Hong-Linh Truong

Aalto University · Department of Computer Science

A long running data-intensive computational application acquires costly computing resources. With the emerging new architectures, like computing systems with multiple nodes of many-core CPUs and accelerators, while domain-specific tools and libraries employed in such an application leverage high parallelism on accelerators for intensive computation...

Optimizing the quality of machine learning (ML) services for individual consumers with specific objectives is crucial for improving consumer satisfaction. In this context, end-to-end ensemble ML serving (EEMLS) faces many challenges in selecting and deploying ensembles of ML models on diverse resources across the edge-cloud continuum. This paper pr...

Deploying end‐to‐end ML applications on edge resources becomes a viable solution to achieve performance and data regulations. With the microservice architecture, these applications can scale dynamically, improving service availability under dynamic workloads. However, orchestrating multiple end‐to‐end ML applications within heterogeneous edge envir...

The Digital Twin (DT) paradigm has been largely adopted for many smart systems in various domains. Due to the heterogeneous and distributed nature of the physical twins, these systems increasingly incorporate disparate security tools, especially those based on service-based AI/ML capabilities. That presents numerous challenges in achieving a compre...

[Context and Motivation] Many recent studies highlight explainability as an important requirement that supports in building transparent, trustworthy, and responsible AI systems. As a result, there is an increasing number of solutions that researchers have developed to assist in the definition of explainability requirements. [Question] We conducted...

The proliferation of data and machine learning (ML) as a service, coupled with advanced federated and distributed training techniques, fosters the development of federated ML marketplaces. One important, but under-researched, aspect is to enable the stakeholder interactions centered around the quality of training and costs in the marketplace and th...

Given a large-scale mobile network with a variety of equipment and radio access networks technologies for an approximate 20 million subscribers, there are many types of data that can be used for big data analytics and machine learning (ML) tasks for network operations, monitoring, and optimization. However, a variety of data is measured, collected,...

Context. The origins of quiet-Sun magnetism (QS) is still under debate and investigating the solar cycle variation observationally in greater detail can provide clues on how to resolve the ensuing controversies. Aims. We investigate the solar cycle variation of the most magnetically quiet regions and their surface gravity oscillation ( f -) mode-in...

This paper presents a novel framework to enhance programmability of the IoT-edge-cloud continuum through the concept of Accelerators, runtime components, techniques, and languages that can be used to optimize resources and services. The framework accommodates rapid change through software composition and elastic adaptation. In particular, elasticit...

The origin of the quiet Sun magnetism is under debate. Investigating the solar cycle variation observationally in more detail can give us clues about how to resolve the controversies. We investigate the solar cycle variation of the most magnetically quiet regions and their surface gravity oscillation ($f$-) mode integrated energy ($E_f$). We use 12...

The maturity of machine learning (ML) development and the decreasing deployment cost of capable edge devices have proliferated the development and deployment of edge ML solutions for critical IoT-based business applications. The combination of edge computing and ML not only addresses the development cost barrier, but also solves the obstacles due t...

The fast growth in the amount of connected devices with computing capabilities in the past years has enabled the emergence of a new computing layer at the Edge. Despite being resource-constrained if compared with cloud servers, they offer lower latencies than those achievable by Cloud computing. The combination of both Cloud and Edge computing para...

The rapid development of IoT (Internet of Things) brings great convenience to people through the utilization of IoT applications, but also brings huge security challenges. Existing IoT security breaches show that many IoT devices have authentication flaws. Although many IoT authentication schemes were proposed, they are not applicable to recent sma...

Identifying mobile apps based on network traffic has multiple benefits for security and network management. However, it is a challenging task due to multiple reasons. First, network traffic is encrypted using an end-to-end encryption mechanism to protect data privacy. Second, user behavior changes dynamically when using different functionalities of...

COVID-19 has turned service-based business continuity into a hot issue, due to the survival of enterprises under long-tailed changes of business caused by various abnormal socioeconomic events and disruptions. We analyze how current techniques enable small and medium enterprises to be resilient and elastic. From observations of service disruptions...

The maturity of machine learning (ML) development and the decreasing deployment cost of capable edge devices have proliferated the development and deployment of edge ML services in developing countries for critical IoT-based business applications. The combination of edge computing and ML not only addresses the development cost barrier but also solv...

Recent years have seen the rapid development and integration of the Internet of Things (IoT) and cloud computing. The market is providing various consumer-oriented smart IoT devices; the mainstream cloud service providers are building their software stacks to support IoT services. With this emerging trend even growing, the security of such smart Io...

As blockchain becomes an essential part of many software systems in the edge and cloud, the developer starts to treat blockchain features like commodity software components that can be integrated into edge and cloud software systems. For the developer it is quite challenging to determine, customize, and evaluate suitable blockchain features for sof...

