With the vigorous development of the Internet of Things, the Internet, cloud computing, and mobile terminals, edge computing has emerged as a new type of Internet of Things technology, which is one of the important components of the Industrial Internet of Things. In the face of large-scale data processing and calculations, traditional cloud computing is facing tremendous pressure, and the demand for new low-latency computing technologies is imminent. As a supplementary expansion of cloud computing technology, mobile edge computing will sink the computing power from the previous cloud to a network edge node. Through the mutual cooperation between computing nodes, the number of nodes that can be calculated is more, the types are more comprehensive, and the computing range is even greater. Broadly, it makes up for the shortcomings of cloud computing technology. Although edge computing technology has many advantages and has certain research and application results, how to allocate a large number of computing tasks and computing resources to computing nodes and how to schedule computing tasks at edge nodes are still challenges for edge computing. In view of the problems encountered by edge computing technology in resource allocation and task scheduling, this paper designs a dynamic task scheduling strategy for edge computing with delay-aware characteristics, which realizes the reasonable utilization of computing resources and is required for edge computing systems. This paper proposes a resource allocation scheme combined with the simulated annealing algorithm, which minimizes the overall performance loss of the system while keeping the system low delay. Finally, it is verified through experiments that the task scheduling and resource allocation methods proposed in this paper can significantly reduce the response delay of the application.
Resource Allocation for Latency-aware Federated Learning in Industrial Internet-of-Things
