Wearable Cognitive Assistance (WCA) has the potential to revolutionize daily life with real-time, context-aware guidance, but current performance models often overlook the dynamic nature of human-system interactions, leading to inefficiencies in resource allocation and system responsiveness. In this work, we investigate the implications of the correlated nature of human-system interactions through the development of a novel data-driven methodology for the modeling of task execution times in WCA.We apply this methodology to a WCA application previously shown to exhibit second-order effects between system responsiveness and human performance. Our resulting model presents an improvement in up to 30% with respect to traditional first-order approaches, highlighting the importance of capturing complex behavioral dynamics. These findings raise important questions about the design and optimization of WCA systems and the tools that target them: What are the implications of this correlation for resource allocation and system design in real-world deployments? How can our methodology inform the development of more accurate and adaptive models for WCA applications? By exploring these questions, this research aims to contribute to the development of more efficient and effective WCA systems.

Cloud Computing, with its globally-accessible nature and virtually unlimited scalability, has revolutionized our daily lives since its widespread adoption in the early 2000s. It allows us to access our documents anywhere, keep in touch with friends, back up photos, and even remotely control our appliances. Despite this, Cloud Computing has limitations when it comes to novel appli- cations requiring real-time processing or low-latencies. Applications such as Cyber-Physical Systems (CPSs) or mobile eXtended Reality (XR), which in turn also have great transformative potential, are unable to run on the Cloud. 

Edge Computing is emerging as a potential solution to these limitations by bringing computation closer to the edge of the network, thereby reducing latency and enabling real-time decision making. The combination of Edge Computing and modern mobile network technologies such as 5G offers potential for massive deployments of latency-sensitive applications. However, scaling and understanding these deployments poses important challenges such the optimization of latency through multiple processing steps and trade-offs in wireless system choice, protocols, hardware, and algorithms. Existing approaches have so far been unsuccessful in capturing the complex effects arising from the interplay between network and compute in these systems. 

This dissertation addresses the challenge of performance evaluation of Edge Computing and the applications enabled by this paradigm with two key contributions to literature. First, a methodological approach to experimentally studying the trade-offs between system responsiveness and resource consumption in latency-sensitive applications such as CPSs and XR is introduced. These applications and systems feature characteristics, such as tight interaction with the physical world and the involvement of humans, that make them challenging to study through simulated approaches or analytical modeling. The approach presented in this thesis involves therefore the emulation of the client-side workload while maintaining the real server-side process and network stack to retain the realism of network and compute effects. 

Next, an exploration of the requirements for accuracy in the emulation is presented. This work discusses the extent to which accuracy in the emulation can open new avenues for optimization of these systems. To this end, the first-ever realistic model of human timings for a particular class of Mobile Augmented Reality (MAR) applications is provided. The model is combined with a mathematical framework to study the potential for optimization in Edge Computing applications. 

Results indicate that the methodology introduced in this work offers advantages over existing methods by improving efficiency, repeatability, and replicability. By fully integrating workload components into the emulated software domain, this methodology reduces complexity while still capturing complex effects of network and compute factors that are challenging to model. This approach represents thus an important contribution to literature, as it consists of a comprehensive method for the performance evaluation of Edge environments, encompassing both the application and the infrastructure. Furthermore, results from the exploration into the implications of realism in the emulation suggest that incorporating enhanced realism in client-side emulation can enable the implementation of optimization approaches that would otherwise be infeasible. In particular, this work highlights the significance of considering human behavior and reactions in addition to system-related metrics and performance optimizations in the context of MAR. 

Cloud Computing, med sin globalt tillgängliga natur och praktiskt taget obegränsade skalbarhet, har revolutionerat våra dagliga liv sedan dess allmänna antagande i början av 2000-talet. Det gör det möjligt för oss att få tillgång till våra dokument var som helst, hålla kontakt med vänner, säkerhetskopiera foton, och fjärrstyra våra hushållsapparater.  Trots detta har Cloud Computing begränsningar när det gäller nya applikationer som kräver realtidsbehandling eller låg latens. Applikationer som cyberfysiska system (engelska Cyber-Physical Systems (CPSs)) eller mobilt utvidgad verklighet (engelska eXtended Reality (XR)), som i sin tur också har stor omvandlingspotential, kan inte köras på molnet.

