Internet of Things (IoT) is a system of interrelated computing devices with the ability to transfer data over the network and collected by the applications that rely on fresh information, where the freshness of data can be measured by a metric called Age of Information (AoI). Age of Information is the time that is measured by the receiving node from the time the data has generated at the source. It is an important metric for many IoT applications such as, collecting data from temperature sensors, pollution rates in a specific city. However, the bottleneck problem occurs at sensors because they are constrained devices in terms of energy (power via battery), and also have limited memory and computational power. Therefore, they cannot serve many requests at the same time and thus, it will decrease the information quality which means more unnecessary aging. As a result, we suggest as a solution a distributed system that takes into account the AoI transmitted by the sensors so that IoT applications will receive the expected information quality. This thesis describes the three algorithms that can be used tobuild and test three different topologies. The first algorithm builds a Random graph while second and thirds algorithms shapes Clustered and Hybrid graphs respectively. For testing, we use Python based SimPy package which is a process-based discrete-event simulation framework. Finally, we compare Random, Clustered and Hybrid graphs results. Overall, the Hybrid graph delivers more fresh information than other graphs. / Internet of Things (IoT) är ett system med sammanhängande datorenheter med förmågan att överföra data över nätverket och samlas in av applikationer som förlitar sig på ny information, där datorns färskhet kan mätas med en metrisk som kallas Age of Information (AoI ). Age of Information är den tid som mäts av den mottagande noden från den tid datan har genererat vid källan. Det är en viktig metrisk för många IoT-applikationer, till exempel att samla in data från temperatursensorer, föroreningar i en specifik stad. Flaskhalsproblemet uppstår emellertid vid sensorer eftersom de är begränsade enheter i termer av energi (ström via batteri), och också har begränsat minne och beräkningskraft. Därför kan de inte betjäna många förfrågningar samtidigt och det kommer därför att minska informationskvaliteten vilket innebär mer onödigt åldrande. Som ett resultat föreslår vi som en lösning ett distribuerat system som tar hänsyn till AoI som sänds av sensorerna så att IoT-applikationer får den förväntade informationskvaliteten. Den här avhandlingen beskriver de tre algoritmerna som kananvändas för att bygga och testa tre olika topologier. Den första algoritmen bygger ett slumpmässigt diagram medan andra och tredjedels algoritmer formar Clustered respektive hybriddiagram. För testning använder vi ett Python-baserat SimPy-paket somär en processbaserad diskret händelsimuleringsram. Slutligen jämför vi slumpmässiga, klusterade och hybriddiagramresultat. Sammantaget ger hybridgrafen mer ny information än andra grafer.

Um Systeme der fünften Generation zellularer Kommunikationsnetze (5G) zu ermöglichen, sind Energie effiziente Architekturen erforderlich, die eine zuverlässige Serviceplattform für die Bereitstellung von 5G-Diensten und darüber hinaus bieten können. Device Enhanced Edge Computing ist eine Ableitung des Multi-Access Edge Computing (MEC), das Rechen- und Speicherressourcen direkt auf den Endgeräten bereitstellt. Die Bedeutung dieses Konzepts wird durch die steigenden Anforderungen von rechenintensiven Anwendungen mit extrem niedriger Latenzzeit belegt, die den MEC-Server allein und den drahtlosen Kanal überfordern. Diese Dissertation stellt ein Berechnungs-Auslagerungsframework mit Berücksichtigung von Energie, Mobilität und Anreizen in einem gerätegestützten MEC-System mit mehreren Benutzern und mehreren Aufgaben vor, das die gegenseitige Abhängigkeit der Aufgaben sowie die Latenzanforderungen der Anwendungen berücksichtigt. / To enable fifth generation cellular communication network (5G) systems, energy efficient architectures are required that can provide a reliable service platform for the delivery of 5G services and beyond. Device Enhanced Edge Computing is a derivative of Multi-Access Edge Computing (MEC), which provides computing and storage resources directly on the end devices. The importance of this concept is evidenced by the increasing demands of ultra-low latency computationally intensive applications that overwhelm the MEC server alone and the wireless channel. This dissertation presents a computational offloading framework considering energy, mobility and incentives in a multi-user, multi-task device-based MEC system that takes into account task interdependence and application latency requirements.