Using machine learning (ML) services, both service customers and providers need to monitor complex contractual constraints of ML service that are strongly related to ML models and data. Therefore, establishing and monitoring comprehensive ML contracts are crucial in ML serving. This paper demonstrates a set of features and utilities of the QoA4ML f...

Optimizing quality trade-offs in an end-to-end big data science process is challenging, as not only do we need to deal with different types of software components, but also the domain knowledge has to be incorporated along the process. This paper focuses on methods for tackling quality trade-offs in a common data science process for classifying Bui...

Realizing the potential of edge computing and networks connecting the edge and the cloud, researchers from academia and industries have increasingly developed techniques and tools for edge infrastructures and applications. This paper focuses on supporting complex edge application interactions, which span different layers and subsystems in edge-clou...

Important service-level constraints in machine learning (ML) services must be communicated and agreed among relevant stakeholders. Due to the lack of studies and support, it is unclear which and how ML-specific attributes and constraints should be specified and assured in service contracts for ML services. This paper examines service contracts in t...

We have witnessed various degrees of disruption to service-based businesses in the society, caused by the Coronavirus pandemic (COVID-19). This paper studies service-oriented enterprises from the perspective of resilience and elasticity, aiming at uncovering the issues in current service development, maintenance and operation in pandemic ages. We p...

Concerns of robustness, reliability, resilience and elasticity in machine learning (ML) systems are important and they must be considered in trade-off with efficiency factors. However, they need to be supported and optimized in an end-to-end manner, not just for ML models. In this paper we present an approach to architectural design and engineering...

More widespread adoption requires swarms of robots to be more flexible for real-world applications. Multiple challenges remain in complex scenarios where a large amount of data needs to be processed in real-time and high degrees of situational awareness are required. The options in this direction are limited in existing robotic swarms, mostly homog...

Optimizing quality trade-offs in an end-to-end big data science process is challenging, as not only we need to deal with different types of software components but also the domain knowledge has to be incorporated along the process. We focus on methods for tackling quality trade-offs in a common data science process for classifying Building Informat...

The increasing availability of edge and IoT infrastructure-as-a-service allows us to develop lightweight IoT components and deploy them into edge/IoT infrastructures, enabling edge analytics and controls. This paper introduces the development of service contracts for IoT microservices from DevOps perspectives. We analyze stakeholders and present ou...

Internet of Things (IoT) generate huge amount of data in real time. Utilization of such data requires appropriate data storage, analytics and computation techniques so that valuable information can be extracted and immediate actions could be taken place. In this paper, we present real time traffic applications, typical IoT-enabled big data applicat...

In the IoT era, a massive number of smart sensors produce a variety of data at unprecedented scale. Edge storage has limited capacities posing a crucial challenge for maintaining only the most relevant IoT data for edge analytics. Currently, this problem is addressed mostly considering traditional cloud-based database perspectives, including storag...

Realizing the potential of edge computing and fog networks connecting the edge and the cloud, researchers and industries have increasingly developed techniques and tools for testing edge infrastructures and applications. Simulating edge applications and systems plays a crucial role because not everyone can have access to a real-world deployment of...

Incorporating blockchain features into edge services is on the rise. However, there is a lack of frameworks for sharing and recommending knowledge about blockchain software artefacts and deployments for edge services development. In this paper, we present various types of information linking blockchain performance with service deployments at differ...

In the IoT domain, a massive number of smart sensors, devices and equipment produce a variety of data at unprecedented scale. To analyze these produced data for timely decision making, data ana-lytics at the network edge is a promising solution. Nevertheless, unlike scalable cloud-based storage services, edge storage has limited capacities posing a...

A mature Business process is one of the core competencies of an enterprise. Nowadays, there are many process models which are owned by enterprises need to be integrated into new environments, such as state sharing. The new environment contains new demands that are often distributed according to the long tail effect which means it is very expensive...

When provisioning "resources" for applications across edge and cloud infrastructures, most work deals with infrastructural containers and virtual machines (VMs) as resources. Such infrastructural resources can be acquired and scaled in an elastic manner for dynamic requirements from the applications. However, this type of low-level infrastructural...

As blockchain becomes an essential part of many software systems in the edge and cloud, the developer starts to treat blockchain features like commodity software components that can be integrated into edge and cloud software systems. For the developer it is quite challenging in selecting, cus-tomizing and testing suitable blockchain features for so...

Abstract Smart manufacturing is strongly correlated with the digitization of all manufacturing activities. This increases the amount of data available to drive productivity and profit through data-driven decision making programs. The goal of this article is to assist data engineers in designing big data analysis pipelines for manufacturing process...

With the rise of Internet of Things, end-users expect to obtain data from well-connected smart devices and stations through data services being provisioned in distributed architectures. Such services could be aggregated in a number of smart ways to provide the end-users and third-party applications with sophisticated data (e.g., weather data couple...

