Emerging scenarios for the “Internet of Things” (IoT) require a dedicated software defined network over the conventional communication network provided by the different service providers and free to use communication methodologies. These IoT networks have their own dedicated requirements, based on the different stakeholders involved in it, which can be realized via dynamic context-based authentication, authorization and accounting (AAA). This AAA needs to be envisaged in a much larger perspective than the current perspective in telecom networks. As part of this study, we have identified a few external stakeholders, who are domain and IoT experts and discussed the various requirements, scenarios and change scenarios for the dedicated IoT networks. Relying on Zachman’s framework, a reference architecture that we call as “Smart AAA agent for dedicated IoT network” is presented to the domain experts and evaluated against their scenarios utilizing a scenario-based software architecture analysis method. The scenarios discussed and utilized for the analysis encompass two ends of the IoT spectrum of requirements. The medical domain scenarios have critical IoT perspective as lives and health of patients is involved, while the enterprise IoT scenarios involve huge scalability and monetizability aspect, which is very important for the industry. With this reference architecture, we demonstrate a system capable of providing a software defined network fulfilling the requirements of a dedicated IoT network as enlisted in scenarios by the external stakeholders. Furthermore, this proposed reference architecture is evaluated with a software architect and matured to its current state and made available for any future research, development or standardization for 5G and next generation networks for the Internet of Things.

Advances in 5G and the Internet of Things (IoT) have to cater to the diverse and varying needs of different stakeholders, devices, sensors, applications, networks, and access technologies that come together for a dedicated IoT network for a synergistic purpose. Therefore, there is a need for a solution that can assimilate the various requirements and policies to dynamically and intelligently orchestrate them in the dedicated IoT network. Thus we identify and describe a representative industry-relevant use case for such a smart and adaptive environment through interviews with experts from a leading telecommunication vendor. We further propose and evaluate candidate architectures to achieve dynamic and intelligent orchestration in such a smart environment using a systematic approach for architecture design and by engaging six senior domain and IoT experts. The candidate architecture with an adaptive and intelligent element (“Smart AAA agent”) was found superior for modifiability, scalability, and performance in the assessments. This architecture also explores the enhanced role of authentication, authorization, and accounting (AAA) and makes the base for complete orchestration. The results indicate that the proposed architecture can meet the requirements for a dedicated IoT network, which may be used in further research or as a reference for industry solutions. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.

When a model is built based on expert knowledge, a small data set will, in many cases, form the base for the model. It must be possible to validate the trustworthiness and model improvement potential of the provided information from humans or machines. In this study, we have investigated how to evaluate the information from humans to improve the model itself. We used evaluation research and collected the research data with the help of focus group interviews and questionnaires. The result of the study suggests a way to determine the trustworthiness of answers from humans and how to understand if these answers indicate a change to the underlying expert model. The introduction of divergence, and candidate areas, made it possible to evaluate the trustworthiness and changes to the expert model. These were deemed valuable by practitioners.