With the development of 5G technology and edge computing, more and more network application services have been migrated to the cloud network in order to improve the performance, availability and ensure Quality of Service. Edge computing has essentially changed the service deployment model and reduce the latency further for better customer experience, which is realized by deploying network service replicas in geographically distributed edge sites. However, how to discover edge application servers and select a proper instance to serve the edge users becomes an important research topic. This master thesis project addresses the problem by leveraging DNS based service selection mechanism, designing and implementing stable match based service selection algorithms with the aim of minimizing latency between edge users and services and balance the load among edge sites, and integrating the solutions by RESTful APIs. To evaluate the performance of the service selection algorithms, a set of experiments are carried on different simulated topologies with different traffic pattern. The experimental results show that the stable match algorithm and its variants can significantly reduce the average latency by up to 50% compared to traditional approaches, while the enhanced stable match based algorithms are able to have the same load balancing effect with the widely used Round Robin algorithm. / Med utvecklingen av 5G-teknik och edge computing har fler nätverkstjänster migrerats till molnätet för att förbättra prestanda, tillgänglighet och säkerställa servicekvalitet. Edge computing har i huvudsak förändrat tjänster distribution modellen och minskat latensen ytterligare för bättre kundupplevelse, vilket realiseras genom att distribuera nätverkstjänstreplikat på geografiskt distribuerade kantsajter. Hur man upptäcker kantappservrar och väljer en rätt instans för att betjäna kantanvändarna blir dock ett viktigt forskningsämne. Detta projekt löser problemet genom att utnyttja DNS-baserad mekanism för tjänstval, designa och implementera stabila matchbaserade algoritmer för tjänsteval i syfte att minimera latens mellan kantanvändare och tjänster och balansera belastningen mellan kantsajter och integrera lösningarna med RESTful API:er. För att utvärdera prestandan för algoritmerna för val av tjänster utförs en uppsättning experiment på olika simulerade topologier med olika trafikmönster. De experimentella resultaten visar att den stabila matchningsalgoritmen och dess varianter avsevärt kan minska den genomsnittliga latensen med upp till 50% jämfört med traditionella metoder, medan de förbättrade stabila matchbaserade algoritmerna kan ha samma belastningsbalanseringseffekt med den mycket använda Round Robin algoritm.

Edge computing emerged as an attractive method of distributing computational resources in a network. When compared with cloud computing, edge computing presents a number of key benefits which include improved response times, scalability, privacy, and redundancy. This makes edge computing desirable for use in mobile robotics, in which low response times and redundancy are key issues. This thesis work will cover the design and implementation of a general-purpose edge orchestrator, that can support a wide range of domains due to being built around the concept of modularity. An edge orchestrator is a program that manages an edge network by analyzing the edge network and the requirements of devices within that network, then optimizing how the computational resources are distributed within the devices in the network. Modules have been designed and implemented on top of the orchestrator that allow for optimizations specific to mobile robotics. A proof of concept module was designed to optimize for latency which was compared with an external algorithm that seeks to optimize for latency as well. Both were implemented on the orchestrator and an evaluation was performed to compare both approaches. It was found that the module designed in this thesis is better suited for optimizing for latency. LXD was chosen to be used for software packaging which is a container-based software packaging solution. A software packaging solution is used to package software which would be deployed by the orchestrator. The choice of LXD is analyzed through an evaluation procedure that compares it with Docker, which is another container-based software packaging solution. It was found that LXD produces containers of smaller size but required more time to generate those containers, when compared with Docker. It was also found that LXD container images exhibited