Dealing with interoperability in the IoT domain is a complex matter that requires various techniques for tackling data, protocol and middleware interoperability. We cannot solve IoT interoperability problems by just developing (new) software components and (semantic) data models. In this tutorial, we will present interoperability techniques for com...

In the context of edge computing, IoT-as-a-Service (IoTaaS) with IoT data hubs and execution services allow IoT tenant applications (apps) to be executed next to IoT devices, enabling edge analytics and controls. However, this brings up new security challenges on controlling tenant apps in IoTaaS, whilst the great potential of IoTaaS can only be re...

Within an IoT Cloud application, various subsystems and layers of IoT, edge and cloud infrastructures are involved and we need to make sure that the involved components and data are interoperable w.r.t. data models, protocols and access policies. Such requirements must be addressed by IoT Cloud applications and platforms. Furthermore, such requirem...

Smart manufacturing is strongly correlated with the digitization of all manufacturing activities. This increases the amount of data available to drive productivity and profit through data-driven decision making programs. The goal of this article is to assist data engineers in designing big data analysis pipelines for manufacturing process data. Thu...

In the context of edge computing, IoT-as-a-Service (IoTaaS) with IoT data hubs and execution services allow IoT tenant applications (apps) to be executed next to IoT devices, enabling edge analytics and controls. However, this brings up new security challenges on controlling tenant apps in IoTaaS, whilst the great potential of IoTaaS can only be re...

presentation on mobile edge cloud analytics at IEEE Cloud 2018

Within an IoT Cloud application, various subsystems and layers of IoT, edge and cloud infrastructures are involved and we need to make sure that the involved components and data are interoperable w.r.t. data models, protocols and access policies. Such requirements must be addressed by IoT Cloud applications and platforms. Furthermore, such requirem...

For predictive maintenance of equipment with Industrial Internet of Things (IIoT) technologies, complex IoT Cloud systems provide strong monitoring and data analysis capabilities for detecting and predicting status of equipment. We need to support complex interactions among different software components and human activities to provide an integrated...

Interoperability for IoT is a challenging problem because it requires us to tackle (i) cross-system interoperability issues at the IoT platform sides as well as relevant network functions and clouds in the edge systems and data centers and (ii) cross-layer interoperability, e.g., w.r.t. data formats, communication protocols, data delivery mechanism...

presentation at Globe-IoT@IC2E

To enhance the competitiveness, companies need continuously improving the capability of timely decision making in collaboration with different enterprises through the whole supply chain, instantly responding to the rapid changing environments. Consequently the challenges are how to enable processes to acquire and react with real-time information fr...

Emerging edge/fog computing models have fostered new types of applications whose software components and dependent services are provisioned across distributed edge and cloud infrastructures. The design of edge cloud systems is complex, thus it is important to understand suitable deployment models and test them. Since edge cloud computing and its de...

The increasing availability of IoT infrastructure-as-a-service not only allows us to easily develop IoT components and deploy them into IoT infrastructures, enabling edge analytics and controls, but also brings challenges for ensuring service contracts between the infrastructures providers and owners of IoT components using the infrastructures. Due...

Many advances have been introduced recently for service-oriented computing and applications (SOCA). The Internet of Things (IoT) has been pervasive in various application domains. Fog/Edge computing models have shown techniques that move computational and analytics capabilities from centralized data centers where most enterprise business services h...

LoRaWAN is a promising network solution for various application domains, especially in developing countries. While its network architecture is highly distributed, the network architecture aims at aggregating data into a centralized location, mainly the cloud-based data center. With such an architecture, we can bring data from distributed sensing so...

With the emerging IoT and Cloud-based networked systems that rely heavily on virtualization technologies, elasticity becomes a dominant system engineering attribute for providing QoS-aware services to their users. Although the concept of elasticity can introduce significant QoS and cost benefits, its implementation in real systems is full of challe...

Systems for big Internet of Things (IoT) data an-alytics are extremely complex. Different software components at different software stacks from different infrastructures and providers are involved in handling different types of data. Various types of incidents may occur during execution of such systems due to problems occurring in software stacks,...

Modern Cyber-Physical Systems (CPS) and Internet of Things (IoT) systems consist of both loosely and tightly interactions among various resources in IoT networks, edge servers and cloud data centers. These elements are being built atop virtualization layers and deployed in both edge and cloud infrastructures. They also deal with a lot of data throu...

Today’s crucial applications in, e.g., smart cities, logistics, health-care and manufacturing rely on complex Internet of Things (IoT) and cloud system infrastructures. Such infrastructures consist of IoT devices, distributed storage, processing, and management services that need to elastic, i.e., adaptable to evolving physical and execution enviro...

This presentation is about reporting experiences and challenges on combining model-driven engineering (MDE) methodologies with elastic execution models to design and test the uncertainty of real-world CPS.