Edge Computing framstår som en potentiell lösning på dessa begräns-ningar genom att föra beräkningar närmare kanten av nätverket, vilket minskar latensen och möjliggör beslutsfattande i realtid. Kombinationen av Edge Computing och moderna mobila nätverksteknologier som 5G erbjuder potential för massiva utrullningar av latenskänsliga applikationer.  Men att skala och förstå dessa utrullningar utgör viktiga utmaningar såsom optimering av latens genom flera bearbetningssteg och avvägningar i val av trådlösa system, protokoll, hårdvara och algoritmer. Befintliga metoder har hittills inte lyckats fånga de komplexa effekter som uppstår från samspelet mellan nätverk och datorer i dessa system. Denna avhandling tar upp utmaningen med prestationsutvärdering av Edge Computing och applikationerna som möjliggörs av detta paradigm med två viktiga bidrag till litteraturen. Först introduceras ett metodologiskt tillvägagångssätt för att experimentellt studera kompromisserna mellan systemrespons och resursförbrukning i latenskänsliga applikationer såsom CPSs och XR som körs på Edge Computing. Dessa applikationer och system har egenskaper, såsom tät interaktion med den fysiska världen och inblandning av människor, som gör dem utmanande att studera genom simulerade tillvägagångssätt eller analytisk modellering. Den metod som presenteras i denna avhandling innebär därför emulering av klientsidans arbetsbelastning samtidigt som den verkliga serversidans process och nätverksstacken bibehålls för att behålla realismen i nätverks- och datoreffekter.

Därefter presenteras en utforskning av kraven på precision i emuleringen. Detta arbete diskuterar i vilken utsträckning precision i emuleringen kan öppna nya vägar för optimering av dessa system. För detta ändamål tillhandahålls den första realistiska modellen av mänskliga tidsbeteenden för en särkild klass av mobil förstärkt verklighet (engelska Mobile Augmented Reality (MAR)). Modellen kombineras med ett matematiskt ramverk för att studera potentialen för optimering i Edge Computing applikationer.

Resultaten indikerar att den metod som introducerats i detta arbete erbjuder fördelar jämfört med befintliga metoder genom att förbättra effektiviteten, repeterbarheten och replikerbarheten. Genom att helt integrera arbetsbelastningskomponenter i den emulerade mjukvarudomänen, minskar denna metodik komplexiteten samtidigt som den fångar komplexa effekter av nätverks- och beräkningsfaktorer som är utmanande att modellera. Detta tillvägagångssätt representerar således ett viktigt bidrag till litteraturen, eftersom det består av en omfattande metod för prestandautvärdering av Edge Computing-miljöer, som omfattar både applikationen och infrastrukturen. Dessutom tyder resultat från utforskningen av implikationerna av precision i emuleringen att inkorporering av förbättrad precision i klientsideemulering kan möjliggöra implementering av optimeringsmetoder som annars skulle vara omöjliga. Särskilt framhåller detta arbete betydelsen av att överväga mänskligt beteende och reaktioner utöver systemrelaterade mätvärden och prestandaoptimeringar i samband med MAR.

This paper presents ExPECA, an edge computing and wireless communication research testbed designed to tackle two pressing challenges: comprehensive end-to-end experimentation and high levels of experimental reproducibility. Leveraging OpenStack-based Chameleon Infrastructure (CHI) framework for its proven flexibility and ease of operation, ExPECA is located in a unique, isolated underground facility, providing a highly controlled setting for wireless experiments. The testbed is engineered to facilitate integrated studies of both communication and computation, offering a diverse array of Software-Defined Radios (SDR) and Commercial Off-The-Shelf (COTS) wireless and wired links, as well as containerized computational environments. We exemplify the experimental possibilities of the testbed using OpenRTiST, a latency-sensitive, bandwidthintensive application, and analyze its performance. Lastly, we highlight an array of research domains and experimental setups that stand to gain from ExPECA's features, including closed-loop applications and time-sensitive networking.

Experimental research on wireless networking in combination with edge and cloud computing has been the subject of explosive interest in the last decade. This development has been driven by the increasing complexity of modern wireless technologies and the extensive softwarization of these through projects such as a Open Radio Access Network (O-RAN). In this context, a number of small- to mid-scale testbeds have emerged, employing a variety of technologies to target a wide array of use-cases and scenarios in the context of novel mobile communication technologies such as 5G and beyond-5G. Little work, however, has yet been devoted to developing a standard framework for wireless testbed automation which is hardwareagnostic and compatible with edge- and cloud-native technologies. Such a solution would simplify the development of new testbeds by completely or partially removing the requirement for custom management and orchestration software. In this paper, we present the first such mostly hardwareagnostic wireless testbed automation framework, Ainur. It is designed to configure, manage, orchestrate, and deploy workloads from an end-to-end perspective. Ainur is built on top of cloudnative technologies such as Docker, and is provided as FOSS to the community through the KTH-EXPECA/Ainur repository on GitHub. We demonstrate the utility of the platform with a series of scenarios, showcasing in particular its flexibility with respect to physical link definition, computation placement, and automation of arbitrarily complex experimental scenarios.