better performance than the Docker ones for software which is not I/O heavy. It was decided through this evaluation that LXD was a better choice for the orchestrator. / Edge computing är en attraktiv metod för distribution av beräkningsresurser i ett nätverk. Jämfört med molnberäkningar har edge computing ett antal viktiga fördelar som inkluderar förbättrade svarstider, skalbarhet, integritet och redundans. Detta gör edge computing önskvärt för användning i mobil robotik, där låga svarstider och redundans är viktiga frågor. Detta examensarbete täcker min design och implementering av en generell edge-orkestrerare, som kan stödja ett brett spektrum av domäner eftersom den är byggd på ett modulärt sätt. En edge-orkestrerare är ett program som hanterar ett edge-nätverk genom att analysera edge-nätverket och kraven på enheter inom det nätverket, för att sedan optimera hur beräkningsresurserna fördelas över enheterna i nätverket. Jag har utformat och implementerat moduler ovanpå orkestratorn som möjliggör optimeringar specifika för mobil robotik. Jag designade också en koncepttest-modul för att optimera för latens, vilken jag jämförde med en extern algoritm som även den försöker optimera för latens. Jag implementerade båda på orkestratorn och utförde en utvärdering för att jämföra båda metoderna. Resultaten visar att modulen utformad i detta examensarbete är bättre lämpad för att optimera för latens. För mjukvarupaketering valde jag att använda LXD, vilket är en containerbaserad mjukvarupaketeringslösning. Dess syfte är att paketera programvara som ska distribueras av orkestratorn. Jag analyserade valet av LXD genom ett utvärderingsförfarande som jämför det med Docker, som är en annan containerbaserad mjukvarupaketeringslösning. Jag fann att LXD producerar mindre containrar, men krävde mer tid för att generera dessa containrar jämfört med Docker. Jag fann också att LXD-containerbilder visade bättre prestanda än Docker-bilderna för programvara som inte är I/O-intensiv. Jag fann genom denna utvärdering att LXD var ett bättre val för orkestratorn.

One of the main challenges in the Multi-access Edge Computing (MEC) issteering traffic from clients to the nearest MEC instances. If the nearest MECfails, a failover mechanism should provide mitigation by steering the trafficto the next nearest MEC. There are two conventional approaches to solve thisproblem, i.e., GeoDNS and Internet Protocol (IP) anycast. GeoDNS is notfailover friendly because of the Domain Name System (DNS) cache lifetime.Moreover, the use of a recursive resolver may inaccurately translate the IPaddress to its geolocation. Thus, this thesis studies and proposes a highlyavailable MEC platform leveraging IP anycast. We built a proof-of-conceptusing Kubernetes, MetalLB, and a custom health-checker running on theGNS3 network emulator. We measured latency, failure percentage, and MeanTime To Repair (MTTR) to observe the system’s behavior. The performanceevaluation of the proposed solution shows an average recovery time betterthan one second. The number of failed requests and latency overhead growslinearly as the failover time and latency between two MECs increases. Thisthesis demonstrates the effectiveness of IP anycast for MEC applications tosteer the traffic to the nearest MEC instance and to enhance resiliency withminor overhead. / n av de största utmaningarna i Multi-access Edge Computing (MEC) är attstyra trafiken från klienter till närmaste MEC instanser. Om den närmasteMEC misslyckas, bör en failover-mekanism ge begränsning genom att styratrafiken till nästa närmaste MEC. Det finns två konventionella metoder för attlösa detta problem, dvs GeoDNS och IP anycast. GeoDNS är inte failovervänligtpå grund av DNS-cache-livslängd. Dessutom kan användningen aven rekursiv upplösare felaktigt översätta IP-adressen till dess geolokalisering.Således studerar och föreslår denna avhandling en mycket tillgänglig MEC-plattform som utnyttjar IP anycast. Vi byggde ett proof-of-concept medKubernetes, MetalLB och en anpassad hälsokontroll som körs på GNS3-nätverksemulatorn. Vi mätte latens, felprocent och Mean Time To Repair(MTTR) för att observera systemets beteende. Prestationsutvärderingen avden föreslagna lösningen visar en genomsnittlig återhämtningstid som ärbättre än en sekund. Antalet misslyckade förfrågningar och latensomkostnaderväxer linjärt när failover-tiden och latensen mellan två MEC ökar. Den häravhandlingen visar effektiviteten hos IP anycast för MEC-applikationer för attstyra trafiken till närmaste MEC instans och för att förbättra elasticiteten medmindre overhead.

