Edge Intelligence: A Robust Reinforcement of Edge Computing and Artificial Intelligence

Parekh, Brinda; Amin, Kiran

doi:10.1007/978-3-030-66218-9_55

Cited by 3 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this way, mobile devices can offload particular tasks to a nearby base station or Access Points (APs) equipped with MEC server. Relying on the powerful computing capacity of MEC servers, it can significantly reduce the energy consumption and processing delay of computationally intensive tasks, meet latency sensitive requirements, and improve the Quality of Service (QoS) of mobile applications [3]. The emergence of the fifth generation of mobile communication system (5G) has led to an explosive growth of applications for mobile terminals [4].…”

Section: Introductionmentioning

confidence: 99%

Energy Consumption and Time-Delay Optimization of Dependency-Aware Tasks Offloading for Industry 5.0 Applications

Xu,

Lv,

Zhang

et al. 2024

IEEE Trans. Consumer Electron.

View full text Add to dashboard Cite

With the development of network and communication technology, artificial intelligence, distributed computing and beyond fifth-generation communications, Industry 5.0 is booming and obtains rapid growth. To improve the processing efficiency of intensive tasks, Mobile Edge Computing (MEC) technology can facilitate task offloading from mobile devices to edge servers. Traditional methods do not fully consider that applications are usually composed of dependency-aware tasks, which neglect the impact of task dependencies on offloading strategies and lead to low efficiency in task scheduling. This paper proposes a joint optimization of energy consumption and time delay for dependency-aware task offloading with mobile edge computing. First, in order to minimize the energy consumption and task processing of mobile device, a dependency-aware task offloading model is established. Secondly, the dependencies between tasks are analyzed to construct a Directed Acyclic Graph (DAG), and an algorithm based on topological ordering is introduced to obtain possible solutions for task scheduling. Furthermore, to minimize the total cost, an improved Particle Swarm Optimization (PSO) algorithm is used to obtain the optimal task offloading decision and MEC server selection optimization. Experimental results demonstrate that the proposed strategy can reduce the time cost and energy consumption compared to existing typical methods for tasks with different dependencies effectively.

show abstract

Section: Introductionmentioning

confidence: 99%