Task offloading decision in fog computing system

Deep Learning for Smart Industry: Efficient Manufacture Inspection System With Fog Computing

“…As a promising technology, fog computing aims to help mobile devices to operate tasks at the network edge directly [19], and is supposed to solve the ever-increasing computation in various scenarios of mobile applications [20]. For the Internet of Things (IoT), fog computing is adopted to improve the quality of service (QoS) [21].…”

“…Moreover, since additional data communication caused by offloading from the cloud to the network edge may incur more overhead, Qiliang Zhu et. al [19] design a task offloading policy for the fog computing model, which takes execution time, energy consumption and other costs into account. Furthermore, based on the challenges of cloud computing, fog computing is designed to deal with the situation of unreliable connectivity to the could [26].…”

A Dynamic Application-Partitioning Algorithm with Improved Offloading Mechanism for Fog Cloud Networks

“…Fog cloud and device computing environment and an energy-efficient with incentive-aware task offloading framework via network-assisted D2D has been investigated in [21], to observe the application performance and energy consumption tradeoffs. The present works [22,23] have proposed fog-cloud architecture and energy efficient task assignment and task scheduling methods emphasizing that all applications can be executed in a parallel manner in cloud-fog architecture. [24] stresses the same task assignment and scheduling approach via network-assisted D2D collaboration.…”

Descarga adaptativa em ambiente com névoa heterogênea: estudo de caso para a área da saúde

“…A grande maioria dos estudos presentes na literatura sobre descarga dinâmica usam, principalmente, duas métricas para avaliar a necessidade de executar uma tarefa remotamente: tempo de execução e consumo de energia (SHI et al, 2014;XIA et al, 2014;ANDRESEN, 2015;ZHU et al, 2017;LI et al, 2018;HUANG et al, 2019).…”

“…Similarmente ao custo local, o custo de latência da aplicação para a descarga dos dados considerou o atraso do processamento baseado na CPU do servidor (SHUKLA; MUNIR, 2017). Além disso, quando um dispositivo realiza a descarga dos dados de entrada, é necessário considerar os recursos gastos na transmissão dos dados e na recepção do resultado (ZHU et al, 2017;LI et al, 2018;HUANG et al, 2019). O custo de transmissão entre as camadas varia de acordo com a camada atual, local onde os dados de entrada estão sendo analisados, uma vez que os módulos do middleware são sincronizados em todas as camadas.…”