Intelligent Computation Offloading and Resource Allocation in IIoT With End-Edge-Cloud Computing Using NSGA-III

Industrial Internet of Things (IIoT), which consists of massive IoT devices and industrial infrastructures such as wireless access points to acquire intelligent services, has been devoted as a critical physical information platform to realizing the fourth industrial revolution, otherwise known as Industry 4.0. Currently, a new paradigm called mobile edge computing (MEC) has brought an opportunity to accelerate the development of IIoT. It has powerful computing capabilities and can be well-used to provide low-latency services to execute some computation applications generated by IIoT devices. However, the existing methods may not be directly used for IIoT scenarios due to the large size of IIoT devices and the characteristics of the applications, as well as the limited and heterogeneous resources of edge servers. In view of this, the computation offloading and resource allocation are formulated as a multi-objective optimization problem, and an end-edge-cloud collaborative intelligent optimization method is devised in this paper. Comprehensive experiments and evaluations are carried out to prove the effectiveness and efficiency of our proposed method with regard to the energy consumption and time consumption of IIoT devices, as well as resource utilization and load balancing of edge servers.

Automated summary

This paper proposes an end-edge-cloud collaborative intelligent optimization method to address the challenges of computation offloading and resource allocation in IIoT scenarios. Comprehensive experiments and evaluations demonstrate the effectiveness and efficiency of the proposed method in terms of energy consumption, time consumption, resource utilization, and load balancing.