Neste trabalho, propõe-se um mecanismo baseado em aprendizado por reforço para escolher o modo de operação de um protocolo MAC híbrido, dependendo da carga de tráfego existente na rede sem-fio. Protocolos como esse combinam MAC do tipo CSMA/CA e TDMA, buscando proporcionar maiores vazões (throughput) e menores latências, e têm sido usados em redes de acesso sem-fio com tecnologia IEEE 802.11. Este trabalho apresenta um modelo para um controlador para esse tipo de MAC, o qual usa experiência para aprender a escolher o melhor modo de operação dependendo da percepção sobre o estado da rede.
Mobile ad hoc wireless network (MANETs) are characterized by a highly-dynamic topology where neither the duration of links between nodes nor their densities within the network can be foreseing. To better understand the effects of such issues in the medium access we provide a performance evaluation of two distinct MAC protocols. The first is our previously proposed HCT (Hybrid Contention/TDMA) Real-Time MAC protocol, which continuously adapts to topology modifications in order to provide a kind of coordinated medium access. Its performance is compared with a contentionbased, non-coordinated CSMA protocol, which is the typical MAC protocol used in MANETs. We analyze both protocols with respect to their ability to deliver messages in a timely manner. More specifically, we compared the ratio of messages delivered within their deadlines and the medium utilization provided by these protocols. Such aspects where analyzed considering mobile networks with different spatial densities and speeds of nodes. This study also addresses the protocols overhead, especially for HCT-MAC. Obtained results show that HCT-MAC appears as a good solution for applications like search-and-rescue, autonomous highway driving (platooning), and multimedia, which require some kind of QoS guarantee in respect to the timely delivery of messages.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.