and imposes the minimum system requirements among all existing multi-channel MAC protocols. In addition, simulation results show that even with only a single half-duplex transceiver, MC-MAC, by exploiting multiple channels, can offer up to a factor of four improvement in throughput over the IEEE 802.11 MAC protocol. The reduction in delay is even more significant. Therefore, the MC-MAC protocol and the accompanying distributed channel assignment protocols constitute an effective solution to the aforementioned performance problem in a multi-hop wireless network. Finally, I generalize the cross-layer design principle to more general networking functions and present a network architecture to motivate and facilitate cross-layer designs in wireless networks. A literature survey is provided to validate the proposed cross-layer design architecture. Current cross-layer design research can be categorized into two classes: joint-layer design using optimization techniques, and adaptive techniques based on system-profile and/or QoS requirements. Joint-layer design based on optimization techniques can achieve optimal performance, but at the expense of complexity. Adaptive schemes may achieve relatively good performance with less complexity. Nevertheless, without careful design and a holistic view of the network architecture, adaptive schemes may actually cause more damage than benefit. / Ph. D.

As developments in wireless ad hoc networks continue, there is an increasing expectation with regard to supporting content-rich multimedia communications (e.g., video) in such networks, in addition to simple data communications. The recent advances in multiple description (MD) video coding have made it highly suitable for multimedia applications in such networks. In this thesis, we study three important problems regarding multiple description video communications in wireless ad hoc networks. They are multipath routing for MD video, MD video multicast, and joint routing and server selection for MD video in wireless ad hoc networks. In multipath routing for MD video problem, we follow an applicationcentric cross-layer approach and formulate an optimal routing problem that minimizes the application layer video distortion. We show that the optimization problem has a highly complex objective function and an exact analytic solution is not obtainable. However, we find that a metaheuristic approach such as Genetic Algorithms (GAs) is eminently effective in addressing this type of complex cross-layer optimization problems. We provide a detailed solution procedure for the GA-based approach, as well as a tight lower bound for video distortion. We use numerical results to compare this approach to several other approaches and demonstrate its superior performance. In MD video multicast problem, we take the similar application-centric, cross-layer approach as in the multipath routing problem. We propose an MD video multicast scheme where multiple source trees are used. Furthermore, each video description is coded into multiple layers in order to cope with diversity in wireless link bandwidths. Based on this multicast model, we formulate the multicast routing as a combinatorial optimization problem and apply Genetic Algorithm (GA)-based metaheuristic procedure to solove this problem. Performance comparisons with existing approaches show significant gains for a wide range of network operating conditions. In the last problem, we study the important problem of joint routing and server selection for MD video in ad hoc networks. We formulate the task as a combinatorial optimization problem and present tight lower and upper bounds for the achievable distortion. The upper bound also provides a feasible solution to the formulated problem. Our extensive numerical results show that the bounds are very close to each other for all the cases studied, indicating the near-global optimality of the derived upper bounding solution. Moreover, we observe significant gains in video quality achieved by the proposed approach over existing server selection schemes. This justifies the importance of jointly considering routing and server selection for optimal MD video streaming in wireless ad hoc networks. / Master of Science

Ces dernières années, les réseaux multi-sauts sans fil (MHWNs) ont connu une explosion de déploiement en raison de la demande croissante de connectivité continue indépendamment de l'emplacement physique. Les protocoles de transport Internet prédominantes, c.-à-Transmission Control Protocol (TCP), se trouvent face à la dégradation des performances dans MHWNs en raison de les taux élevés de pertes et de défaillance du lien. Plusieurs solutions ont été proposées qui sont basées sur l'estimation de l'état du réseau ou sur l'utilisation de renseignements de la couche MAC (dénommée métriques) dans une manière d’inter-couche pour mieux comprendre l'état du réseau. La première partie de cette thèse fournit une enquête et la définition complète de métriques communs des couches physique, MAC, réseau et transport et fournit ainsi un multi-critères et la classification hiérarchique. Après cela, l'efficacité dans la réflexion des informations de réseau des métriques de la couche MAC est également étudiée dans une façon systématique en simulant des situations différents de réseau et de mesurer les métriques de la couche MAC. Ainsi, le bonne MAC métrique pour le contrôle de congestion qui est couplé avec le niveau de contention de réseau et les pertes provoquées moyen sera découvert. D'après les résultats de l'étude sur l'efficacité, deux nouveaux systèmes de contrôle de débit pour les protocoles de transport sont proposés qui s'adaptent efficacement le débit de source en fonction de l'état du réseau fournie par certains métriques MAC. Grâce à un vaste ensemble de simulations, les performances des systèmes proposées de contrôle de débit dans MHWNs sont examinées approfondie avec des situations de réseau. / In recent years, Multi-hop Wireless Networks (MHWNs) have experienced an explosion of deployment due to the increasing demand for continuous connectivity regardless of the physical location. Internet predominant transport protocols, i.e. Transmission Control Protocol (TCP), face performance degradation in MHWNs because of the high loss and link failure rates. Several solutions have been proposed which are based on network state estimation or use information from MAC layer (called metrics) in a cross-layer manner to better comprehend the network state. The first part of this thesis provides a survey and comprehensive definition of common metrics from Physical, MAC, Network and Transport layers and thus provides a multi-criteria and hierarchical classification. After that, the effectiveness in reflecting network information of MAC metrics is also investigated in a systematic way by simulating various network situations and measuring the MAC metrics. Thus, the good MAC metric for congestion control which is coupled with the network contention level and the medium induced losses will be found out. From the results of the effectiveness study, new rate control schemes for transport protocols are proposed which adapt efficiently the source bit rate depending on the network condition provided by some MAC metrics. Through an extensive set of simulations, the performance of the proposed rate control schemes in MHWNs is investigated thoroughly with several network situations.

