Paper presented at KES-AMSTA 2019

Member of out project team, Renato Soic, participated in the conference KES-AMSTA which took place in St. Julians, Malta. KES-AMSTA is an international scientific conference for research in the field of agent and multi-agent systems. HR-SYNTH team presented its paper titled “Context-Aware Service Orchestration in Smart Environments”, which tackles the challenge of integrating complex services in smart environments. Our motivation was related to enabling speech synthesis in modern industrial and institutional smart systems.

 

Here is a short abstract of the paper:

With rapid technological advancements, smart systems have become an in-tegral part of human environments. Capabilities of such systems are evolv-ing constantly, resulting in broad areas of specific applications, ranging from personal to business and industrial use-cases. This has encouraged de-velopment of complex heterogeneous service ecosystems able to perform a wide variety of specific functionalities deployed on diverse physical nodes. Consequently, it has become a greater challenge to both maintain op-timal resource utilization and achieve reliable management and orchestra-tion of available services. For this purpose, we propose an agent-based sys-tem capable of orchestrating services on system nodes based on current con-text. This enables simplification of large-scale systems by introducing a ge-neric set of services available to all nodes in the system, while service acti-vation depends on environment state. The proposed solution provides flex-ibility in versatile environments typically encountered in domains such as smart homes and buildings, smart cities and Industry 4.0. Additionally, it enables reduced consumption of resources on a given physical node. The described system is evaluated using a case study in the smart building envi-ronment, where it is shown how the proposed model can simplify the sys-tem and reduce resource utilization.

The paper can be downloaded here: https://link.springer.com/chapter/10.1007/978-981-13-8679-4_3