A carregar...
2 resultados
Resultados da pesquisa
A mostrar 1 - 2 de 2
- Optimizing resource reuse in the web of thingsPublication . Gomes, Ruben; Correia, NoéliaThe Web of Things enables collecting vast amounts of data about the environment and sharing them over the Internet. Its popularity, however, has brought challenges under constrained environments, such as an increase in the number of connected devices, and a consequent additional consumption of resources, leading to the deterioration of communications and application response times. By discovering and reusing semantically equivalent Things among applications, resources may be spared and responsiveness improved. In this article, an optimization model is developed to address this issue, and both fair and unfair goals are used for performance comparison over multiple scenarios, with different levels of network connectivity, Thing equivalence and placement. Results show that the interplay between network connectivity and equivalence ratio is determinant for responsiveness improvement, and both parameters can be used for an adequate planning of which Thing hosts to reuse. Also, ensuring a fair responsiveness among applications imposes fewer reuses, particularly in low connectivity and equivalence conditions, than using unfair criteria, where some applications can benefit from high responsiveness while others don't. When a high equivalence ratio is coupled with a low connectivity degree, reuses tend to compound into fewer hosts, independently of fairness.
- Resilient wireless sensor actor networks through multi-objective self-adaptationPublication . Gomes, Ruben; Correia, NoéliaWireless Sensor Actor Networks (WSAN) are a key enabler of Internet of Things applications that demand timely and reliable data exchange under dynamic conditions. Among the various domains that benefit from these networks, precision agriculture stands out, demanding adaptive strategies for effective monitoring and control. This study proposes a reinforcement learning approach that leverages the Operationalization construct of the Self-Orchestrated Web of Things (SOrWoT) framework to enhance the adaptability of Things’ internal operations. A problem is formulated as a Markov Decision Process, and a Deep Q-Learning agent is trained in a custom simulation environment to identify the most suitable Operationalizations for optimizing data accuracy and latency, under changing conditions and communication failures. The results show that during normal operation the agent favored parallel sensor data averaging to minimize read error, but after an actor failure and the consequent increase in sensor-to-actor distances, it adapted by prioritizing latency through faster Operationalization choices. Sensitivity analyses further confirmed the agent’s ability to adjust policies in response to partial failures, and to shifts in the relative importance of latency versus accuracy. These findings demonstrate that reinforcement learning can autonomously optimize WSAN performance, contributing to resilient and self-adaptive systems.