Browsing by Author "Carvalho, Rodrigo"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
- A2PC: augmented advantage pointer-critic model for low latency on mobile IoT with edge computingPublication . Carvalho, Rodrigo; Al-Tam, Faroq; Correia, NoéliaAs a growing trend, edge computing infrastructures are starting to be integrated with Internet of Things (IoT) systems to facilitate time-critical applications. These systems often require the processing of data with limited usefulness in time, so the edge becomes vital in the development of such reactive IoT applications with real-time requirements. Although different architectural designs will always have advantages and disadvantages, mobile gateways appear to be particularly relevant in enabling this integration with the edge, particularly in the context of wide area networks with occasional data generation. In these scenarios, mobility planning is necessary, as aspects of the technology need to be aligned with the temporal needs of an application. The nature of this planning problem makes cutting-edge deep reinforcement learning (DRL) techniques useful in solving pertinent issues, such as having to deal with multiple dimensions in the action space while aiming for optimum levels of system performance. This article presents a novel scalable DRL model that incorporates a pointer-network (Ptr-Net) and an actor-critic algorithm to handle complex action spaces. The model synchronously determines the gateway location and visit time. Ultimately, the gateways are able to attain high-quality trajectory planning with reduced latency.
- Mobility planning of LoRa gateways for edge storage of IoT dataPublication . Carvalho, Rodrigo; Correia, Noélia; Al-Tam, FaroqLoRaWAN is now a leading technology in IoT developments due to its low power consumption and simple deployment features. Despite being termed a long-distance technology, its coverage is often hampered by the harsh propagation environment. In such cases, a very cost-effective solution is to use mobile gateways for both data collection and delivery at specific places of the edge, avoiding the need for cellular communication modules. This article addresses the optimization problem of deciding how mobile gateways should move, and which edge devices should be visited (and when) for collected data to be fed into the edge distributed storage, while ensuring data usefulness. This optimization problem of gateway mobility with edge storage is formulated mathematically, and a deep reinforcement learning framework is proposed to solve it. Results show that the proposed framework can achieve near optimal results, in particular for large-dense deployments and not very strict time windows. The proposed deep reinforcement learning solution is able to capture underlying patterns, like device coverage and traffic, without prior knowledge of such information.