Le thème général du sujet tourne autour de l'optimisation inter-couche des réseaux de capteurs basés sur la technologie ultra large bande ULB (UWB, Ultra Wide Band) moyennant des solutions protocolaires permettant d'un côté de répondre au besoin de qualité de service QdS à critères multiples dans les réseaux de capteurs sans fil et d'autre côté d'assurer le partage et l'allocation efficace les ressources disponibles (spectrale et temporelle) ainsi que l'optimisation de la consommation d'énergie dans des tels réseaux. Le domaine d'application cible choisi dans le présent travail est les systèmes de suivi des patients au sein d'un réseau de capteurs déployé en hôpital intelligent (WHSN, Large-scale Wireless Hospital Sensor Network). Dans ce contexte, nous avons proposé le modèle UWBCAS pour assurer le partage des ressources spectrales entre les PANs. Puis, nous avons conçu et implémenté un protocole MAC multi-canal multi-créneau de temps avec support de qualité de service, PMCMTP, pour assurer une allocation conjointe des canaux de fréquence et des créneaux de temps au sein de chaque réseau PAN. Enfin nous avons proposé l'algorithme JSAR qui traite à la fois les problèmes d'ordonnancement des cycles d'activités des membres du réseau dans le but d'optimiser la consommation d'énergie, d'allocation efficace des canaux de fréquence et des créneaux de temps afin d'améliorer le taux d'utilisation des ressources et les performances du réseau et de routage avec support de QdS à critères multiples afin de répondre aux besoins des applications supportées / The general context of the present memory is about the cross-layer optimization of wireless sensors networks based on ultra wide band technology UWB. The proposed solutions ensure the share and the efficient allocation of spectral and temporal resources, the optimization of the energy consumption and the support of multi-constraints quality of services QoS. The most challenging issue is providing a tradeoff between the resource efficiency and the multiconstrained QoS support. For this purpose, we proposed a new Wireless Hospital Sensor Network (WHSN) three-tiered architecture in order to support large-scale deployment and to improve the network performance. Then we designed a channel allocation scheme (UWBCAS,)and a prioritized multi-channel multi-time slot MAC protocol (PMCMTP) to enhance network performance and maximize the resource utilization. Finally, we proposed a joint duty cycle scheduling, resource allocation and multi-constrained QoS routing algorithm (JSAR) which simultaneously combines, a duty cycle scheduling scheme for energy saving, a resource allocation scheme for efficient use of frequency channels and time slots, and an heuristic for multi-constrained routing protocol

Submitted by camilla martins (camillasmmartins@gmail.com) on 2017-03-03T17:43:57Z No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Tese_MecanismoRoteamentoCross-Layer.pdf: 10461389 bytes, checksum: e41ea0b15329c6767cba562bb1de8de1 (MD5) / Approved for entry into archive by Edisangela Bastos (edisangela@ufpa.br) on 2017-03-07T12:41:06Z (GMT) No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Tese_MecanismoRoteamentoCross-Layer.pdf: 10461389 bytes, checksum: e41ea0b15329c6767cba562bb1de8de1 (MD5) / Made available in DSpace on 2017-03-07T12:41:06Z (GMT). No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Tese_MecanismoRoteamentoCross-Layer.pdf: 10461389 bytes, checksum: e41ea0b15329c6767cba562bb1de8de1 (MD5) Previous issue date: 2016-03-18 / CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / A evolução das tecnologias de comunicações sem fio levou à necessidade de fornecer suporte de rede para dados e aplicações de vídeo e, assim, promover o desenvolvimento de novos tipos de configurações de rede adaptadas a estas novas exigências. Redes móveis Ad hoc é um importante tipo de operação de redes que emprega mecanismos que podem permitir uma autoconfiguração dinâmica, o que exige uma maior eficiência dos seus protocolos de roteamento. Esses protocolos também podem ser desafiados devido às falhas de energia que estão se tornando cada vez mais graves em relação às falhas de redes de computadores convencionais. Além disso, a qualidade do fluxo multimídia corresponde a uma premissa fundamental para as redes da próxima geração sem fio e para a Internet do futuro. Esta tese propõe um novo mecanismo de roteamento baseado no paradigma cross-layer para aprimorar os principais protocolos de roteamento, através da inserção de novas métricas em um processo de decisão de inteligência computacional baseado em sistemas Fuzzy, provendo eficiência energética, suporte a gerencia de mobilidade e qualidade de experiência aos dispositivos, escolhendo a melhor rota para o fluxo das redes de computadores. A proposta é avaliada em um simulador de redes, demonstrando sua eficiência através de resultados de rede, de qualidade de experiência e da maximização do tempo de vida da comunicação. / The evolution of wireless communications technologies has led to the need to provide network support for data and video applications and thus promote the development of new types of network configurations adapted to these new requirements. MANET is an important type of operation networks that employs mechanisms that can enable dynamic autoconfiguration, which requires a higher efficiency of its routing protocols. These protocols can also be challenged due to energy failures that are becoming increasingly severe in relation to the common networks failure; furthermore, the quality of the multimedia stream corresponds to a fundamental premise to the next generation wireless networks and the future Internet. This thesis proposes a new routing mechanism based on cross-layer paradigm to enhance the main routing protocols, by inserting new metrics in a computational intelligence decision making based on fuzzy systems, providing energy efficiency, support to manage mobility and quality experience to the devices, choosing the best route for the flow of computer networks. The proposal is evaluated in network simulator, demonstrating its efficiency through network results, quality of experience metrics and maximizing the communication’s lifetime.