Artificiell intelligens utvecklas i snabb takt, och objektdetektering har blivit en central komponent inom detta område. Objektdetektering möjliggör att automatiserade system på ett noggrant sätt kan identifiera och lokalisera objekt i bilder. En av de mest framstående metoderna för detta ändamål är YOLOv5 (You Only Look Once, version 5), känd för sin snabbhet och effektivitet i realtidsapplikationer. Implementeringen av sådan avancerad teknologi på mindre enheter som Raspberry Pi 4 är utmaningar, främst till följd av begränsad processorkraft och energitillgång på dessa små enheter. Denna avhandling undersöker den optimala användningen av YOLOv5- modellen med hänsyn till energieffektivitet och latens i kommunikationen. Dessa aspekter är särskilt kritiska för enheter som kräver hög effektivitet, exempelvis smartphones, drönare och andra portabla enheter. Studien jämför två huvudsakliga tillvägagångssätt: bearbetning direkt på enheten (in-node) och distans utförande på en server. Genom att välja en lämplig metod för processkörning påverkas effektiviteten av objektdetektering i praktiska tillämpningar. Att bearbeta data direkt på enheten kan ge fördelar i form av snabbare svarstid och bättre integritet, eftersom det undviker att skicka data över nätverket. Dock kan detta öka energiförbrukningen och ökad belastning på enheten. Å andra sidan kan remote process, som utnyttjar kraftfulla datorer, förbättra prestandan och minska belastningen på enheten, men detta kan leda till ökad latens och potentiella integritetsproblem. Genom att använda resurser från remote-servern kan arbetsbelastningen på enheter som Raspberry Pi minskas, vilket resulterar i förbättrad energieffektivitet och latens över samtliga testade upplösningar. / Artificial intelligence is advancing quickly, and object detection has become a key part of this field. Object detection helps automated systems recognise and object detecting pictures very accurately. One of the best methods for this is YOLOv5 (You Only Look Once, version 5), known for working fast and well in real-time uses. However, using such sophisticated technology on smaller devices like the Raspberry Pi 4 can be challenging. These challenges come mainly from limited processing power and energy availability on such small devices. This thesis explores the best way to use the YOLOv5 model while considering energy efficiency and latency between communication. These aspects are crucial when devices need to be efficient, like smartphones, drones, or other portable devices. The study compares two main ways to set up the system: processing directly on the device (in-node) and processing remotely on a server or in the cloud. Choosing where to process the data affects the effectiveness of object detection in real-world applications. Processing on the device can be better for privacy and speed since it does not need to send data over a network. However, this might use more energy and put more strain on the device. On the other hand, processing remotely can use powerful computers to improve performance and reduce the load on the device, but it might make things slower and raise privacy issues. By using remote server resources, the workload in single-processing devices like Rasberry Pi is drastically reduced, which shows better energy efficiency and latency in all test resolutions.

The Internet of Things is a recent computing paradigm, de- fined by networks of highly connected things – sensors, actuators and smart objects – communicating across networks of homes, buildings, vehicles, and even people. The Internet of Things brings with it a host of new problems, from managing security on constrained devices to processing never before seen amounts of data. While cloud computing might be able to keep up with current data processing and computational demands, it is unclear whether it can be extended to the requirements brought forth by Internet of Things. Fog computing provides an architectural solution to address some of these problems by providing a layer of intermediary nodes within what is called an edge network, separating the local object networks and the Cloud. These edge nodes provide interoperability, real-time interaction, routing, and, if necessary, computational delegation to the Cloud. This paper attempts to evaluate Go, a distributed systems language developed by Google, in the context of requirements set forth by Fog computing. Similar methodologies of previous literature are simulated and benchmarked against in order to assess the viability of Go in the edge nodes of Fog computing architecture.

