Distributed Resource Distribution and Offloading for Resource-Agnostic Microservices in Industrial IoT

Due to increase in real-time mobile applications and Industrial Internet-of-Things (IIoT) devices, the edge computing paradigm provides a systematic and eccentric platform for real-time Internet-of-Things applications. Though the paradigm provides an effective infrastructure, however the resource requirements of IIoT devices change radically with time, which is described as a resource-agnostic property. Therefore, the estimation of resource requirements of IIoT devices is a critical and resilient assignment. In addition, it requires an extensive amount of resources to process the data traffic flows and microservice offloading. Hence, we present RAISE, a novel resource-agnostic microservice offloading scheme for mobile IIoT devices. RAISE efficiently estimates the resource-agnostic nature of IIoT devices to maximize their resource utilization in the network. Based on the estimated resource requirement, we propose a resource-agnostic microservice offloading scheme to maximize the success rate. Extensive experiments show that RAISE provides better performance in terms of network throughput and Quality-of-Service (QoS) than the other existing methods, SDTO and DTOS, in terms of cost and reliability.

Automated summary

Due to the increasing number of real-time mobile applications and Industrial Internet-of-Things (IIoT) devices, the edge computing paradigm has become a useful platform for real-time IoT applications. However, the varying resource requirements of IIoT devices pose a challenge for effective utilization. In this study, we propose a novel resource-agnostic microservice offloading scheme called RAISE, which efficiently estimates the resource requirements of IIoT devices and maximizes their utilization in the network. Experimental results demonstrate that RAISE outperforms existing methods, SDTO and DTOS, in terms of network throughput and Quality-of-Service (QoS), while also reducing cost and improving reliability.