Loading...
4 results
Search Results
Now showing 1 - 4 of 4
- Deep PC-MAC: a deep reinforcement learning pointer-critic media access protocolPublication . Al-Tam, Faroq; Mazayev, Andriy; Correia, Noélia; Rodriguez, J.Developing artificial intelligence (AI) solutions for communication problems is one of the hottest topics nowadays. This article presents Deep PC-MAC, a novel deep reinforcement learning (DRL) solution to solve the fair coexistence problem (FCP) between heterogeneous nodes in the unlicensed bands. It is based on a hybrid architecture between pointer networks (Ptr-nets) and advantage actor-critic (A2C), i.e., pointer-critic architecture. The proposed model allows base stations to fairly share unlicensed bands with incumbent nodes. It jointly protects the incumbent nodes from spectrum starvation and improves key-performance indicators (KPIs). Deep PC-MAC is trained from scratch with zero-knowledge about FCP and experimental results demonstrate its efficiency when compared to a baseline method.
- Attention-based model and deep reinforcement learning for distribution of event processing tasksPublication . Mazayev, Andriy; Al-Tam, Faroq; Correia, NoéliaEvent processing is the cornerstone of the dynamic and responsive Internet of Things (IoT). Recent approaches in this area are based on representational state transfer (REST) principles, which allow event processing tasks to be placed at any device that follows the same principles. However, the tasks should be properly distributed among edge devices to ensure fair resources utilization and guarantee seamless execution. This article investigates the use of deep learning to fairly distribute the tasks. An attention-based neural network model is proposed to generate efficient load balancing solutions under different scenarios. The proposed model is based on the Transformer and Pointer Network architectures, and is trained by an advantage actorcritic reinforcement learning algorithm. The model is designed to scale to the number of event processing tasks and the number of edge devices, with no need for hyperparameters re-tuning or even retraining. Extensive experimental results show that the proposed model outperforms conventional heuristics in many key performance indicators. The generic design and the obtained results show that the proposed model can potentially be applied to several other load balancing problem variations, which makes the proposal an attractive option to be used in real-world scenarios due to its scalability and efficiency.
- Radio Resource Scheduling with Deep Pointer Networks and Reinforcement LearningPublication . Al-Tam, Faroq; Mazayev, Andriy; Correia, Noélia; Rodriguez, J.This article presents an artificial intelligence (AI) adaptable solution to handle the radio resource scheduling (RRS) task in 5G networks. RRS is one of the core tasks in radio resource management (RRM) and aims to efficiently allocate frequency domain resources to users. The proposed solution is an advantage pointer critic (APC) deep reinforcement learning (DRL) agent. It is built with a deep pointer network architecture and trained by the policy gradient algorithm. The proposed agent is deployed in a system level simulator and the experimental results demonstrate its adaptability to network dynamics and efficiency when compared to baseline algorithms.
- Cognitive load balancing approach for 6G MEC serving IoT mashupsPublication . Attanasio, Barbara; Mazayev, Andriy; du Plessis, Shani; Correia, NoéliaThe sixth generation (6G) of communication networks represents more of a revolution than an evolution of the previous generations, providing new directions and innovative approaches to face the network challenges of the future. A crucial aspect is to make the best use of available resources for the support of an entirely new generation of services. From this viewpoint, the Web of Things (WoT), which enables Things to become Web Things to chain, use and re-use in IoT mashups, allows interoperability among IoT platforms. At the same time, Multi-access Edge Computing (MEC) brings computing and data storage to the edge of the network, which creates the so-called distributed and collective edge intelligence. Such intelligence is created in order to deal with the huge amount of data to be collected, analyzed and processed, from real word contexts, such as smart cities, which are evolving into dynamic and networked systems of people and things. To better exploit this architecture, it is crucial to break monolithic applications into modular microservices, which can be executed independently. Here, we propose an approach based on complex network theory and two weighted and interdependent multiplex networks to address the Microservices-compliant Load Balancing (McLB) problem in MEC infrastructure. Our findings show that the multiplex network representation represents an extra dimension of analysis, allowing to capture the complexity in WoT mashup organization and its impact on the organizational aspect of MEC servers. The impact of this extracted knowledge on the cognitive organization of MEC is quantified, through the use of heuristics that are engineered to guarantee load balancing and, consequently, QoS.