<div>The Internet has substantially embraced mobility since last decade. Cellular data network carries majority of Internet mobile access traffic and become the de facto solution of accessing Internet in mobile fashion, while many clean-slate Internet mobility solutions were proposed but none of them has been largely deployed. Internet mobile users increasingly concern more about their privacy as both researches and real-world incidents show leaking of communication and location privacy could lead to serious consequences. Just the communication itself between mobile user and their peer users or websites could leak considerable privacy of mobile user, such as location history, to other parties. Additionally, comparing to ordinary Internet access, connecting through cellular network yet provides equivalent connection stability or longevity.</div><div><br></div><div>In this research we proposed a novelty paradigm that leverages concurrent far-side proxies to maximize network location privacy protection and minimize interruption and performance penalty brought by mobility. To avoid the deployment feasibility hurdle we also investigated the root causes impeding popularity of existing Internet mobility proposals and proposed guidelines on how to create an economical feasible solution for this goal. Based on these findings we designed a mobility support system offered as a value-added service by mobility service providers and built on elastic infrastructure that leverages various cloud aided designs, to satisfy economic feasibility and explore the architectural trade-offs among service QoS, economic viability, security and privacy. </div>

Submitted by Caroline Xavier (caroline.xavier@pucrs.br) on 2017-11-14T10:44:09Z No. of bitstreams: 1 DIS_MATHEUS_CRESPI_SCHENFELD_COMPLETO.pdf: 6989470 bytes, checksum: 4a16f12e8953d43da2cb18cc63c6119a (MD5) / Approved for entry into archive by Caroline Xavier (caroline.xavier@pucrs.br) on 2017-11-14T10:44:28Z (GMT) No. of bitstreams: 1 DIS_MATHEUS_CRESPI_SCHENFELD_COMPLETO.pdf: 6989470 bytes, checksum: 4a16f12e8953d43da2cb18cc63c6119a (MD5) / Made available in DSpace on 2017-11-14T10:44:39Z (GMT). No. of bitstreams: 1 DIS_MATHEUS_CRESPI_SCHENFELD_COMPLETO.pdf: 6989470 bytes, checksum: 4a16f12e8953d43da2cb18cc63c6119a (MD5) Previous issue date: 2017-03-23 / Internet of Things (IoT) is considered a computational evolution that advocates the existence of a large number of physical objects embedded with sensors and actuators, connected by wireless networks and communicating through the Internet. From the beginning of the concept to the present day, IoT is widely used in the various sectors of industry and also in academia. One of the needs encountered in these areas was to be connected to IoT devices or subsystems throughout the world. Thus, cloud computing gains space in these scenarios where there is a need to be connected and communicating with a middleware to perform the data processing of the devices. The concept of cloud computing refers to the use of memory, storage and processing of shared resources, interconnected by the Internet. However, IoT applications sensitive to communication latency, such as medical emergency applications, military applications, critical security applications, among others, are not feasible with the use of cloud computing, since for the execution of all calculations and actions messaging between devices and the cloud is required. Solving this limitation found in the use of cloud computing, the concept of fog computing arises and whose main idea is to create a federated processing layer, still in the local network of the computing devices of the ends of the network. In addition to fog computing, there is also edge computing operating directly on the devices layer, performing some kind of processing, even with little computational complexity, in order to further decrease the volume of communication, besides collaborating to provide autonomy in decision making yet in the Things layer. A major challenge for both fog and edge computing within the IoT scenario is the definition of a system architecture that can be used in different application domains, such as health, smart cities and others. This work presents a system architecture for IoT devices capable of enabling data processing in the devices themselves or the closest to them, creating the edge computing layer and fog computing layer that can be applied in different domains, improving Quality of Services (QoS) and autonomy in decision making, even if the devices are temporarily disconnected from the network (offline). The validation of this architecture was done within two application scenarios, one of public lighting in smart city environment and another simulating an intelligent agricultural greenhouse. The main objectives of the tests were to verify if the use of the concepts of edge and fog computing improve system efficiency compared to traditional IoT architectures. The tests revealed satisfactory results, improving connection times, processing and delivery of information to applications, reducing the volume of communication between devices and core middleware, and improving communications security. It also presents a