https://www.mdu.se/

Digitalization is a global trend becoming ever more important to our connected and sustainable society. This trend also affects industry where the Industrial Internet of Things is an important part, and there is a need to conserve spectrum as well as energy when communicating data to a fog or cloud back-end system. In this paper we investigate the benefits of fog computing by proposing a novel distributed learning model on the sensor device and simulating the data stream in the fog, instead of transmitting all raw sensor values to the cloud back-end. To save energy and to communicate as few packets as possible, the updated parameters of the learned model at the sensor device are communicated in longer time intervals to a fog computing system. The proposed framework is implemented and tested in a real world testbed in order to make quantitative measurements and evaluate the system. Our results show that the proposed model can achieve a 98% decrease in the number of packets sent over the wireless link, and the fog node can still simulate the data stream with an acceptable accuracy of 97%. We also observe an end-to-end delay of 180 ms in our proposed three-layer framework. Hence, the framework shows that a combination of fog and cloud computing with a distributed data modeling at the sensor device for wireless sensor networks can be beneficial for Industrial Internet of Things applications.

The network infrastructures in the future industrial networks need to accommodate, manage and guarantee performance to meet the converged Internet technology (IT) and operational technology (OT) traffics requirements. The pace of IT-OT networks development has been slow despite their considered benefits in optimizing the performance and enhancing information flows. The hindering factors vary from general challenges in performance management of the diverse traffic for green-field configuration to lack of outlines for evolving from brown-fields to the converged network. Focusing on the brown-field, this study provides additional insight into a brown-field characteristic to set a baseline that enables the subsequent step development towards the future’s expected converged networks. The case study highlights differences between real-world network behavior and the common assumptions for analyzing the network traffic covered in the literature. Considering the unsatisfactory performance of the existing methods for characterization of brownfield traffic, a performance and dynamics mixture measurement is proposed. The proposed method takes both IT and OT traffic into consideration and reduces the complexity, and consequently improves the flexibility, of performance and configuration management of the brown-field.

The industrial network infrastructures are transforming to a horizontal architecture to enable data availability for advanced applications and enhance flexibility for integrating new tech-nologies. The uninterrupted operation of the legacy systems needs to be ensured by safeguarding their requirements in network configuration and resource management. Network traffic modeling is essential in understanding the ongoing communication for resource estimation and configuration management. The presented work proposes a two-step approach for modeling aggregated traffic classes of brownfield installation. It first detects the repeated work-cycles and then aims to identify the operational states to profile their characteristics. The performance and influence of the approach are evaluated and validated in two experimental setups with data collected from an industrial plant in operation. The comparative results show that the proposed method successfully captures the temporal and spatial dynamics of the network traffic for characterization of various communication states in the operational work-cycles. 

Under the vision of industry 4.0, industrial networks are expected to accommodate a large amount of aggregated traffic of both operation and information technologies to enable the integration of innovative services and new applications. In this respect, guaranteeing the uninterrupted operation of the installed systems is an indisputable condition for network management. Network measurement and performance monitoring of the underlying communication states can provide invaluable insight for safeguarding the system performance by estimating required and available resources for flexible integration without risking network interruption or degrading network performance. In this work, we propose a data-driven in-band telemetry method to monitor the aggregated traffic of the network at the switch level. The method learns and models the communication states by local network-level measurement of communication intensity. The approximated model parameters provide information for network management for prognostic purposes and congestion avoidance resource planning when integrating new applications. Applying the method also addresses the consequence of telemetry data overhead on QoS since the transmission of telemetry packets can be done based on the current state of the network. The monitoring at the switch level is a step towards the Network-AI for future industrial networks.