As the number of cyber-physical systems rises, it becomes increasingly crucial to study Networked Control Systems (NCSs) combining control communication co-design. This nature of NCSs has led to task-specific approaches to research, creating a dearth of generalizable, repeatable, and scalable experimentation. Further, with the advent of edge computing solutions, it is of paramount importance to explore its relevance in such applications. In this work, we present CLEAVE, a novel, completely software-based framework for repeatable and scalable experimentation in edge native NCSs. Our approach is based on the emulation of physical plants communicating over a real network with software-based controllers. CLEAVE is designed and built for the edge, using Python3 and with full compatibility with industry-standard containerization solutions. Although designed for single-loop emulations, the flexibility afforded by the aforementioned characteristics allow our framework to be adapted to a multitude of complex scenarios.

We validate CLEAVE using an initial implementation of an inverted pendulum NCS. Our results showcase the utility of the tool as a repeatable, extensible, and scalable solution to NCS performance evaluation and benchmarking on the Edge.

Wearable cognitive assistants (WCA) are anticipated to become a widely-used application class, in conjunction with emerging network infrastructures like 5G that incorporate edge computing capabilities. While prototypical studies of such applications exist today, the relationship between infrastructure service provisioning and its implication for WCA usability is largely unexplored despite the relevance that these applications have for future networks. This paper presents an experimental study assessing how WCA users react to varying end-to-end delays induced by the application pipeline or infrastructure. Participants interacted directly with an instrumented task-guidance WCA as delays were introduced into the system in a controllable fashion. System and task state were tracked in real time, and biometric data from wearable sensors on the participants were recorded. Our results show that periods of extended system delay cause users to correspondingly (and substantially) slow down in their guided task execution, an effect that persists for a time after the system returns to a more responsive state. Furthermore, the slow-down in task execution is correlated with a personality trait, neuroticism, associated with intolerance for time delays. We show that our results implicate impaired cognitive planning, as contrasted with resource depletion or emotional arousal, as the reason for slowed user task executions under system delay. The findings have several implications for the design and operation of WCA applications as well as computational and communication infrastructure, and additionally for the development of performance analysis tools for WCA.

Many emerging mobile applications, including augmented reality (AR) and wearable cognitive assistance (WCA), aim to provide seamless user interaction. However, the complexity of benchmarking these human-in-the-loop applications limits reproducibility and makes performance evaluation difficult. In this paper, we present EdgeDroid, a benchmarking suite designed to reproducibly evaluate these applications.Our core idea rests on recording traces of user interaction, which are then replayed at benchmarking time in a controlled fashion based on an underlying model of human behavior. This allows for an automated system that greatly simplifies benchmarking large scale scenarios and stress testing the application.Our results show the benefits of EdgeDroid as a tool for both system designers and application developers.

Benchmarking human-in-the-loop appli-cations running on edge computing in-frastructure is complex given their nature,which heavily depends on the actions takenby the human user. This limits reproducibil-ity as well as feasibility of performance eval-uations. We propose a methodology andpresent a benchmarking suite that can ad-dress these challenges. Our core idea restson recording traces of these applicationswhich are played out in a controlled fashionbased on an underlying model of human be-havior. The traces are exposed to the origi-nal backend compute process of the respec-tive human-in-the-loop application, gener-ating realistic feedback. This allows for anautomated system which greatly simplifiesbenchmarking large scale scenarios.

Wearable Cognitive Assistance (WCA) applications present a challenge to benchmark and characterize due to their human-in-the-loop nature. Employing user testing to optimize system parameters is generally not feasible, given the scope of the problem and the number of observations needed to detect small but important effects in controlled experiments. Considering the intended mass-scale deployment of WCA applications in the future, there exists a need for tools enabling human-independent benchmarking.We present in this paper the first model for the complete end-to-end emulation of humans in WCA. We build this model through statistical analysis of data collected from previous work in this field, and demonstrate its utility by studying application task durations. Compared to first-order approximations, our model shows a ~36% larger gap between step execution times at high system impairment versus low. We further introduce a novel framework for stochastic optimization of resource consumption-responsiveness tradeoffs in WCA, and show that by combining this framework with our realistic model of human behavior, significant reductions of up to 50% in number processed frame samples and 20% in energy consumption can be achieved with respect to the state-of-the-art.