review of related work in both academia and industry. / Internet das Coisas (IoT) ? considerada uma evolu??o computacional que preconiza a exist?ncia de uma grande quantidade de objetos f?sicos embarcados com sensores e atuadores, conectados por redes sem fio e que se comunicam atrav?s da Internet. Desde o surgimento do conceito at? os dias atuais, a IoT ? amplamente utilizada nos diversos setores da ind?stria e tamb?m no meio acad?mico. Uma das necessidades encontradas nessas ?reas foi a de estar conectado com dispositivos ou subsistemas de IoT espalhados por todo o mundo. Assim, cloud computing ganha espa?o nesses cen?rios, onde existe a necessidade de estar conectado e se comunicando com um middleware para realizar o processamento dos dados dos dispositivos. O conceito de cloud computing refere-se ao uso de mem?ria, armazenamento e processamento de recursos compartilhados, interligados pela Internet. No entanto, aplica??es IoT sens?veis ? lat?ncia de comunica??o, tais como, aplica??es m?dico-emergenciais, aplica??es militares, aplica??es de seguran?a cr?tica, entre outras, s?o invi?veis com o uso de cloud computing, visto que para a execu??o de todos os c?lculos e a??es ? necess?ria a troca de mensagens entre dispositivos e nuvem. Solucionando essa limita??o encontrada na utiliza??o de cloud computing, surge o conceito de fog computing, cuja ideia principal ? criar uma camada federada de processamento ainda na rede local dos dispositivos de computa??o das extremidades da rede. Al?m de fog computing tamb?m surge edge computing operando diretamente na camada dos dispositivos, realizando algum tipo de processamento, mesmo que de pouca complexidade computacional, a fim de diminuir ainda mais o volume de comunica??o, al?m de colaborar para prover autonomia na tomada de decis?es ainda na camada das coisas. Um grande desafio tanto para fog quanto para edge computing dentro do cen?rio de IoT ? a defini??o de uma arquitetura de sistema que possa ser usada em diferentes dom?nios de aplica??o, como sa?de, cidades inteligentes entre outros. Esse trabalho apresenta uma arquitetura de sistema para dispositivos IoT capaz de habilitar o processamento de dados nos pr?prios dispositivos ou o mais pr?ximo deles, criando a camada de edge e fog computing que podem ser aplicadas em diferentes dom?nios, melhorando a Qualidade dos Servi?os (QoS) e autonomia na tomada de decis?o, mesmo se os dispositivos estiverem temporariamente desconectados da rede (offline). A valida??o dessa arquitetura foi feita dentro de dois cen?rios de aplica??o, um de ilumina??o p?blica em ambiente de IoT e outro simulando uma estufa agr?cola inteligente. Os principais objetivos das execu??es dos testes foram verificar se a utiliza??o dos conceitos de edge e fog computing melhoram a efici?ncia do sistema em compara??o com arquiteturas tradicionais de IoT. Os testes revelaram resultados satisfat?rios, melhorando os tempos de conex?o, processamento e entrega das informa??es ?s aplica??es, redu??o do volume de comunica??o entre dispositivos e core middleware, al?m de melhorar a seguran?a nas comunica??es. Tamb?m ? apresentada uma revis?o de trabalhos relacionados tanto no meio acad?mico como no da ind?stria.

abstract: Internet of Things (IoT) is emerging as part of the infrastructures for advancing a large variety of applications involving connections of many intelligent devices, leading to smart communities. Due to the severe limitation of the computing resources of IoT devices, it is common to offload tasks of various applications requiring substantial computing resources to computing systems with sufficient computing resources, such as servers, cloud systems, and/or data centers for processing. However, this offloading method suffers from both high latency and network congestion in the IoT infrastructures. Recently edge computing has emerged to reduce the negative impacts of tasks offloading to remote computing systems. As edge computing is in close proximity to IoT devices, it can reduce the latency of task offloading and reduce network congestion. Yet, edge computing has its drawbacks, such as the limited computing resources of some edge computing devices and the unbalanced loads among these devices. In order to effectively explore the potential of edge computing to support IoT applications, it is necessary to have efficient task management and load balancing in edge computing networks. In this dissertation research, an approach is presented to periodically distributing tasks within the edge computing network while satisfying the quality-of-service (QoS) requirements of tasks. The QoS requirements include task completion deadline and security requirement. The approach aims to maximize the number of tasks that can be accommodated in the edge computing network, with consideration of tasks’ priorities. The goal is achieved through the joint optimization of the computing resource allocation and network bandwidth provisioning. Evaluation results show the improvement of the approach in increasing the number of tasks that can be accommodated in the edge computing network and the efficiency in resource utilization. / Dissertation/Thesis / Doctoral Dissertation Computer Engineering 2018